clinno commited on
Commit
21c6832
·
verified ·
1 Parent(s): e1228bb

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: other
4
+ base_model: clinno/eightwords-20241112
5
+ tags:
6
+ - llama-factory
7
+ - full
8
+ - generated_from_trainer
9
+ model-index:
10
+ - name: sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # sft
18
+
19
+ This model is a fine-tuned version of [clinno/eightwords-20241112](https://huggingface.co/clinno/eightwords-20241112) on the identity and the eightwords-241112 datasets.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.9320
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 1e-05
41
+ - train_batch_size: 2
42
+ - eval_batch_size: 1
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 8
45
+ - total_train_batch_size: 16
46
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.1
49
+ - num_epochs: 16.0
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-------:|:----:|:---------------:|
55
+ | 0.7759 | 4.4608 | 1000 | 1.0107 |
56
+ | 0.554 | 8.9215 | 2000 | 0.9391 |
57
+ | 0.423 | 13.3845 | 3000 | 0.9251 |
58
+
59
+
60
+ ### Framework versions
61
+
62
+ - Transformers 4.46.1
63
+ - Pytorch 2.5.0+cu121
64
+ - Datasets 3.1.0
65
+ - Tokenizers 0.20.3
all_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 15.988870339454646,
3
+ "eval_loss": 0.9320011138916016,
4
+ "eval_runtime": 17.1468,
5
+ "eval_samples_per_second": 23.328,
6
+ "eval_steps_per_second": 23.328,
7
+ "total_flos": 8.551781210951516e+17,
8
+ "train_loss": 0.7042842949075359,
9
+ "train_runtime": 4850.1152,
10
+ "train_samples_per_second": 11.853,
11
+ "train_steps_per_second": 0.739
12
+ }
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "clinno/eightwords-20241112",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 4096,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 14336,
15
+ "max_position_embeddings": 8192,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 32,
19
+ "num_hidden_layers": 32,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 500000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "bfloat16",
27
+ "transformers_version": "4.46.1",
28
+ "use_cache": false,
29
+ "vocab_size": 128256
30
+ }
eval_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 15.988870339454646,
3
+ "eval_loss": 0.9320011138916016,
4
+ "eval_runtime": 17.1468,
5
+ "eval_samples_per_second": 23.328,
6
+ "eval_steps_per_second": 23.328
7
+ }
generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 128000,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 128001,
6
+ 128009
7
+ ],
8
+ "max_length": 4096,
9
+ "temperature": 0.6,
10
+ "top_p": 0.9,
11
+ "transformers_version": "4.46.1"
12
+ }
model-00001-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef245996012af39168628a68f8f19c5ae1f991c2c367441a6ae6770930f88d23
3
+ size 4976698672
model-00002-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:081767a18a40b9a1163d9261e26f8d1417a816256cecbb212bf81529f36a8929
3
+ size 4999802720
model-00003-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d153a2b2aad001092897f1eb53f03c60a3f001007017028063e3aec1e4adf955
3
+ size 4915916176
model-00004-of-00004.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d27ec9f0fa6fbdd6c9bca924ea77dd8d2f8c49978de53fd7fdec0a981a5788de
3
+ size 1168138808
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 16060522496
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00004-of-00004.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
296
+ "model.norm.weight": "model-00004-of-00004.safetensors"
297
+ }
298
+ }
runs/Nov13_01-10-38_1c13a5dda409/events.out.tfevents.1731460260.1c13a5dda409.6510.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:170ea5c08e42ae0096bfc01184d604f30a982ba6e267893c30f9e40821f735b5
3
+ size 81942
runs/Nov13_01-10-38_1c13a5dda409/events.out.tfevents.1731465185.1c13a5dda409.6510.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82ef81864d293945391ba3d5fe3d27cdb6e108c984d2b7598a14269735f92a1e
3
+ size 359
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|begin_of_text|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|eot_id|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|eot_id|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c5cf44023714fb39b05e71e425f8d7b92805ff73f7988b083b8c87f0bf87393
3
+ size 17209961
tokenizer_config.json ADDED
@@ -0,0 +1,2065 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|reserved_special_token_2|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_3|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|reserved_special_token_4|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|reserved_special_token_5|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_6|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_7|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_8|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_9|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_10|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_11|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_12|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_13|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_14|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_15|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_16|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_17|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_18|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_19|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_20|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_21|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_22|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_23|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_24|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_25|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_26|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_27|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_28|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_29|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_30|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_31|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_32|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_33|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_34|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_35|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_36|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_37|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_38|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_39|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_40|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_41|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_42|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_43|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_44|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_45|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_46|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_47|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_48|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_49|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_50|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_51|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_52|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_53|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_54|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_55|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_56|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_57|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_58|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_59|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_60|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_61|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_62|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_63|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_64|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_65|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_66|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_67|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_68|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_69|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_70|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_71|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_72|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_73|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_74|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_75|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_76|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_77|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_78|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_79|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_80|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_81|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_82|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_83|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_84|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_85|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_86|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_87|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_88|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_89|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_90|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_91|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_92|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_93|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_94|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_95|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_96|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_97|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_98|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_99|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_100|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_101|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_102|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_103|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_104|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_105|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_106|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_107|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_108|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_109|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_110|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_111|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_112|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_113|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_114|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_115|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_116|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_117|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_118|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_119|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_120|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_121|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_122|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_123|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_124|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_125|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_126|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_127|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_128|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_129|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_130|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_131|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_132|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_133|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_134|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_135|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_136|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_137|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_138|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_139|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_140|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_141|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_142|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_143|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_144|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_145|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_146|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_147|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_148|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_149|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_150|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_151|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_152|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_153|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_154|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_155|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_156|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_157|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_158|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_159|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_160|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_161|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_162|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_163|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_164|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_165|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_166|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_167|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_168|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_169|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_170|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_171|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_172|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_173|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_174|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_175|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_176|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_177|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_178|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_179|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_180|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_181|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_182|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_183|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_184|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_185|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_186|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_187|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_188|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_189|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_190|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_191|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_192|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_193|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_194|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_195|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_196|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_197|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_198|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_199|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_200|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_201|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_202|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_203|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_204|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_205|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_206|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_207|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_208|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_209|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_210|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_211|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_212|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_213|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_214|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_215|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_216|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_217|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_218|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_219|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_220|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_221|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_222|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_223|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_224|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_225|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_226|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_227|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_228|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_229|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_230|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_231|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_232|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_233|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_234|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_235|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_236|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_237|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_238|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_239|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_240|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_241|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_242|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_243|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_244|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_245|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_246|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_247|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_248|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_249|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_250|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "bos_token": "<|begin_of_text|>",
2053
+ "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
+ "eos_token": "<|eot_id|>",
2056
+ "model_input_names": [
2057
+ "input_ids",
2058
+ "attention_mask"
2059
+ ],
2060
+ "model_max_length": 1000000000000000019884624838656,
2061
+ "pad_token": "<|eot_id|>",
2062
+ "padding_side": "right",
2063
+ "split_special_tokens": false,
2064
+ "tokenizer_class": "PreTrainedTokenizerFast"
2065
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 15.988870339454646,
3
+ "total_flos": 8.551781210951516e+17,
4
+ "train_loss": 0.7042842949075359,
5
+ "train_runtime": 4850.1152,
6
+ "train_samples_per_second": 11.853,
7
+ "train_steps_per_second": 0.739
8
+ }
trainer_log.jsonl ADDED
@@ -0,0 +1,362 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 10, "total_steps": 3584, "loss": 2.0545, "lr": 2.785515320334262e-07, "epoch": 0.044518642181413465, "percentage": 0.28, "elapsed_time": "0:00:18", "remaining_time": "1:51:33"}
2
+ {"current_steps": 20, "total_steps": 3584, "loss": 2.0294, "lr": 5.571030640668524e-07, "epoch": 0.08903728436282693, "percentage": 0.56, "elapsed_time": "0:00:36", "remaining_time": "1:48:19"}
3
+ {"current_steps": 30, "total_steps": 3584, "loss": 1.9841, "lr": 8.356545961002786e-07, "epoch": 0.1335559265442404, "percentage": 0.84, "elapsed_time": "0:00:54", "remaining_time": "1:47:04"}
4
+ {"current_steps": 40, "total_steps": 3584, "loss": 1.8176, "lr": 1.1142061281337048e-06, "epoch": 0.17807456872565386, "percentage": 1.12, "elapsed_time": "0:01:11", "remaining_time": "1:45:44"}
5
+ {"current_steps": 50, "total_steps": 3584, "loss": 1.6325, "lr": 1.392757660167131e-06, "epoch": 0.22259321090706732, "percentage": 1.4, "elapsed_time": "0:01:33", "remaining_time": "1:50:35"}
6
+ {"current_steps": 60, "total_steps": 3584, "loss": 1.6341, "lr": 1.6713091922005572e-06, "epoch": 0.2671118530884808, "percentage": 1.67, "elapsed_time": "0:02:05", "remaining_time": "2:02:47"}
7
+ {"current_steps": 70, "total_steps": 3584, "loss": 1.4943, "lr": 1.9498607242339835e-06, "epoch": 0.3116304952698943, "percentage": 1.95, "elapsed_time": "0:02:27", "remaining_time": "2:03:16"}
8
+ {"current_steps": 80, "total_steps": 3584, "loss": 1.4708, "lr": 2.2284122562674097e-06, "epoch": 0.3561491374513077, "percentage": 2.23, "elapsed_time": "0:02:46", "remaining_time": "2:01:47"}
9
+ {"current_steps": 90, "total_steps": 3584, "loss": 1.415, "lr": 2.506963788300836e-06, "epoch": 0.4006677796327212, "percentage": 2.51, "elapsed_time": "0:03:03", "remaining_time": "1:58:53"}
10
+ {"current_steps": 100, "total_steps": 3584, "loss": 1.4596, "lr": 2.785515320334262e-06, "epoch": 0.44518642181413465, "percentage": 2.79, "elapsed_time": "0:03:21", "remaining_time": "1:57:12"}
11
+ {"current_steps": 110, "total_steps": 3584, "loss": 1.4339, "lr": 3.064066852367688e-06, "epoch": 0.48970506399554814, "percentage": 3.07, "elapsed_time": "0:03:41", "remaining_time": "1:56:30"}
12
+ {"current_steps": 120, "total_steps": 3584, "loss": 1.4009, "lr": 3.3426183844011143e-06, "epoch": 0.5342237061769616, "percentage": 3.35, "elapsed_time": "0:03:59", "remaining_time": "1:55:23"}
13
+ {"current_steps": 130, "total_steps": 3584, "loss": 1.3688, "lr": 3.6211699164345405e-06, "epoch": 0.5787423483583751, "percentage": 3.63, "elapsed_time": "0:04:18", "remaining_time": "1:54:24"}
14
+ {"current_steps": 140, "total_steps": 3584, "loss": 1.3595, "lr": 3.899721448467967e-06, "epoch": 0.6232609905397886, "percentage": 3.91, "elapsed_time": "0:04:35", "remaining_time": "1:53:07"}
15
+ {"current_steps": 150, "total_steps": 3584, "loss": 1.3609, "lr": 4.178272980501394e-06, "epoch": 0.667779632721202, "percentage": 4.19, "elapsed_time": "0:04:53", "remaining_time": "1:52:09"}
16
+ {"current_steps": 160, "total_steps": 3584, "loss": 1.3777, "lr": 4.456824512534819e-06, "epoch": 0.7122982749026154, "percentage": 4.46, "elapsed_time": "0:05:10", "remaining_time": "1:50:44"}
17
+ {"current_steps": 170, "total_steps": 3584, "loss": 1.3374, "lr": 4.735376044568246e-06, "epoch": 0.756816917084029, "percentage": 4.74, "elapsed_time": "0:05:29", "remaining_time": "1:50:09"}
18
+ {"current_steps": 180, "total_steps": 3584, "loss": 1.3524, "lr": 5.013927576601672e-06, "epoch": 0.8013355592654424, "percentage": 5.02, "elapsed_time": "0:05:46", "remaining_time": "1:49:18"}
19
+ {"current_steps": 190, "total_steps": 3584, "loss": 1.3153, "lr": 5.292479108635098e-06, "epoch": 0.8458542014468559, "percentage": 5.3, "elapsed_time": "0:06:03", "remaining_time": "1:48:09"}
20
+ {"current_steps": 200, "total_steps": 3584, "loss": 1.3519, "lr": 5.571030640668524e-06, "epoch": 0.8903728436282693, "percentage": 5.58, "elapsed_time": "0:06:20", "remaining_time": "1:47:22"}
21
+ {"current_steps": 210, "total_steps": 3584, "loss": 1.348, "lr": 5.849582172701951e-06, "epoch": 0.9348914858096828, "percentage": 5.86, "elapsed_time": "0:06:37", "remaining_time": "1:46:29"}
22
+ {"current_steps": 220, "total_steps": 3584, "loss": 1.3062, "lr": 6.128133704735376e-06, "epoch": 0.9794101279910963, "percentage": 6.14, "elapsed_time": "0:06:54", "remaining_time": "1:45:35"}
23
+ {"current_steps": 230, "total_steps": 3584, "loss": 1.4358, "lr": 6.406685236768803e-06, "epoch": 1.0261547022815805, "percentage": 6.42, "elapsed_time": "0:07:10", "remaining_time": "1:44:39"}
24
+ {"current_steps": 240, "total_steps": 3584, "loss": 1.2481, "lr": 6.685236768802229e-06, "epoch": 1.070673344462994, "percentage": 6.7, "elapsed_time": "0:07:28", "remaining_time": "1:44:03"}
25
+ {"current_steps": 250, "total_steps": 3584, "loss": 1.2833, "lr": 6.963788300835655e-06, "epoch": 1.1151919866444073, "percentage": 6.98, "elapsed_time": "0:07:45", "remaining_time": "1:43:22"}
26
+ {"current_steps": 260, "total_steps": 3584, "loss": 1.1941, "lr": 7.242339832869081e-06, "epoch": 1.1597106288258208, "percentage": 7.25, "elapsed_time": "0:08:01", "remaining_time": "1:42:35"}
27
+ {"current_steps": 270, "total_steps": 3584, "loss": 1.2831, "lr": 7.5208913649025075e-06, "epoch": 1.2042292710072342, "percentage": 7.53, "elapsed_time": "0:08:17", "remaining_time": "1:41:43"}
28
+ {"current_steps": 280, "total_steps": 3584, "loss": 1.2854, "lr": 7.799442896935934e-06, "epoch": 1.2487479131886476, "percentage": 7.81, "elapsed_time": "0:08:33", "remaining_time": "1:40:56"}
29
+ {"current_steps": 290, "total_steps": 3584, "loss": 1.257, "lr": 8.07799442896936e-06, "epoch": 1.293266555370061, "percentage": 8.09, "elapsed_time": "0:08:49", "remaining_time": "1:40:12"}
30
+ {"current_steps": 300, "total_steps": 3584, "loss": 1.2468, "lr": 8.356545961002787e-06, "epoch": 1.3377851975514747, "percentage": 8.37, "elapsed_time": "0:09:06", "remaining_time": "1:39:39"}
31
+ {"current_steps": 310, "total_steps": 3584, "loss": 1.2743, "lr": 8.635097493036211e-06, "epoch": 1.3823038397328882, "percentage": 8.65, "elapsed_time": "0:09:21", "remaining_time": "1:38:53"}
32
+ {"current_steps": 320, "total_steps": 3584, "loss": 1.2265, "lr": 8.913649025069639e-06, "epoch": 1.4268224819143016, "percentage": 8.93, "elapsed_time": "0:09:37", "remaining_time": "1:38:10"}
33
+ {"current_steps": 330, "total_steps": 3584, "loss": 1.2898, "lr": 9.192200557103064e-06, "epoch": 1.471341124095715, "percentage": 9.21, "elapsed_time": "0:09:53", "remaining_time": "1:37:31"}
34
+ {"current_steps": 340, "total_steps": 3584, "loss": 1.2406, "lr": 9.470752089136492e-06, "epoch": 1.5158597662771287, "percentage": 9.49, "elapsed_time": "0:10:09", "remaining_time": "1:36:50"}
35
+ {"current_steps": 350, "total_steps": 3584, "loss": 1.2098, "lr": 9.749303621169918e-06, "epoch": 1.5603784084585421, "percentage": 9.77, "elapsed_time": "0:10:24", "remaining_time": "1:36:14"}
36
+ {"current_steps": 360, "total_steps": 3584, "loss": 1.2067, "lr": 9.9999976276417e-06, "epoch": 1.6048970506399556, "percentage": 10.04, "elapsed_time": "0:10:40", "remaining_time": "1:35:34"}
37
+ {"current_steps": 370, "total_steps": 3584, "loss": 1.2338, "lr": 9.999712947369595e-06, "epoch": 1.649415692821369, "percentage": 10.32, "elapsed_time": "0:10:55", "remaining_time": "1:34:55"}
38
+ {"current_steps": 380, "total_steps": 3584, "loss": 1.2546, "lr": 9.998953826391322e-06, "epoch": 1.6939343350027825, "percentage": 10.6, "elapsed_time": "0:11:10", "remaining_time": "1:34:16"}
39
+ {"current_steps": 390, "total_steps": 3584, "loss": 1.201, "lr": 9.997720336742596e-06, "epoch": 1.738452977184196, "percentage": 10.88, "elapsed_time": "0:11:25", "remaining_time": "1:33:36"}
40
+ {"current_steps": 400, "total_steps": 3584, "loss": 1.1761, "lr": 9.996012595473676e-06, "epoch": 1.7829716193656093, "percentage": 11.16, "elapsed_time": "0:11:41", "remaining_time": "1:33:04"}
41
+ {"current_steps": 410, "total_steps": 3584, "loss": 1.1884, "lr": 9.993830764638262e-06, "epoch": 1.8274902615470228, "percentage": 11.44, "elapsed_time": "0:11:56", "remaining_time": "1:32:25"}
42
+ {"current_steps": 420, "total_steps": 3584, "loss": 1.1951, "lr": 9.991175051278111e-06, "epoch": 1.8720089037284362, "percentage": 11.72, "elapsed_time": "0:12:11", "remaining_time": "1:31:49"}
43
+ {"current_steps": 430, "total_steps": 3584, "loss": 1.175, "lr": 9.988045707403394e-06, "epoch": 1.9165275459098496, "percentage": 12.0, "elapsed_time": "0:12:26", "remaining_time": "1:31:12"}
44
+ {"current_steps": 440, "total_steps": 3584, "loss": 1.2045, "lr": 9.984443029968786e-06, "epoch": 1.961046188091263, "percentage": 12.28, "elapsed_time": "0:12:40", "remaining_time": "1:30:37"}
45
+ {"current_steps": 450, "total_steps": 3584, "loss": 1.3052, "lr": 9.980367360845278e-06, "epoch": 2.0077907623817475, "percentage": 12.56, "elapsed_time": "0:12:56", "remaining_time": "1:30:06"}
46
+ {"current_steps": 460, "total_steps": 3584, "loss": 1.1092, "lr": 9.975819086787743e-06, "epoch": 2.052309404563161, "percentage": 12.83, "elapsed_time": "0:13:10", "remaining_time": "1:29:30"}
47
+ {"current_steps": 470, "total_steps": 3584, "loss": 1.1435, "lr": 9.970798639398228e-06, "epoch": 2.0968280467445743, "percentage": 13.11, "elapsed_time": "0:13:25", "remaining_time": "1:28:55"}
48
+ {"current_steps": 480, "total_steps": 3584, "loss": 1.0927, "lr": 9.965306495085005e-06, "epoch": 2.141346688925988, "percentage": 13.39, "elapsed_time": "0:13:39", "remaining_time": "1:28:21"}
49
+ {"current_steps": 490, "total_steps": 3584, "loss": 1.0692, "lr": 9.959343175017362e-06, "epoch": 2.185865331107401, "percentage": 13.67, "elapsed_time": "0:13:54", "remaining_time": "1:27:48"}
50
+ {"current_steps": 500, "total_steps": 3584, "loss": 1.0603, "lr": 9.952909245076141e-06, "epoch": 2.2303839732888147, "percentage": 13.95, "elapsed_time": "0:14:09", "remaining_time": "1:27:20"}
51
+ {"current_steps": 510, "total_steps": 3584, "loss": 1.0717, "lr": 9.946005315800047e-06, "epoch": 2.274902615470228, "percentage": 14.23, "elapsed_time": "0:14:23", "remaining_time": "1:26:46"}
52
+ {"current_steps": 520, "total_steps": 3584, "loss": 1.0808, "lr": 9.93863204232771e-06, "epoch": 2.3194212576516415, "percentage": 14.51, "elapsed_time": "0:14:37", "remaining_time": "1:26:11"}
53
+ {"current_steps": 530, "total_steps": 3584, "loss": 1.0297, "lr": 9.930790124335511e-06, "epoch": 2.363939899833055, "percentage": 14.79, "elapsed_time": "0:14:52", "remaining_time": "1:25:40"}
54
+ {"current_steps": 540, "total_steps": 3584, "loss": 1.0481, "lr": 9.922480305971193e-06, "epoch": 2.4084585420144684, "percentage": 15.07, "elapsed_time": "0:15:06", "remaining_time": "1:25:09"}
55
+ {"current_steps": 550, "total_steps": 3584, "loss": 1.0919, "lr": 9.91370337578325e-06, "epoch": 2.452977184195882, "percentage": 15.35, "elapsed_time": "0:15:21", "remaining_time": "1:24:41"}
56
+ {"current_steps": 560, "total_steps": 3584, "loss": 1.0835, "lr": 9.904460166646084e-06, "epoch": 2.4974958263772953, "percentage": 15.62, "elapsed_time": "0:15:35", "remaining_time": "1:24:11"}
57
+ {"current_steps": 570, "total_steps": 3584, "loss": 1.0336, "lr": 9.894751555680988e-06, "epoch": 2.542014468558709, "percentage": 15.9, "elapsed_time": "0:15:49", "remaining_time": "1:23:38"}
58
+ {"current_steps": 580, "total_steps": 3584, "loss": 1.0728, "lr": 9.884578464172901e-06, "epoch": 2.586533110740122, "percentage": 16.18, "elapsed_time": "0:16:03", "remaining_time": "1:23:07"}
59
+ {"current_steps": 590, "total_steps": 3584, "loss": 1.0493, "lr": 9.873941857482988e-06, "epoch": 2.631051752921536, "percentage": 16.46, "elapsed_time": "0:16:17", "remaining_time": "1:22:38"}
60
+ {"current_steps": 600, "total_steps": 3584, "loss": 1.0346, "lr": 9.862842744957037e-06, "epoch": 2.6755703951029495, "percentage": 16.74, "elapsed_time": "0:16:31", "remaining_time": "1:22:12"}
61
+ {"current_steps": 610, "total_steps": 3584, "loss": 1.0483, "lr": 9.85128217982967e-06, "epoch": 2.720089037284363, "percentage": 17.02, "elapsed_time": "0:16:45", "remaining_time": "1:21:41"}
62
+ {"current_steps": 620, "total_steps": 3584, "loss": 1.0384, "lr": 9.8392612591244e-06, "epoch": 2.7646076794657763, "percentage": 17.3, "elapsed_time": "0:16:58", "remaining_time": "1:21:09"}
63
+ {"current_steps": 630, "total_steps": 3584, "loss": 1.0266, "lr": 9.826781123549542e-06, "epoch": 2.80912632164719, "percentage": 17.58, "elapsed_time": "0:17:12", "remaining_time": "1:20:39"}
64
+ {"current_steps": 640, "total_steps": 3584, "loss": 1.0352, "lr": 9.813842957389953e-06, "epoch": 2.853644963828603, "percentage": 17.86, "elapsed_time": "0:17:26", "remaining_time": "1:20:12"}
65
+ {"current_steps": 650, "total_steps": 3584, "loss": 1.009, "lr": 9.800447988394657e-06, "epoch": 2.8981636060100167, "percentage": 18.14, "elapsed_time": "0:17:40", "remaining_time": "1:19:47"}
66
+ {"current_steps": 660, "total_steps": 3584, "loss": 1.0834, "lr": 9.786597487660336e-06, "epoch": 2.94268224819143, "percentage": 18.42, "elapsed_time": "0:17:53", "remaining_time": "1:19:16"}
67
+ {"current_steps": 670, "total_steps": 3584, "loss": 1.0735, "lr": 9.772292769510718e-06, "epoch": 2.9872008903728435, "percentage": 18.69, "elapsed_time": "0:18:07", "remaining_time": "1:18:49"}
68
+ {"current_steps": 680, "total_steps": 3584, "loss": 1.0532, "lr": 9.75753519137185e-06, "epoch": 3.033945464663328, "percentage": 18.97, "elapsed_time": "0:18:20", "remaining_time": "1:18:21"}
69
+ {"current_steps": 690, "total_steps": 3584, "loss": 0.9169, "lr": 9.742326153643285e-06, "epoch": 3.0784641068447414, "percentage": 19.25, "elapsed_time": "0:18:34", "remaining_time": "1:17:54"}
70
+ {"current_steps": 700, "total_steps": 3584, "loss": 0.9443, "lr": 9.726667099565202e-06, "epoch": 3.122982749026155, "percentage": 19.53, "elapsed_time": "0:18:47", "remaining_time": "1:17:26"}
71
+ {"current_steps": 710, "total_steps": 3584, "loss": 0.9023, "lr": 9.710559515081446e-06, "epoch": 3.1675013912075682, "percentage": 19.81, "elapsed_time": "0:19:01", "remaining_time": "1:17:00"}
72
+ {"current_steps": 720, "total_steps": 3584, "loss": 0.9227, "lr": 9.69400492869852e-06, "epoch": 3.2120200333889817, "percentage": 20.09, "elapsed_time": "0:19:14", "remaining_time": "1:16:32"}
73
+ {"current_steps": 730, "total_steps": 3584, "loss": 0.9329, "lr": 9.677004911340539e-06, "epoch": 3.256538675570395, "percentage": 20.37, "elapsed_time": "0:19:27", "remaining_time": "1:16:03"}
74
+ {"current_steps": 740, "total_steps": 3584, "loss": 0.903, "lr": 9.659561076200173e-06, "epoch": 3.3010573177518086, "percentage": 20.65, "elapsed_time": "0:19:40", "remaining_time": "1:15:35"}
75
+ {"current_steps": 750, "total_steps": 3584, "loss": 0.9046, "lr": 9.64167507858554e-06, "epoch": 3.345575959933222, "percentage": 20.93, "elapsed_time": "0:19:53", "remaining_time": "1:15:08"}
76
+ {"current_steps": 760, "total_steps": 3584, "loss": 0.927, "lr": 9.62334861576315e-06, "epoch": 3.3900946021146354, "percentage": 21.21, "elapsed_time": "0:20:06", "remaining_time": "1:14:43"}
77
+ {"current_steps": 770, "total_steps": 3584, "loss": 0.9274, "lr": 9.604583426796837e-06, "epoch": 3.434613244296049, "percentage": 21.48, "elapsed_time": "0:20:19", "remaining_time": "1:14:16"}
78
+ {"current_steps": 780, "total_steps": 3584, "loss": 0.9127, "lr": 9.585381292382734e-06, "epoch": 3.4791318864774623, "percentage": 21.76, "elapsed_time": "0:20:31", "remaining_time": "1:13:48"}
79
+ {"current_steps": 790, "total_steps": 3584, "loss": 0.9269, "lr": 9.565744034680291e-06, "epoch": 3.5236505286588757, "percentage": 22.04, "elapsed_time": "0:20:44", "remaining_time": "1:13:20"}
80
+ {"current_steps": 800, "total_steps": 3584, "loss": 0.8863, "lr": 9.545673517139376e-06, "epoch": 3.5681691708402896, "percentage": 22.32, "elapsed_time": "0:20:56", "remaining_time": "1:12:54"}
81
+ {"current_steps": 810, "total_steps": 3584, "loss": 0.8776, "lr": 9.52517164432343e-06, "epoch": 3.6126878130217026, "percentage": 22.6, "elapsed_time": "0:21:09", "remaining_time": "1:12:26"}
82
+ {"current_steps": 820, "total_steps": 3584, "loss": 0.9424, "lr": 9.50424036172875e-06, "epoch": 3.6572064552031165, "percentage": 22.88, "elapsed_time": "0:21:21", "remaining_time": "1:11:58"}
83
+ {"current_steps": 830, "total_steps": 3584, "loss": 0.8712, "lr": 9.482881655599867e-06, "epoch": 3.70172509738453, "percentage": 23.16, "elapsed_time": "0:21:33", "remaining_time": "1:11:32"}
84
+ {"current_steps": 840, "total_steps": 3584, "loss": 0.9157, "lr": 9.461097552741065e-06, "epoch": 3.7462437395659434, "percentage": 23.44, "elapsed_time": "0:21:45", "remaining_time": "1:11:05"}
85
+ {"current_steps": 850, "total_steps": 3584, "loss": 0.8571, "lr": 9.438890120324049e-06, "epoch": 3.790762381747357, "percentage": 23.72, "elapsed_time": "0:21:58", "remaining_time": "1:10:40"}
86
+ {"current_steps": 860, "total_steps": 3584, "loss": 0.861, "lr": 9.416261465691786e-06, "epoch": 3.8352810239287702, "percentage": 24.0, "elapsed_time": "0:22:10", "remaining_time": "1:10:13"}
87
+ {"current_steps": 870, "total_steps": 3584, "loss": 0.8952, "lr": 9.393213736158532e-06, "epoch": 3.8797996661101837, "percentage": 24.27, "elapsed_time": "0:22:22", "remaining_time": "1:09:47"}
88
+ {"current_steps": 880, "total_steps": 3584, "loss": 0.8598, "lr": 9.369749118806063e-06, "epoch": 3.924318308291597, "percentage": 24.55, "elapsed_time": "0:22:34", "remaining_time": "1:09:20"}
89
+ {"current_steps": 890, "total_steps": 3584, "loss": 0.8614, "lr": 9.345869840276138e-06, "epoch": 3.9688369504730105, "percentage": 24.83, "elapsed_time": "0:22:45", "remaining_time": "1:08:54"}
90
+ {"current_steps": 900, "total_steps": 3584, "loss": 0.8842, "lr": 9.321578166559202e-06, "epoch": 4.015581524763495, "percentage": 25.11, "elapsed_time": "0:22:58", "remaining_time": "1:08:29"}
91
+ {"current_steps": 910, "total_steps": 3584, "loss": 0.7889, "lr": 9.296876402779357e-06, "epoch": 4.060100166944908, "percentage": 25.39, "elapsed_time": "0:23:09", "remaining_time": "1:08:02"}
92
+ {"current_steps": 920, "total_steps": 3584, "loss": 0.8188, "lr": 9.271766892975632e-06, "epoch": 4.104618809126322, "percentage": 25.67, "elapsed_time": "0:23:20", "remaining_time": "1:07:36"}
93
+ {"current_steps": 930, "total_steps": 3584, "loss": 0.7822, "lr": 9.246252019879526e-06, "epoch": 4.149137451307735, "percentage": 25.95, "elapsed_time": "0:23:32", "remaining_time": "1:07:11"}
94
+ {"current_steps": 940, "total_steps": 3584, "loss": 0.8268, "lr": 9.22033420468893e-06, "epoch": 4.193656093489149, "percentage": 26.23, "elapsed_time": "0:23:44", "remaining_time": "1:06:45"}
95
+ {"current_steps": 950, "total_steps": 3584, "loss": 0.7838, "lr": 9.194015906838345e-06, "epoch": 4.238174735670562, "percentage": 26.51, "elapsed_time": "0:23:56", "remaining_time": "1:06:22"}
96
+ {"current_steps": 960, "total_steps": 3584, "loss": 0.7691, "lr": 9.167299623765515e-06, "epoch": 4.282693377851976, "percentage": 26.79, "elapsed_time": "0:24:07", "remaining_time": "1:05:57"}
97
+ {"current_steps": 970, "total_steps": 3584, "loss": 0.7575, "lr": 9.14018789067443e-06, "epoch": 4.3272120200333895, "percentage": 27.06, "elapsed_time": "0:24:18", "remaining_time": "1:05:31"}
98
+ {"current_steps": 980, "total_steps": 3584, "loss": 0.8305, "lr": 9.11268328029475e-06, "epoch": 4.371730662214802, "percentage": 27.34, "elapsed_time": "0:24:29", "remaining_time": "1:05:05"}
99
+ {"current_steps": 990, "total_steps": 3584, "loss": 0.7607, "lr": 9.08478840263767e-06, "epoch": 4.416249304396216, "percentage": 27.62, "elapsed_time": "0:24:41", "remaining_time": "1:04:41"}
100
+ {"current_steps": 1000, "total_steps": 3584, "loss": 0.7759, "lr": 9.05650590474825e-06, "epoch": 4.460767946577629, "percentage": 27.9, "elapsed_time": "0:24:52", "remaining_time": "1:04:17"}
101
+ {"current_steps": 1000, "total_steps": 3584, "eval_loss": 1.0106589794158936, "epoch": 4.460767946577629, "percentage": 27.9, "elapsed_time": "0:25:38", "remaining_time": "1:06:16"}
102
+ {"current_steps": 1010, "total_steps": 3584, "loss": 0.7025, "lr": 9.027838470454222e-06, "epoch": 4.505286588759043, "percentage": 28.18, "elapsed_time": "0:25:50", "remaining_time": "1:05:51"}
103
+ {"current_steps": 1020, "total_steps": 3584, "loss": 0.776, "lr": 8.998788820111323e-06, "epoch": 4.549805230940456, "percentage": 28.46, "elapsed_time": "0:26:01", "remaining_time": "1:05:24"}
104
+ {"current_steps": 1030, "total_steps": 3584, "loss": 0.8328, "lr": 8.969359710345132e-06, "epoch": 4.59432387312187, "percentage": 28.74, "elapsed_time": "0:26:11", "remaining_time": "1:04:57"}
105
+ {"current_steps": 1040, "total_steps": 3584, "loss": 0.7564, "lr": 8.939553933789499e-06, "epoch": 4.638842515303283, "percentage": 29.02, "elapsed_time": "0:26:22", "remaining_time": "1:04:30"}
106
+ {"current_steps": 1050, "total_steps": 3584, "loss": 0.7684, "lr": 8.90937431882154e-06, "epoch": 4.683361157484697, "percentage": 29.3, "elapsed_time": "0:26:33", "remaining_time": "1:04:05"}
107
+ {"current_steps": 1060, "total_steps": 3584, "loss": 0.8135, "lr": 8.878823729293238e-06, "epoch": 4.72787979966611, "percentage": 29.58, "elapsed_time": "0:26:44", "remaining_time": "1:03:39"}
108
+ {"current_steps": 1070, "total_steps": 3584, "loss": 0.8271, "lr": 8.847905064259683e-06, "epoch": 4.772398441847524, "percentage": 29.85, "elapsed_time": "0:26:54", "remaining_time": "1:03:13"}
109
+ {"current_steps": 1080, "total_steps": 3584, "loss": 0.8179, "lr": 8.816621257703969e-06, "epoch": 4.816917084028937, "percentage": 30.13, "elapsed_time": "0:27:04", "remaining_time": "1:02:46"}
110
+ {"current_steps": 1090, "total_steps": 3584, "loss": 0.7721, "lr": 8.784975278258783e-06, "epoch": 4.861435726210351, "percentage": 30.41, "elapsed_time": "0:27:15", "remaining_time": "1:02:21"}
111
+ {"current_steps": 1100, "total_steps": 3584, "loss": 0.7752, "lr": 8.752970128924696e-06, "epoch": 4.905954368391764, "percentage": 30.69, "elapsed_time": "0:27:25", "remaining_time": "1:01:56"}
112
+ {"current_steps": 1110, "total_steps": 3584, "loss": 0.788, "lr": 8.7206088467852e-06, "epoch": 4.950473010573178, "percentage": 30.97, "elapsed_time": "0:27:35", "remaining_time": "1:01:30"}
113
+ {"current_steps": 1120, "total_steps": 3584, "loss": 0.8012, "lr": 8.687894502718503e-06, "epoch": 4.994991652754591, "percentage": 31.25, "elapsed_time": "0:27:45", "remaining_time": "1:01:04"}
114
+ {"current_steps": 1130, "total_steps": 3584, "loss": 0.8055, "lr": 8.654830201106133e-06, "epoch": 5.041736227045075, "percentage": 31.53, "elapsed_time": "0:27:56", "remaining_time": "1:00:39"}
115
+ {"current_steps": 1140, "total_steps": 3584, "loss": 0.7483, "lr": 8.621419079538337e-06, "epoch": 5.086254869226488, "percentage": 31.81, "elapsed_time": "0:28:06", "remaining_time": "1:00:14"}
116
+ {"current_steps": 1150, "total_steps": 3584, "loss": 0.7349, "lr": 8.587664308516361e-06, "epoch": 5.130773511407902, "percentage": 32.09, "elapsed_time": "0:28:16", "remaining_time": "0:59:50"}
117
+ {"current_steps": 1160, "total_steps": 3584, "loss": 0.7454, "lr": 8.553569091151576e-06, "epoch": 5.175292153589315, "percentage": 32.37, "elapsed_time": "0:28:26", "remaining_time": "0:59:25"}
118
+ {"current_steps": 1170, "total_steps": 3584, "loss": 0.6866, "lr": 8.519136662861531e-06, "epoch": 5.219810795770729, "percentage": 32.65, "elapsed_time": "0:28:36", "remaining_time": "0:59:01"}
119
+ {"current_steps": 1180, "total_steps": 3584, "loss": 0.7269, "lr": 8.484370291062927e-06, "epoch": 5.264329437952142, "percentage": 32.92, "elapsed_time": "0:28:46", "remaining_time": "0:58:37"}
120
+ {"current_steps": 1190, "total_steps": 3584, "loss": 0.6977, "lr": 8.449273274861566e-06, "epoch": 5.308848080133556, "percentage": 33.2, "elapsed_time": "0:28:56", "remaining_time": "0:58:12"}
121
+ {"current_steps": 1200, "total_steps": 3584, "loss": 0.6814, "lr": 8.413848944739282e-06, "epoch": 5.353366722314969, "percentage": 33.48, "elapsed_time": "0:29:06", "remaining_time": "0:57:49"}
122
+ {"current_steps": 1210, "total_steps": 3584, "loss": 0.7206, "lr": 8.378100662237904e-06, "epoch": 5.397885364496383, "percentage": 33.76, "elapsed_time": "0:29:16", "remaining_time": "0:57:25"}
123
+ {"current_steps": 1220, "total_steps": 3584, "loss": 0.7317, "lr": 8.342031819640263e-06, "epoch": 5.442404006677796, "percentage": 34.04, "elapsed_time": "0:29:25", "remaining_time": "0:57:00"}
124
+ {"current_steps": 1230, "total_steps": 3584, "loss": 0.7149, "lr": 8.305645839648287e-06, "epoch": 5.48692264885921, "percentage": 34.32, "elapsed_time": "0:29:34", "remaining_time": "0:56:36"}
125
+ {"current_steps": 1240, "total_steps": 3584, "loss": 0.6568, "lr": 8.268946175058214e-06, "epoch": 5.531441291040624, "percentage": 34.6, "elapsed_time": "0:29:44", "remaining_time": "0:56:12"}
126
+ {"current_steps": 1250, "total_steps": 3584, "loss": 0.7292, "lr": 8.231936308432935e-06, "epoch": 5.575959933222037, "percentage": 34.88, "elapsed_time": "0:29:53", "remaining_time": "0:55:49"}
127
+ {"current_steps": 1260, "total_steps": 3584, "loss": 0.6966, "lr": 8.194619751771527e-06, "epoch": 5.6204785754034505, "percentage": 35.16, "elapsed_time": "0:30:02", "remaining_time": "0:55:25"}
128
+ {"current_steps": 1270, "total_steps": 3584, "loss": 0.7128, "lr": 8.157000046175984e-06, "epoch": 5.6649972175848635, "percentage": 35.44, "elapsed_time": "0:30:11", "remaining_time": "0:55:01"}
129
+ {"current_steps": 1280, "total_steps": 3584, "loss": 0.7343, "lr": 8.119080761515197e-06, "epoch": 5.709515859766277, "percentage": 35.71, "elapsed_time": "0:30:20", "remaining_time": "0:54:37"}
130
+ {"current_steps": 1290, "total_steps": 3584, "loss": 0.7454, "lr": 8.080865496086177e-06, "epoch": 5.75403450194769, "percentage": 35.99, "elapsed_time": "0:30:29", "remaining_time": "0:54:13"}
131
+ {"current_steps": 1300, "total_steps": 3584, "loss": 0.7337, "lr": 8.042357876272626e-06, "epoch": 5.798553144129104, "percentage": 36.27, "elapsed_time": "0:30:39", "remaining_time": "0:53:51"}
132
+ {"current_steps": 1310, "total_steps": 3584, "loss": 0.7011, "lr": 8.003561556200796e-06, "epoch": 5.843071786310517, "percentage": 36.55, "elapsed_time": "0:30:48", "remaining_time": "0:53:28"}
133
+ {"current_steps": 1320, "total_steps": 3584, "loss": 0.6969, "lr": 7.964480217392739e-06, "epoch": 5.887590428491931, "percentage": 36.83, "elapsed_time": "0:30:56", "remaining_time": "0:53:04"}
134
+ {"current_steps": 1330, "total_steps": 3584, "loss": 0.7272, "lr": 7.925117568416966e-06, "epoch": 5.932109070673344, "percentage": 37.11, "elapsed_time": "0:31:05", "remaining_time": "0:52:41"}
135
+ {"current_steps": 1340, "total_steps": 3584, "loss": 0.6795, "lr": 7.885477344536516e-06, "epoch": 5.976627712854758, "percentage": 37.39, "elapsed_time": "0:31:14", "remaining_time": "0:52:18"}
136
+ {"current_steps": 1350, "total_steps": 3584, "loss": 0.7507, "lr": 7.845563307354506e-06, "epoch": 6.023372287145242, "percentage": 37.67, "elapsed_time": "0:31:23", "remaining_time": "0:51:56"}
137
+ {"current_steps": 1360, "total_steps": 3584, "loss": 0.6812, "lr": 7.80537924445718e-06, "epoch": 6.067890929326656, "percentage": 37.95, "elapsed_time": "0:31:31", "remaining_time": "0:51:33"}
138
+ {"current_steps": 1370, "total_steps": 3584, "loss": 0.694, "lr": 7.764928969054493e-06, "epoch": 6.112409571508069, "percentage": 38.23, "elapsed_time": "0:31:39", "remaining_time": "0:51:09"}
139
+ {"current_steps": 1380, "total_steps": 3584, "loss": 0.6636, "lr": 7.724216319618257e-06, "epoch": 6.156928213689483, "percentage": 38.5, "elapsed_time": "0:31:47", "remaining_time": "0:50:46"}
140
+ {"current_steps": 1390, "total_steps": 3584, "loss": 0.6817, "lr": 7.683245159517903e-06, "epoch": 6.201446855870896, "percentage": 38.78, "elapsed_time": "0:31:56", "remaining_time": "0:50:24"}
141
+ {"current_steps": 1400, "total_steps": 3584, "loss": 0.6709, "lr": 7.642019376653858e-06, "epoch": 6.24596549805231, "percentage": 39.06, "elapsed_time": "0:32:04", "remaining_time": "0:50:02"}
142
+ {"current_steps": 1410, "total_steps": 3584, "loss": 0.6755, "lr": 7.600542883088629e-06, "epoch": 6.290484140233723, "percentage": 39.34, "elapsed_time": "0:32:12", "remaining_time": "0:49:39"}
143
+ {"current_steps": 1420, "total_steps": 3584, "loss": 0.7135, "lr": 7.5588196146755526e-06, "epoch": 6.3350027824151365, "percentage": 39.62, "elapsed_time": "0:32:20", "remaining_time": "0:49:17"}
144
+ {"current_steps": 1430, "total_steps": 3584, "loss": 0.6461, "lr": 7.5168535306853155e-06, "epoch": 6.3795214245965495, "percentage": 39.9, "elapsed_time": "0:32:28", "remaining_time": "0:48:55"}
145
+ {"current_steps": 1440, "total_steps": 3584, "loss": 0.6194, "lr": 7.474648613430252e-06, "epoch": 6.424040066777963, "percentage": 40.18, "elapsed_time": "0:32:36", "remaining_time": "0:48:33"}
146
+ {"current_steps": 1450, "total_steps": 3584, "loss": 0.6871, "lr": 7.432208867886439e-06, "epoch": 6.468558708959376, "percentage": 40.46, "elapsed_time": "0:32:45", "remaining_time": "0:48:12"}
147
+ {"current_steps": 1460, "total_steps": 3584, "loss": 0.6691, "lr": 7.389538321313652e-06, "epoch": 6.51307735114079, "percentage": 40.74, "elapsed_time": "0:32:53", "remaining_time": "0:47:50"}
148
+ {"current_steps": 1470, "total_steps": 3584, "loss": 0.6686, "lr": 7.346641022873205e-06, "epoch": 6.557595993322204, "percentage": 41.02, "elapsed_time": "0:33:00", "remaining_time": "0:47:28"}
149
+ {"current_steps": 1480, "total_steps": 3584, "loss": 0.648, "lr": 7.303521043243711e-06, "epoch": 6.602114635503617, "percentage": 41.29, "elapsed_time": "0:33:08", "remaining_time": "0:47:07"}
150
+ {"current_steps": 1490, "total_steps": 3584, "loss": 0.7131, "lr": 7.2601824742347985e-06, "epoch": 6.646633277685031, "percentage": 41.57, "elapsed_time": "0:33:16", "remaining_time": "0:46:45"}
151
+ {"current_steps": 1500, "total_steps": 3584, "loss": 0.7121, "lr": 7.2166294283988315e-06, "epoch": 6.691151919866444, "percentage": 41.85, "elapsed_time": "0:33:24", "remaining_time": "0:46:24"}
152
+ {"current_steps": 1510, "total_steps": 3584, "loss": 0.6216, "lr": 7.172866038640644e-06, "epoch": 6.735670562047858, "percentage": 42.13, "elapsed_time": "0:33:31", "remaining_time": "0:46:02"}
153
+ {"current_steps": 1520, "total_steps": 3584, "loss": 0.6726, "lr": 7.128896457825364e-06, "epoch": 6.780189204229271, "percentage": 42.41, "elapsed_time": "0:33:39", "remaining_time": "0:45:41"}
154
+ {"current_steps": 1530, "total_steps": 3584, "loss": 0.6597, "lr": 7.084724858384326e-06, "epoch": 6.824707846410685, "percentage": 42.69, "elapsed_time": "0:33:46", "remaining_time": "0:45:20"}
155
+ {"current_steps": 1540, "total_steps": 3584, "loss": 0.6608, "lr": 7.04035543191914e-06, "epoch": 6.869226488592098, "percentage": 42.97, "elapsed_time": "0:33:53", "remaining_time": "0:44:59"}
156
+ {"current_steps": 1550, "total_steps": 3584, "loss": 0.6419, "lr": 6.995792388803929e-06, "epoch": 6.913745130773512, "percentage": 43.25, "elapsed_time": "0:34:01", "remaining_time": "0:44:38"}
157
+ {"current_steps": 1560, "total_steps": 3584, "loss": 0.6505, "lr": 6.9510399577857976e-06, "epoch": 6.958263772954925, "percentage": 43.53, "elapsed_time": "0:34:08", "remaining_time": "0:44:17"}
158
+ {"current_steps": 1570, "total_steps": 3584, "loss": 0.734, "lr": 6.906102385583548e-06, "epoch": 7.005008347245409, "percentage": 43.81, "elapsed_time": "0:34:15", "remaining_time": "0:43:56"}
159
+ {"current_steps": 1580, "total_steps": 3584, "loss": 0.6262, "lr": 6.860983936484689e-06, "epoch": 7.049526989426822, "percentage": 44.08, "elapsed_time": "0:34:22", "remaining_time": "0:43:35"}
160
+ {"current_steps": 1590, "total_steps": 3584, "loss": 0.6499, "lr": 6.815688891940796e-06, "epoch": 7.094045631608236, "percentage": 44.36, "elapsed_time": "0:34:29", "remaining_time": "0:43:15"}
161
+ {"current_steps": 1600, "total_steps": 3584, "loss": 0.6259, "lr": 6.770221550161214e-06, "epoch": 7.138564273789649, "percentage": 44.64, "elapsed_time": "0:34:37", "remaining_time": "0:42:56"}
162
+ {"current_steps": 1610, "total_steps": 3584, "loss": 0.6564, "lr": 6.724586225705191e-06, "epoch": 7.183082915971063, "percentage": 44.92, "elapsed_time": "0:34:55", "remaining_time": "0:42:49"}
163
+ {"current_steps": 1620, "total_steps": 3584, "loss": 0.6358, "lr": 6.678787249072456e-06, "epoch": 7.227601558152476, "percentage": 45.2, "elapsed_time": "0:35:13", "remaining_time": "0:42:41"}
164
+ {"current_steps": 1630, "total_steps": 3584, "loss": 0.6883, "lr": 6.632828966292279e-06, "epoch": 7.27212020033389, "percentage": 45.48, "elapsed_time": "0:35:31", "remaining_time": "0:42:34"}
165
+ {"current_steps": 1640, "total_steps": 3584, "loss": 0.6618, "lr": 6.586715738511067e-06, "epoch": 7.316638842515303, "percentage": 45.76, "elapsed_time": "0:35:48", "remaining_time": "0:42:26"}
166
+ {"current_steps": 1650, "total_steps": 3584, "loss": 0.6233, "lr": 6.540451941578505e-06, "epoch": 7.361157484696717, "percentage": 46.04, "elapsed_time": "0:36:06", "remaining_time": "0:42:19"}
167
+ {"current_steps": 1660, "total_steps": 3584, "loss": 0.6973, "lr": 6.494041965632335e-06, "epoch": 7.40567612687813, "percentage": 46.32, "elapsed_time": "0:36:24", "remaining_time": "0:42:11"}
168
+ {"current_steps": 1670, "total_steps": 3584, "loss": 0.6683, "lr": 6.447490214681742e-06, "epoch": 7.450194769059544, "percentage": 46.6, "elapsed_time": "0:36:41", "remaining_time": "0:42:02"}
169
+ {"current_steps": 1680, "total_steps": 3584, "loss": 0.5964, "lr": 6.400801106189457e-06, "epoch": 7.494713411240957, "percentage": 46.88, "elapsed_time": "0:36:58", "remaining_time": "0:41:54"}
170
+ {"current_steps": 1690, "total_steps": 3584, "loss": 0.6784, "lr": 6.353979070652555e-06, "epoch": 7.539232053422371, "percentage": 47.15, "elapsed_time": "0:37:16", "remaining_time": "0:41:46"}
171
+ {"current_steps": 1700, "total_steps": 3584, "loss": 0.6335, "lr": 6.307028551182041e-06, "epoch": 7.583750695603785, "percentage": 47.43, "elapsed_time": "0:37:34", "remaining_time": "0:41:38"}
172
+ {"current_steps": 1710, "total_steps": 3584, "loss": 0.6539, "lr": 6.259954003081215e-06, "epoch": 7.628269337785198, "percentage": 47.71, "elapsed_time": "0:37:51", "remaining_time": "0:41:29"}
173
+ {"current_steps": 1720, "total_steps": 3584, "loss": 0.6371, "lr": 6.212759893422908e-06, "epoch": 7.6727879799666105, "percentage": 47.99, "elapsed_time": "0:38:08", "remaining_time": "0:41:20"}
174
+ {"current_steps": 1730, "total_steps": 3584, "loss": 0.6426, "lr": 6.165450700625565e-06, "epoch": 7.717306622148024, "percentage": 48.27, "elapsed_time": "0:38:26", "remaining_time": "0:41:11"}
175
+ {"current_steps": 1740, "total_steps": 3584, "loss": 0.6587, "lr": 6.118030914028292e-06, "epoch": 7.761825264329438, "percentage": 48.55, "elapsed_time": "0:38:43", "remaining_time": "0:41:01"}
176
+ {"current_steps": 1750, "total_steps": 3584, "loss": 0.5994, "lr": 6.070505033464835e-06, "epoch": 7.806343906510851, "percentage": 48.83, "elapsed_time": "0:39:00", "remaining_time": "0:40:53"}
177
+ {"current_steps": 1760, "total_steps": 3584, "loss": 0.6387, "lr": 6.022877568836579e-06, "epoch": 7.850862548692265, "percentage": 49.11, "elapsed_time": "0:39:18", "remaining_time": "0:40:43"}
178
+ {"current_steps": 1770, "total_steps": 3584, "loss": 0.6704, "lr": 5.975153039684579e-06, "epoch": 7.895381190873678, "percentage": 49.39, "elapsed_time": "0:39:35", "remaining_time": "0:40:34"}
179
+ {"current_steps": 1780, "total_steps": 3584, "loss": 0.6274, "lr": 5.927335974760699e-06, "epoch": 7.939899833055092, "percentage": 49.67, "elapsed_time": "0:39:51", "remaining_time": "0:40:23"}
180
+ {"current_steps": 1790, "total_steps": 3584, "loss": 0.6611, "lr": 5.87943091159785e-06, "epoch": 7.984418475236505, "percentage": 49.94, "elapsed_time": "0:40:08", "remaining_time": "0:40:13"}
181
+ {"current_steps": 1800, "total_steps": 3584, "loss": 0.6732, "lr": 5.831442396079413e-06, "epoch": 8.03116304952699, "percentage": 50.22, "elapsed_time": "0:40:25", "remaining_time": "0:40:04"}
182
+ {"current_steps": 1810, "total_steps": 3584, "loss": 0.5774, "lr": 5.78337498200786e-06, "epoch": 8.075681691708404, "percentage": 50.5, "elapsed_time": "0:40:41", "remaining_time": "0:39:53"}
183
+ {"current_steps": 1820, "total_steps": 3584, "loss": 0.6312, "lr": 5.735233230672636e-06, "epoch": 8.120200333889816, "percentage": 50.78, "elapsed_time": "0:40:58", "remaining_time": "0:39:42"}
184
+ {"current_steps": 1830, "total_steps": 3584, "loss": 0.6262, "lr": 5.687021710417308e-06, "epoch": 8.16471897607123, "percentage": 51.06, "elapsed_time": "0:41:14", "remaining_time": "0:39:31"}
185
+ {"current_steps": 1840, "total_steps": 3584, "loss": 0.5604, "lr": 5.638744996206074e-06, "epoch": 8.209237618252644, "percentage": 51.34, "elapsed_time": "0:41:31", "remaining_time": "0:39:21"}
186
+ {"current_steps": 1850, "total_steps": 3584, "loss": 0.6017, "lr": 5.590407669189612e-06, "epoch": 8.253756260434058, "percentage": 51.62, "elapsed_time": "0:41:47", "remaining_time": "0:39:10"}
187
+ {"current_steps": 1860, "total_steps": 3584, "loss": 0.5133, "lr": 5.542014316270377e-06, "epoch": 8.29827490261547, "percentage": 51.9, "elapsed_time": "0:42:03", "remaining_time": "0:38:59"}
188
+ {"current_steps": 1870, "total_steps": 3584, "loss": 0.5995, "lr": 5.493569529667312e-06, "epoch": 8.342793544796884, "percentage": 52.18, "elapsed_time": "0:42:19", "remaining_time": "0:38:47"}
189
+ {"current_steps": 1880, "total_steps": 3584, "loss": 0.6081, "lr": 5.445077906480095e-06, "epoch": 8.387312186978297, "percentage": 52.46, "elapsed_time": "0:42:35", "remaining_time": "0:38:36"}
190
+ {"current_steps": 1890, "total_steps": 3584, "loss": 0.6193, "lr": 5.396544048252893e-06, "epoch": 8.431830829159711, "percentage": 52.73, "elapsed_time": "0:42:51", "remaining_time": "0:38:25"}
191
+ {"current_steps": 1900, "total_steps": 3584, "loss": 0.568, "lr": 5.3479725605377065e-06, "epoch": 8.476349471341123, "percentage": 53.01, "elapsed_time": "0:43:08", "remaining_time": "0:38:14"}
192
+ {"current_steps": 1910, "total_steps": 3584, "loss": 0.5966, "lr": 5.299368052457332e-06, "epoch": 8.520868113522537, "percentage": 53.29, "elapsed_time": "0:43:24", "remaining_time": "0:38:02"}
193
+ {"current_steps": 1920, "total_steps": 3584, "loss": 0.6217, "lr": 5.250735136267993e-06, "epoch": 8.565386755703951, "percentage": 53.57, "elapsed_time": "0:43:39", "remaining_time": "0:37:50"}
194
+ {"current_steps": 1930, "total_steps": 3584, "loss": 0.554, "lr": 5.2020784269216515e-06, "epoch": 8.609905397885365, "percentage": 53.85, "elapsed_time": "0:43:55", "remaining_time": "0:37:38"}
195
+ {"current_steps": 1940, "total_steps": 3584, "loss": 0.562, "lr": 5.153402541628097e-06, "epoch": 8.654424040066779, "percentage": 54.13, "elapsed_time": "0:44:11", "remaining_time": "0:37:26"}
196
+ {"current_steps": 1950, "total_steps": 3584, "loss": 0.598, "lr": 5.1047120994167855e-06, "epoch": 8.698942682248191, "percentage": 54.41, "elapsed_time": "0:44:27", "remaining_time": "0:37:14"}
197
+ {"current_steps": 1960, "total_steps": 3584, "loss": 0.6065, "lr": 5.056011720698536e-06, "epoch": 8.743461324429605, "percentage": 54.69, "elapsed_time": "0:44:42", "remaining_time": "0:37:02"}
198
+ {"current_steps": 1970, "total_steps": 3584, "loss": 0.5696, "lr": 5.007306026827076e-06, "epoch": 8.787979966611019, "percentage": 54.97, "elapsed_time": "0:44:58", "remaining_time": "0:36:50"}
199
+ {"current_steps": 1980, "total_steps": 3584, "loss": 0.5824, "lr": 4.958599639660508e-06, "epoch": 8.832498608792433, "percentage": 55.25, "elapsed_time": "0:45:13", "remaining_time": "0:36:38"}
200
+ {"current_steps": 1990, "total_steps": 3584, "loss": 0.6082, "lr": 4.909897181122725e-06, "epoch": 8.877017250973845, "percentage": 55.52, "elapsed_time": "0:45:29", "remaining_time": "0:36:26"}
201
+ {"current_steps": 2000, "total_steps": 3584, "loss": 0.554, "lr": 4.861203272764813e-06, "epoch": 8.921535893155259, "percentage": 55.8, "elapsed_time": "0:45:44", "remaining_time": "0:36:13"}
202
+ {"current_steps": 2000, "total_steps": 3584, "eval_loss": 0.9391384720802307, "epoch": 8.921535893155259, "percentage": 55.8, "elapsed_time": "0:46:01", "remaining_time": "0:36:27"}
203
+ {"current_steps": 2010, "total_steps": 3584, "loss": 0.5373, "lr": 4.8125225353265085e-06, "epoch": 8.966054535336673, "percentage": 56.08, "elapsed_time": "0:46:16", "remaining_time": "0:36:14"}
204
+ {"current_steps": 2020, "total_steps": 3584, "loss": 0.6353, "lr": 4.7638595882977064e-06, "epoch": 9.012799109627156, "percentage": 56.36, "elapsed_time": "0:46:31", "remaining_time": "0:36:01"}
205
+ {"current_steps": 2030, "total_steps": 3584, "loss": 0.5151, "lr": 4.71521904948011e-06, "epoch": 9.05731775180857, "percentage": 56.64, "elapsed_time": "0:46:47", "remaining_time": "0:35:49"}
206
+ {"current_steps": 2040, "total_steps": 3584, "loss": 0.5314, "lr": 4.666605534549021e-06, "epoch": 9.101836393989982, "percentage": 56.92, "elapsed_time": "0:47:02", "remaining_time": "0:35:36"}
207
+ {"current_steps": 2050, "total_steps": 3584, "loss": 0.5424, "lr": 4.618023656615352e-06, "epoch": 9.146355036171396, "percentage": 57.2, "elapsed_time": "0:47:17", "remaining_time": "0:35:23"}
208
+ {"current_steps": 2060, "total_steps": 3584, "loss": 0.4959, "lr": 4.569478025787869e-06, "epoch": 9.19087367835281, "percentage": 57.48, "elapsed_time": "0:47:32", "remaining_time": "0:35:10"}
209
+ {"current_steps": 2070, "total_steps": 3584, "loss": 0.5301, "lr": 4.520973248735715e-06, "epoch": 9.235392320534224, "percentage": 57.76, "elapsed_time": "0:47:47", "remaining_time": "0:34:57"}
210
+ {"current_steps": 2080, "total_steps": 3584, "loss": 0.5219, "lr": 4.472513928251275e-06, "epoch": 9.279910962715638, "percentage": 58.04, "elapsed_time": "0:48:02", "remaining_time": "0:34:43"}
211
+ {"current_steps": 2090, "total_steps": 3584, "loss": 0.5537, "lr": 4.424104662813396e-06, "epoch": 9.32442960489705, "percentage": 58.31, "elapsed_time": "0:48:16", "remaining_time": "0:34:30"}
212
+ {"current_steps": 2100, "total_steps": 3584, "loss": 0.5269, "lr": 4.375750046151023e-06, "epoch": 9.368948247078464, "percentage": 58.59, "elapsed_time": "0:48:31", "remaining_time": "0:34:17"}
213
+ {"current_steps": 2110, "total_steps": 3584, "loss": 0.5535, "lr": 4.3274546668072835e-06, "epoch": 9.413466889259878, "percentage": 58.87, "elapsed_time": "0:48:45", "remaining_time": "0:34:03"}
214
+ {"current_steps": 2120, "total_steps": 3584, "loss": 0.5382, "lr": 4.279223107704058e-06, "epoch": 9.457985531441292, "percentage": 59.15, "elapsed_time": "0:48:59", "remaining_time": "0:33:50"}
215
+ {"current_steps": 2130, "total_steps": 3584, "loss": 0.5643, "lr": 4.2310599457071e-06, "epoch": 9.502504173622704, "percentage": 59.43, "elapsed_time": "0:49:13", "remaining_time": "0:33:36"}
216
+ {"current_steps": 2140, "total_steps": 3584, "loss": 0.5493, "lr": 4.1829697511917146e-06, "epoch": 9.547022815804118, "percentage": 59.71, "elapsed_time": "0:49:28", "remaining_time": "0:33:22"}
217
+ {"current_steps": 2150, "total_steps": 3584, "loss": 0.5457, "lr": 4.134957087609065e-06, "epoch": 9.591541457985532, "percentage": 59.99, "elapsed_time": "0:49:43", "remaining_time": "0:33:09"}
218
+ {"current_steps": 2160, "total_steps": 3584, "loss": 0.4859, "lr": 4.087026511053116e-06, "epoch": 9.636060100166945, "percentage": 60.27, "elapsed_time": "0:49:57", "remaining_time": "0:32:56"}
219
+ {"current_steps": 2170, "total_steps": 3584, "loss": 0.4969, "lr": 4.0391825698283084e-06, "epoch": 9.680578742348358, "percentage": 60.55, "elapsed_time": "0:50:11", "remaining_time": "0:32:42"}
220
+ {"current_steps": 2180, "total_steps": 3584, "loss": 0.5311, "lr": 3.991429804017944e-06, "epoch": 9.725097384529771, "percentage": 60.83, "elapsed_time": "0:50:25", "remaining_time": "0:32:28"}
221
+ {"current_steps": 2190, "total_steps": 3584, "loss": 0.5437, "lr": 3.9437727450533605e-06, "epoch": 9.769616026711185, "percentage": 61.1, "elapsed_time": "0:50:39", "remaining_time": "0:32:14"}
222
+ {"current_steps": 2200, "total_steps": 3584, "loss": 0.5197, "lr": 3.89621591528393e-06, "epoch": 9.8141346688926, "percentage": 61.38, "elapsed_time": "0:50:54", "remaining_time": "0:32:01"}
223
+ {"current_steps": 2210, "total_steps": 3584, "loss": 0.5104, "lr": 3.848763827547915e-06, "epoch": 9.858653311074011, "percentage": 61.66, "elapsed_time": "0:51:07", "remaining_time": "0:31:47"}
224
+ {"current_steps": 2220, "total_steps": 3584, "loss": 0.55, "lr": 3.8014209847442345e-06, "epoch": 9.903171953255425, "percentage": 61.94, "elapsed_time": "0:51:21", "remaining_time": "0:31:33"}
225
+ {"current_steps": 2230, "total_steps": 3584, "loss": 0.53, "lr": 3.7541918794051637e-06, "epoch": 9.947690595436839, "percentage": 62.22, "elapsed_time": "0:51:34", "remaining_time": "0:31:19"}
226
+ {"current_steps": 2240, "total_steps": 3584, "loss": 0.4882, "lr": 3.7070809932700134e-06, "epoch": 9.992209237618253, "percentage": 62.5, "elapsed_time": "0:51:48", "remaining_time": "0:31:05"}
227
+ {"current_steps": 2250, "total_steps": 3584, "loss": 0.4714, "lr": 3.6600927968598588e-06, "epoch": 10.038953811908737, "percentage": 62.78, "elapsed_time": "0:52:02", "remaining_time": "0:30:51"}
228
+ {"current_steps": 2260, "total_steps": 3584, "loss": 0.4774, "lr": 3.613231749053304e-06, "epoch": 10.08347245409015, "percentage": 63.06, "elapsed_time": "0:52:16", "remaining_time": "0:30:37"}
229
+ {"current_steps": 2270, "total_steps": 3584, "loss": 0.4764, "lr": 3.5665022966633678e-06, "epoch": 10.127991096271563, "percentage": 63.34, "elapsed_time": "0:52:29", "remaining_time": "0:30:23"}
230
+ {"current_steps": 2280, "total_steps": 3584, "loss": 0.4632, "lr": 3.519908874015501e-06, "epoch": 10.172509738452977, "percentage": 63.62, "elapsed_time": "0:52:42", "remaining_time": "0:30:08"}
231
+ {"current_steps": 2290, "total_steps": 3584, "loss": 0.4604, "lr": 3.473455902526809e-06, "epoch": 10.21702838063439, "percentage": 63.9, "elapsed_time": "0:52:55", "remaining_time": "0:29:54"}
232
+ {"current_steps": 2300, "total_steps": 3584, "loss": 0.4753, "lr": 3.4271477902864836e-06, "epoch": 10.261547022815805, "percentage": 64.17, "elapsed_time": "0:53:10", "remaining_time": "0:29:40"}
233
+ {"current_steps": 2310, "total_steps": 3584, "loss": 0.4323, "lr": 3.3809889316375012e-06, "epoch": 10.306065664997218, "percentage": 64.45, "elapsed_time": "0:53:23", "remaining_time": "0:29:26"}
234
+ {"current_steps": 2320, "total_steps": 3584, "loss": 0.4659, "lr": 3.334983706759627e-06, "epoch": 10.35058430717863, "percentage": 64.73, "elapsed_time": "0:53:36", "remaining_time": "0:29:12"}
235
+ {"current_steps": 2330, "total_steps": 3584, "loss": 0.4896, "lr": 3.2891364812537686e-06, "epoch": 10.395102949360044, "percentage": 65.01, "elapsed_time": "0:53:49", "remaining_time": "0:28:57"}
236
+ {"current_steps": 2340, "total_steps": 3584, "loss": 0.478, "lr": 3.2434516057277055e-06, "epoch": 10.439621591541458, "percentage": 65.29, "elapsed_time": "0:54:01", "remaining_time": "0:28:43"}
237
+ {"current_steps": 2350, "total_steps": 3584, "loss": 0.4453, "lr": 3.1979334153832486e-06, "epoch": 10.484140233722872, "percentage": 65.57, "elapsed_time": "0:54:15", "remaining_time": "0:28:29"}
238
+ {"current_steps": 2360, "total_steps": 3584, "loss": 0.5075, "lr": 3.1525862296048446e-06, "epoch": 10.528658875904284, "percentage": 65.85, "elapsed_time": "0:54:27", "remaining_time": "0:28:14"}
239
+ {"current_steps": 2370, "total_steps": 3584, "loss": 0.4865, "lr": 3.1074143515497114e-06, "epoch": 10.573177518085698, "percentage": 66.13, "elapsed_time": "0:54:40", "remaining_time": "0:28:00"}
240
+ {"current_steps": 2380, "total_steps": 3584, "loss": 0.5178, "lr": 3.0624220677394854e-06, "epoch": 10.617696160267112, "percentage": 66.41, "elapsed_time": "0:54:53", "remaining_time": "0:27:45"}
241
+ {"current_steps": 2390, "total_steps": 3584, "loss": 0.5069, "lr": 3.017613647653461e-06, "epoch": 10.662214802448526, "percentage": 66.69, "elapsed_time": "0:55:05", "remaining_time": "0:27:31"}
242
+ {"current_steps": 2400, "total_steps": 3584, "loss": 0.4423, "lr": 2.9729933433234402e-06, "epoch": 10.706733444629938, "percentage": 66.96, "elapsed_time": "0:55:18", "remaining_time": "0:27:17"}
243
+ {"current_steps": 2410, "total_steps": 3584, "loss": 0.4359, "lr": 2.9285653889302514e-06, "epoch": 10.751252086811352, "percentage": 67.24, "elapsed_time": "0:55:30", "remaining_time": "0:27:02"}
244
+ {"current_steps": 2420, "total_steps": 3584, "loss": 0.4517, "lr": 2.8843340004019427e-06, "epoch": 10.795770728992766, "percentage": 67.52, "elapsed_time": "0:55:42", "remaining_time": "0:26:47"}
245
+ {"current_steps": 2430, "total_steps": 3584, "loss": 0.4775, "lr": 2.8403033750137255e-06, "epoch": 10.84028937117418, "percentage": 67.8, "elapsed_time": "0:55:54", "remaining_time": "0:26:33"}
246
+ {"current_steps": 2440, "total_steps": 3584, "loss": 0.5064, "lr": 2.7964776909896733e-06, "epoch": 10.884808013355592, "percentage": 68.08, "elapsed_time": "0:56:07", "remaining_time": "0:26:18"}
247
+ {"current_steps": 2450, "total_steps": 3584, "loss": 0.4651, "lr": 2.7528611071062366e-06, "epoch": 10.929326655537006, "percentage": 68.36, "elapsed_time": "0:56:19", "remaining_time": "0:26:04"}
248
+ {"current_steps": 2460, "total_steps": 3584, "loss": 0.4909, "lr": 2.7094577622976096e-06, "epoch": 10.97384529771842, "percentage": 68.64, "elapsed_time": "0:56:31", "remaining_time": "0:25:49"}
249
+ {"current_steps": 2470, "total_steps": 3584, "loss": 0.4996, "lr": 2.6662717752629597e-06, "epoch": 11.020589872008903, "percentage": 68.92, "elapsed_time": "0:56:43", "remaining_time": "0:25:34"}
250
+ {"current_steps": 2480, "total_steps": 3584, "loss": 0.4445, "lr": 2.6233072440755934e-06, "epoch": 11.065108514190317, "percentage": 69.2, "elapsed_time": "0:56:55", "remaining_time": "0:25:20"}
251
+ {"current_steps": 2490, "total_steps": 3584, "loss": 0.4471, "lr": 2.580568245794085e-06, "epoch": 11.109627156371731, "percentage": 69.48, "elapsed_time": "0:57:07", "remaining_time": "0:25:05"}
252
+ {"current_steps": 2500, "total_steps": 3584, "loss": 0.49, "lr": 2.538058836075373e-06, "epoch": 11.154145798553143, "percentage": 69.75, "elapsed_time": "0:57:19", "remaining_time": "0:24:51"}
253
+ {"current_steps": 2510, "total_steps": 3584, "loss": 0.4148, "lr": 2.4957830487899224e-06, "epoch": 11.198664440734557, "percentage": 70.03, "elapsed_time": "0:57:31", "remaining_time": "0:24:36"}
254
+ {"current_steps": 2520, "total_steps": 3584, "loss": 0.4247, "lr": 2.4537448956389146e-06, "epoch": 11.243183082915971, "percentage": 70.31, "elapsed_time": "0:57:42", "remaining_time": "0:24:21"}
255
+ {"current_steps": 2530, "total_steps": 3584, "loss": 0.4368, "lr": 2.411948365773588e-06, "epoch": 11.287701725097385, "percentage": 70.59, "elapsed_time": "0:57:54", "remaining_time": "0:24:07"}
256
+ {"current_steps": 2540, "total_steps": 3584, "loss": 0.4273, "lr": 2.3703974254166704e-06, "epoch": 11.332220367278797, "percentage": 70.87, "elapsed_time": "0:58:06", "remaining_time": "0:23:52"}
257
+ {"current_steps": 2550, "total_steps": 3584, "loss": 0.4421, "lr": 2.3290960174860293e-06, "epoch": 11.376739009460211, "percentage": 71.15, "elapsed_time": "0:58:18", "remaining_time": "0:23:38"}
258
+ {"current_steps": 2560, "total_steps": 3584, "loss": 0.4072, "lr": 2.2880480612204925e-06, "epoch": 11.421257651641625, "percentage": 71.43, "elapsed_time": "0:58:29", "remaining_time": "0:23:23"}
259
+ {"current_steps": 2570, "total_steps": 3584, "loss": 0.4472, "lr": 2.247257451807961e-06, "epoch": 11.465776293823039, "percentage": 71.71, "elapsed_time": "0:58:40", "remaining_time": "0:23:08"}
260
+ {"current_steps": 2580, "total_steps": 3584, "loss": 0.4613, "lr": 2.206728060015761e-06, "epoch": 11.510294936004453, "percentage": 71.99, "elapsed_time": "0:58:51", "remaining_time": "0:22:54"}
261
+ {"current_steps": 2590, "total_steps": 3584, "loss": 0.4111, "lr": 2.1664637318233484e-06, "epoch": 11.554813578185865, "percentage": 72.27, "elapsed_time": "0:59:02", "remaining_time": "0:22:39"}
262
+ {"current_steps": 2600, "total_steps": 3584, "loss": 0.4385, "lr": 2.1264682880573374e-06, "epoch": 11.599332220367279, "percentage": 72.54, "elapsed_time": "0:59:13", "remaining_time": "0:22:24"}
263
+ {"current_steps": 2610, "total_steps": 3584, "loss": 0.4448, "lr": 2.086745524028933e-06, "epoch": 11.643850862548693, "percentage": 72.82, "elapsed_time": "0:59:24", "remaining_time": "0:22:10"}
264
+ {"current_steps": 2620, "total_steps": 3584, "loss": 0.4292, "lr": 2.0472992091737886e-06, "epoch": 11.688369504730106, "percentage": 73.1, "elapsed_time": "0:59:35", "remaining_time": "0:21:55"}
265
+ {"current_steps": 2630, "total_steps": 3584, "loss": 0.425, "lr": 2.0081330866942962e-06, "epoch": 11.732888146911518, "percentage": 73.38, "elapsed_time": "0:59:46", "remaining_time": "0:21:41"}
266
+ {"current_steps": 2640, "total_steps": 3584, "loss": 0.4311, "lr": 1.96925087320439e-06, "epoch": 11.777406789092932, "percentage": 73.66, "elapsed_time": "0:59:57", "remaining_time": "0:21:26"}
267
+ {"current_steps": 2650, "total_steps": 3584, "loss": 0.4725, "lr": 1.930656258376859e-06, "epoch": 11.821925431274346, "percentage": 73.94, "elapsed_time": "1:00:09", "remaining_time": "0:21:12"}
268
+ {"current_steps": 2660, "total_steps": 3584, "loss": 0.4149, "lr": 1.8923529045932292e-06, "epoch": 11.86644407345576, "percentage": 74.22, "elapsed_time": "1:00:19", "remaining_time": "0:20:57"}
269
+ {"current_steps": 2670, "total_steps": 3584, "loss": 0.4436, "lr": 1.8543444465962147e-06, "epoch": 11.910962715637172, "percentage": 74.5, "elapsed_time": "1:00:29", "remaining_time": "0:20:42"}
270
+ {"current_steps": 2680, "total_steps": 3584, "loss": 0.4254, "lr": 1.8166344911448115e-06, "epoch": 11.955481357818586, "percentage": 74.78, "elapsed_time": "1:00:40", "remaining_time": "0:20:27"}
271
+ {"current_steps": 2690, "total_steps": 3584, "loss": 0.5129, "lr": 1.7792266166720368e-06, "epoch": 12.00222593210907, "percentage": 75.06, "elapsed_time": "1:00:50", "remaining_time": "0:20:13"}
272
+ {"current_steps": 2700, "total_steps": 3584, "loss": 0.4114, "lr": 1.742124372945364e-06, "epoch": 12.046744574290484, "percentage": 75.33, "elapsed_time": "1:01:01", "remaining_time": "0:19:58"}
273
+ {"current_steps": 2710, "total_steps": 3584, "loss": 0.4351, "lr": 1.7053312807298633e-06, "epoch": 12.091263216471898, "percentage": 75.61, "elapsed_time": "1:01:12", "remaining_time": "0:19:44"}
274
+ {"current_steps": 2720, "total_steps": 3584, "loss": 0.404, "lr": 1.6688508314541086e-06, "epoch": 12.135781858653312, "percentage": 75.89, "elapsed_time": "1:01:22", "remaining_time": "0:19:29"}
275
+ {"current_steps": 2730, "total_steps": 3584, "loss": 0.4349, "lr": 1.6326864868788678e-06, "epoch": 12.180300500834724, "percentage": 76.17, "elapsed_time": "1:01:32", "remaining_time": "0:19:15"}
276
+ {"current_steps": 2740, "total_steps": 3584, "loss": 0.4581, "lr": 1.5968416787685919e-06, "epoch": 12.224819143016138, "percentage": 76.45, "elapsed_time": "1:01:42", "remaining_time": "0:19:00"}
277
+ {"current_steps": 2750, "total_steps": 3584, "loss": 0.4589, "lr": 1.5613198085657804e-06, "epoch": 12.269337785197552, "percentage": 76.73, "elapsed_time": "1:01:52", "remaining_time": "0:18:46"}
278
+ {"current_steps": 2760, "total_steps": 3584, "loss": 0.4357, "lr": 1.5261242470681813e-06, "epoch": 12.313856427378965, "percentage": 77.01, "elapsed_time": "1:02:02", "remaining_time": "0:18:31"}
279
+ {"current_steps": 2770, "total_steps": 3584, "loss": 0.3949, "lr": 1.4912583341089516e-06, "epoch": 12.358375069560378, "percentage": 77.29, "elapsed_time": "1:02:12", "remaining_time": "0:18:16"}
280
+ {"current_steps": 2780, "total_steps": 3584, "loss": 0.4184, "lr": 1.4567253782397073e-06, "epoch": 12.402893711741791, "percentage": 77.57, "elapsed_time": "1:02:22", "remaining_time": "0:18:02"}
281
+ {"current_steps": 2790, "total_steps": 3584, "loss": 0.4309, "lr": 1.4225286564165785e-06, "epoch": 12.447412353923205, "percentage": 77.85, "elapsed_time": "1:02:31", "remaining_time": "0:17:47"}
282
+ {"current_steps": 2800, "total_steps": 3584, "loss": 0.4539, "lr": 1.3886714136892287e-06, "epoch": 12.49193099610462, "percentage": 78.12, "elapsed_time": "1:02:41", "remaining_time": "0:17:33"}
283
+ {"current_steps": 2810, "total_steps": 3584, "loss": 0.4243, "lr": 1.3551568628929434e-06, "epoch": 12.536449638286033, "percentage": 78.4, "elapsed_time": "1:02:51", "remaining_time": "0:17:18"}
284
+ {"current_steps": 2820, "total_steps": 3584, "loss": 0.4039, "lr": 1.321988184343732e-06, "epoch": 12.580968280467445, "percentage": 78.68, "elapsed_time": "1:03:00", "remaining_time": "0:17:04"}
285
+ {"current_steps": 2830, "total_steps": 3584, "loss": 0.4182, "lr": 1.2891685255365517e-06, "epoch": 12.625486922648859, "percentage": 78.96, "elapsed_time": "1:03:09", "remaining_time": "0:16:49"}
286
+ {"current_steps": 2840, "total_steps": 3584, "loss": 0.4146, "lr": 1.256701000846619e-06, "epoch": 12.670005564830273, "percentage": 79.24, "elapsed_time": "1:03:18", "remaining_time": "0:16:35"}
287
+ {"current_steps": 2850, "total_steps": 3584, "loss": 0.434, "lr": 1.22458869123388e-06, "epoch": 12.714524207011687, "percentage": 79.52, "elapsed_time": "1:03:28", "remaining_time": "0:16:20"}
288
+ {"current_steps": 2860, "total_steps": 3584, "loss": 0.4356, "lr": 1.1928346439506526e-06, "epoch": 12.759042849193099, "percentage": 79.8, "elapsed_time": "1:03:37", "remaining_time": "0:16:06"}
289
+ {"current_steps": 2870, "total_steps": 3584, "loss": 0.4073, "lr": 1.1614418722524506e-06, "epoch": 12.803561491374513, "percentage": 80.08, "elapsed_time": "1:03:47", "remaining_time": "0:15:52"}
290
+ {"current_steps": 2880, "total_steps": 3584, "loss": 0.4376, "lr": 1.1304133551120532e-06, "epoch": 12.848080133555927, "percentage": 80.36, "elapsed_time": "1:03:56", "remaining_time": "0:15:37"}
291
+ {"current_steps": 2890, "total_steps": 3584, "loss": 0.4078, "lr": 1.0997520369368158e-06, "epoch": 12.89259877573734, "percentage": 80.64, "elapsed_time": "1:04:05", "remaining_time": "0:15:23"}
292
+ {"current_steps": 2900, "total_steps": 3584, "loss": 0.4329, "lr": 1.0694608272892698e-06, "epoch": 12.937117417918753, "percentage": 80.92, "elapsed_time": "1:04:14", "remaining_time": "0:15:09"}
293
+ {"current_steps": 2910, "total_steps": 3584, "loss": 0.3766, "lr": 1.0395426006110164e-06, "epoch": 12.981636060100167, "percentage": 81.19, "elapsed_time": "1:04:23", "remaining_time": "0:14:54"}
294
+ {"current_steps": 2920, "total_steps": 3584, "loss": 0.3808, "lr": 1.0100001959499644e-06, "epoch": 13.02838063439065, "percentage": 81.47, "elapsed_time": "1:04:32", "remaining_time": "0:14:40"}
295
+ {"current_steps": 2930, "total_steps": 3584, "loss": 0.4232, "lr": 9.808364166909256e-07, "epoch": 13.072899276572064, "percentage": 81.75, "elapsed_time": "1:04:41", "remaining_time": "0:14:26"}
296
+ {"current_steps": 2940, "total_steps": 3584, "loss": 0.4332, "lr": 9.520540302895847e-07, "epoch": 13.117417918753478, "percentage": 82.03, "elapsed_time": "1:04:49", "remaining_time": "0:14:12"}
297
+ {"current_steps": 2950, "total_steps": 3584, "loss": 0.4059, "lr": 9.236557680098918e-07, "epoch": 13.161936560934892, "percentage": 82.31, "elapsed_time": "1:04:58", "remaining_time": "0:13:57"}
298
+ {"current_steps": 2960, "total_steps": 3584, "loss": 0.3704, "lr": 8.956443246648771e-07, "epoch": 13.206455203116304, "percentage": 82.59, "elapsed_time": "1:05:06", "remaining_time": "0:13:43"}
299
+ {"current_steps": 2970, "total_steps": 3584, "loss": 0.4327, "lr": 8.680223583609399e-07, "epoch": 13.250973845297718, "percentage": 82.87, "elapsed_time": "1:05:15", "remaining_time": "0:13:29"}
300
+ {"current_steps": 2980, "total_steps": 3584, "loss": 0.4229, "lr": 8.407924902455983e-07, "epoch": 13.295492487479132, "percentage": 83.15, "elapsed_time": "1:05:23", "remaining_time": "0:13:15"}
301
+ {"current_steps": 2990, "total_steps": 3584, "loss": 0.4121, "lr": 8.139573042587729e-07, "epoch": 13.340011129660546, "percentage": 83.43, "elapsed_time": "1:05:31", "remaining_time": "0:13:01"}
302
+ {"current_steps": 3000, "total_steps": 3584, "loss": 0.423, "lr": 7.875193468875719e-07, "epoch": 13.384529771841958, "percentage": 83.71, "elapsed_time": "1:05:40", "remaining_time": "0:12:47"}
303
+ {"current_steps": 3000, "total_steps": 3584, "eval_loss": 0.9250730872154236, "epoch": 13.384529771841958, "percentage": 83.71, "elapsed_time": "1:05:57", "remaining_time": "0:12:50"}
304
+ {"current_steps": 3010, "total_steps": 3584, "loss": 0.4316, "lr": 7.614811269246631e-07, "epoch": 13.429048414023372, "percentage": 83.98, "elapsed_time": "1:06:06", "remaining_time": "0:12:36"}
305
+ {"current_steps": 3020, "total_steps": 3584, "loss": 0.4104, "lr": 7.35845115230191e-07, "epoch": 13.473567056204786, "percentage": 84.26, "elapsed_time": "1:06:13", "remaining_time": "0:12:22"}
306
+ {"current_steps": 3030, "total_steps": 3584, "loss": 0.4367, "lr": 7.106137444973177e-07, "epoch": 13.5180856983862, "percentage": 84.54, "elapsed_time": "1:06:21", "remaining_time": "0:12:08"}
307
+ {"current_steps": 3040, "total_steps": 3584, "loss": 0.417, "lr": 6.857894090213702e-07, "epoch": 13.562604340567614, "percentage": 84.82, "elapsed_time": "1:06:29", "remaining_time": "0:11:53"}
308
+ {"current_steps": 3050, "total_steps": 3584, "loss": 0.394, "lr": 6.613744644726383e-07, "epoch": 13.607122982749026, "percentage": 85.1, "elapsed_time": "1:06:38", "remaining_time": "0:11:40"}
309
+ {"current_steps": 3060, "total_steps": 3584, "loss": 0.4172, "lr": 6.3737122767284e-07, "epoch": 13.65164162493044, "percentage": 85.38, "elapsed_time": "1:06:46", "remaining_time": "0:11:26"}
310
+ {"current_steps": 3070, "total_steps": 3584, "loss": 0.4517, "lr": 6.137819763752656e-07, "epoch": 13.696160267111853, "percentage": 85.66, "elapsed_time": "1:06:53", "remaining_time": "0:11:12"}
311
+ {"current_steps": 3080, "total_steps": 3584, "loss": 0.4256, "lr": 5.90608949048635e-07, "epoch": 13.740678909293267, "percentage": 85.94, "elapsed_time": "1:07:01", "remaining_time": "0:10:58"}
312
+ {"current_steps": 3090, "total_steps": 3584, "loss": 0.4019, "lr": 5.678543446646811e-07, "epoch": 13.78519755147468, "percentage": 86.22, "elapsed_time": "1:07:09", "remaining_time": "0:10:44"}
313
+ {"current_steps": 3100, "total_steps": 3584, "loss": 0.453, "lr": 5.455203224894857e-07, "epoch": 13.829716193656093, "percentage": 86.5, "elapsed_time": "1:07:17", "remaining_time": "0:10:30"}
314
+ {"current_steps": 3110, "total_steps": 3584, "loss": 0.4107, "lr": 5.236090018785705e-07, "epoch": 13.874234835837507, "percentage": 86.77, "elapsed_time": "1:07:24", "remaining_time": "0:10:16"}
315
+ {"current_steps": 3120, "total_steps": 3584, "loss": 0.4475, "lr": 5.021224620757914e-07, "epoch": 13.918753478018921, "percentage": 87.05, "elapsed_time": "1:07:31", "remaining_time": "0:10:02"}
316
+ {"current_steps": 3130, "total_steps": 3584, "loss": 0.4322, "lr": 4.810627420160269e-07, "epoch": 13.963272120200333, "percentage": 87.33, "elapsed_time": "1:07:39", "remaining_time": "0:09:48"}
317
+ {"current_steps": 3140, "total_steps": 3584, "loss": 0.4318, "lr": 4.604318401317009e-07, "epoch": 14.010016694490819, "percentage": 87.61, "elapsed_time": "1:07:46", "remaining_time": "0:09:35"}
318
+ {"current_steps": 3150, "total_steps": 3584, "loss": 0.4489, "lr": 4.402317141631407e-07, "epoch": 14.054535336672231, "percentage": 87.89, "elapsed_time": "1:07:54", "remaining_time": "0:09:21"}
319
+ {"current_steps": 3160, "total_steps": 3584, "loss": 0.4381, "lr": 4.2046428097279766e-07, "epoch": 14.099053978853645, "percentage": 88.17, "elapsed_time": "1:08:01", "remaining_time": "0:09:07"}
320
+ {"current_steps": 3170, "total_steps": 3584, "loss": 0.4107, "lr": 4.011314163633573e-07, "epoch": 14.143572621035059, "percentage": 88.45, "elapsed_time": "1:08:07", "remaining_time": "0:08:53"}
321
+ {"current_steps": 3180, "total_steps": 3584, "loss": 0.4399, "lr": 3.822349548997295e-07, "epoch": 14.188091263216473, "percentage": 88.73, "elapsed_time": "1:08:15", "remaining_time": "0:08:40"}
322
+ {"current_steps": 3190, "total_steps": 3584, "loss": 0.417, "lr": 3.637766897349654e-07, "epoch": 14.232609905397885, "percentage": 89.01, "elapsed_time": "1:08:21", "remaining_time": "0:08:26"}
323
+ {"current_steps": 3200, "total_steps": 3584, "loss": 0.4449, "lr": 3.4575837244009367e-07, "epoch": 14.277128547579299, "percentage": 89.29, "elapsed_time": "1:08:30", "remaining_time": "0:08:13"}
324
+ {"current_steps": 3210, "total_steps": 3584, "loss": 0.3875, "lr": 3.281817128379139e-07, "epoch": 14.321647189760712, "percentage": 89.56, "elapsed_time": "1:08:47", "remaining_time": "0:08:00"}
325
+ {"current_steps": 3220, "total_steps": 3584, "loss": 0.4187, "lr": 3.1104837884073866e-07, "epoch": 14.366165831942126, "percentage": 89.84, "elapsed_time": "1:09:05", "remaining_time": "0:07:48"}
326
+ {"current_steps": 3230, "total_steps": 3584, "loss": 0.41, "lr": 2.943599962921279e-07, "epoch": 14.410684474123538, "percentage": 90.12, "elapsed_time": "1:09:23", "remaining_time": "0:07:36"}
327
+ {"current_steps": 3240, "total_steps": 3584, "loss": 0.4016, "lr": 2.7811814881259503e-07, "epoch": 14.455203116304952, "percentage": 90.4, "elapsed_time": "1:09:41", "remaining_time": "0:07:23"}
328
+ {"current_steps": 3250, "total_steps": 3584, "loss": 0.3906, "lr": 2.623243776493434e-07, "epoch": 14.499721758486366, "percentage": 90.68, "elapsed_time": "1:09:59", "remaining_time": "0:07:11"}
329
+ {"current_steps": 3260, "total_steps": 3584, "loss": 0.4241, "lr": 2.469801815300027e-07, "epoch": 14.54424040066778, "percentage": 90.96, "elapsed_time": "1:10:17", "remaining_time": "0:06:59"}
330
+ {"current_steps": 3270, "total_steps": 3584, "loss": 0.4104, "lr": 2.3208701652041697e-07, "epoch": 14.588759042849194, "percentage": 91.24, "elapsed_time": "1:10:35", "remaining_time": "0:06:46"}
331
+ {"current_steps": 3280, "total_steps": 3584, "loss": 0.4031, "lr": 2.1764629588646667e-07, "epoch": 14.633277685030606, "percentage": 91.52, "elapsed_time": "1:10:53", "remaining_time": "0:06:34"}
332
+ {"current_steps": 3290, "total_steps": 3584, "loss": 0.3911, "lr": 2.036593899599615e-07, "epoch": 14.67779632721202, "percentage": 91.8, "elapsed_time": "1:11:10", "remaining_time": "0:06:21"}
333
+ {"current_steps": 3300, "total_steps": 3584, "loss": 0.4137, "lr": 1.9012762600860656e-07, "epoch": 14.722314969393434, "percentage": 92.08, "elapsed_time": "1:11:28", "remaining_time": "0:06:09"}
334
+ {"current_steps": 3310, "total_steps": 3584, "loss": 0.4559, "lr": 1.7705228811005004e-07, "epoch": 14.766833611574848, "percentage": 92.35, "elapsed_time": "1:11:45", "remaining_time": "0:05:56"}
335
+ {"current_steps": 3320, "total_steps": 3584, "loss": 0.3986, "lr": 1.6443461703003427e-07, "epoch": 14.81135225375626, "percentage": 92.63, "elapsed_time": "1:12:02", "remaining_time": "0:05:43"}
336
+ {"current_steps": 3330, "total_steps": 3584, "loss": 0.4073, "lr": 1.5227581010465341e-07, "epoch": 14.855870895937674, "percentage": 92.91, "elapsed_time": "1:12:19", "remaining_time": "0:05:30"}
337
+ {"current_steps": 3340, "total_steps": 3584, "loss": 0.4137, "lr": 1.4057702112673765e-07, "epoch": 14.900389538119088, "percentage": 93.19, "elapsed_time": "1:12:36", "remaining_time": "0:05:18"}
338
+ {"current_steps": 3350, "total_steps": 3584, "loss": 0.4283, "lr": 1.2933936023636073e-07, "epoch": 14.944908180300501, "percentage": 93.47, "elapsed_time": "1:12:54", "remaining_time": "0:05:05"}
339
+ {"current_steps": 3360, "total_steps": 3584, "loss": 0.4097, "lr": 1.185638938154976e-07, "epoch": 14.989426822481914, "percentage": 93.75, "elapsed_time": "1:13:11", "remaining_time": "0:04:52"}
340
+ {"current_steps": 3370, "total_steps": 3584, "loss": 0.4326, "lr": 1.08251644386832e-07, "epoch": 15.0361713967724, "percentage": 94.03, "elapsed_time": "1:13:29", "remaining_time": "0:04:39"}
341
+ {"current_steps": 3380, "total_steps": 3584, "loss": 0.4338, "lr": 9.84035905167241e-08, "epoch": 15.080690038953811, "percentage": 94.31, "elapsed_time": "1:13:45", "remaining_time": "0:04:27"}
342
+ {"current_steps": 3390, "total_steps": 3584, "loss": 0.4197, "lr": 8.902066672235144e-08, "epoch": 15.125208681135225, "percentage": 94.59, "elapsed_time": "1:14:02", "remaining_time": "0:04:14"}
343
+ {"current_steps": 3400, "total_steps": 3584, "loss": 0.4277, "lr": 8.010376338302872e-08, "epoch": 15.16972732331664, "percentage": 94.87, "elapsed_time": "1:14:19", "remaining_time": "0:04:01"}
344
+ {"current_steps": 3410, "total_steps": 3584, "loss": 0.4325, "lr": 7.165372665571879e-08, "epoch": 15.214245965498053, "percentage": 95.15, "elapsed_time": "1:14:36", "remaining_time": "0:03:48"}
345
+ {"current_steps": 3420, "total_steps": 3584, "loss": 0.399, "lr": 6.367135839473349e-08, "epoch": 15.258764607679465, "percentage": 95.42, "elapsed_time": "1:14:52", "remaining_time": "0:03:35"}
346
+ {"current_steps": 3430, "total_steps": 3584, "loss": 0.4368, "lr": 5.6157416075648954e-08, "epoch": 15.303283249860879, "percentage": 95.7, "elapsed_time": "1:15:09", "remaining_time": "0:03:22"}
347
+ {"current_steps": 3440, "total_steps": 3584, "loss": 0.4029, "lr": 4.911261272341872e-08, "epoch": 15.347801892042293, "percentage": 95.98, "elapsed_time": "1:15:25", "remaining_time": "0:03:09"}
348
+ {"current_steps": 3450, "total_steps": 3584, "loss": 0.4269, "lr": 4.25376168447178e-08, "epoch": 15.392320534223707, "percentage": 96.26, "elapsed_time": "1:15:42", "remaining_time": "0:02:56"}
349
+ {"current_steps": 3460, "total_steps": 3584, "loss": 0.4442, "lr": 3.643305236450345e-08, "epoch": 15.436839176405119, "percentage": 96.54, "elapsed_time": "1:15:59", "remaining_time": "0:02:43"}
350
+ {"current_steps": 3470, "total_steps": 3584, "loss": 0.4207, "lr": 3.079949856680975e-08, "epoch": 15.481357818586533, "percentage": 96.82, "elapsed_time": "1:16:14", "remaining_time": "0:02:30"}
351
+ {"current_steps": 3480, "total_steps": 3584, "loss": 0.4257, "lr": 2.5637490039775447e-08, "epoch": 15.525876460767947, "percentage": 97.1, "elapsed_time": "1:16:30", "remaining_time": "0:02:17"}
352
+ {"current_steps": 3490, "total_steps": 3584, "loss": 0.4161, "lr": 2.0947516624917898e-08, "epoch": 15.57039510294936, "percentage": 97.38, "elapsed_time": "1:16:46", "remaining_time": "0:02:04"}
353
+ {"current_steps": 3500, "total_steps": 3584, "loss": 0.3976, "lr": 1.6730023370645775e-08, "epoch": 15.614913745130773, "percentage": 97.66, "elapsed_time": "1:17:02", "remaining_time": "0:01:50"}
354
+ {"current_steps": 3510, "total_steps": 3584, "loss": 0.4074, "lr": 1.298541049003288e-08, "epoch": 15.659432387312187, "percentage": 97.94, "elapsed_time": "1:17:18", "remaining_time": "0:01:37"}
355
+ {"current_steps": 3520, "total_steps": 3584, "loss": 0.4155, "lr": 9.714033322833494e-09, "epoch": 15.7039510294936, "percentage": 98.21, "elapsed_time": "1:17:33", "remaining_time": "0:01:24"}
356
+ {"current_steps": 3530, "total_steps": 3584, "loss": 0.3747, "lr": 6.9162023017699255e-09, "epoch": 15.748469671675014, "percentage": 98.49, "elapsed_time": "1:17:49", "remaining_time": "0:01:11"}
357
+ {"current_steps": 3540, "total_steps": 3584, "loss": 0.3766, "lr": 4.592182923068289e-09, "epoch": 15.792988313856428, "percentage": 98.77, "elapsed_time": "1:18:05", "remaining_time": "0:00:58"}
358
+ {"current_steps": 3550, "total_steps": 3584, "loss": 0.4017, "lr": 2.7421957212697692e-09, "epoch": 15.83750695603784, "percentage": 99.05, "elapsed_time": "1:18:21", "remaining_time": "0:00:45"}
359
+ {"current_steps": 3560, "total_steps": 3584, "loss": 0.42, "lr": 1.3664162482990296e-09, "epoch": 15.882025598219254, "percentage": 99.33, "elapsed_time": "1:18:37", "remaining_time": "0:00:31"}
360
+ {"current_steps": 3570, "total_steps": 3584, "loss": 0.44, "lr": 4.649750568080924e-10, "epoch": 15.926544240400668, "percentage": 99.61, "elapsed_time": "1:18:52", "remaining_time": "0:00:18"}
361
+ {"current_steps": 3580, "total_steps": 3584, "loss": 0.4156, "lr": 3.795768778680487e-11, "epoch": 15.971062882582082, "percentage": 99.89, "elapsed_time": "1:19:07", "remaining_time": "0:00:05"}
362
+ {"current_steps": 3584, "total_steps": 3584, "epoch": 15.988870339454646, "percentage": 100.0, "elapsed_time": "1:20:13", "remaining_time": "0:00:00"}
trainer_state.json ADDED
@@ -0,0 +1,2572 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 15.988870339454646,
5
+ "eval_steps": 1000,
6
+ "global_step": 3584,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.044518642181413465,
13
+ "grad_norm": 33.75,
14
+ "learning_rate": 2.785515320334262e-07,
15
+ "loss": 2.0545,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.08903728436282693,
20
+ "grad_norm": 28.125,
21
+ "learning_rate": 5.571030640668524e-07,
22
+ "loss": 2.0294,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.1335559265442404,
27
+ "grad_norm": 20.875,
28
+ "learning_rate": 8.356545961002786e-07,
29
+ "loss": 1.9841,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.17807456872565386,
34
+ "grad_norm": 14.25,
35
+ "learning_rate": 1.1142061281337048e-06,
36
+ "loss": 1.8176,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.22259321090706732,
41
+ "grad_norm": 23.5,
42
+ "learning_rate": 1.392757660167131e-06,
43
+ "loss": 1.6325,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.2671118530884808,
48
+ "grad_norm": 19.25,
49
+ "learning_rate": 1.6713091922005572e-06,
50
+ "loss": 1.6341,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.3116304952698943,
55
+ "grad_norm": 13.8125,
56
+ "learning_rate": 1.9498607242339835e-06,
57
+ "loss": 1.4943,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.3561491374513077,
62
+ "grad_norm": 12.0,
63
+ "learning_rate": 2.2284122562674097e-06,
64
+ "loss": 1.4708,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.4006677796327212,
69
+ "grad_norm": 11.125,
70
+ "learning_rate": 2.506963788300836e-06,
71
+ "loss": 1.415,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.44518642181413465,
76
+ "grad_norm": 3.203125,
77
+ "learning_rate": 2.785515320334262e-06,
78
+ "loss": 1.4596,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.48970506399554814,
83
+ "grad_norm": 2.71875,
84
+ "learning_rate": 3.064066852367688e-06,
85
+ "loss": 1.4339,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.5342237061769616,
90
+ "grad_norm": 2.6875,
91
+ "learning_rate": 3.3426183844011143e-06,
92
+ "loss": 1.4009,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.5787423483583751,
97
+ "grad_norm": 3.109375,
98
+ "learning_rate": 3.6211699164345405e-06,
99
+ "loss": 1.3688,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.6232609905397886,
104
+ "grad_norm": 2.84375,
105
+ "learning_rate": 3.899721448467967e-06,
106
+ "loss": 1.3595,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.667779632721202,
111
+ "grad_norm": 2.65625,
112
+ "learning_rate": 4.178272980501394e-06,
113
+ "loss": 1.3609,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.7122982749026154,
118
+ "grad_norm": 2.953125,
119
+ "learning_rate": 4.456824512534819e-06,
120
+ "loss": 1.3777,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.756816917084029,
125
+ "grad_norm": 2.71875,
126
+ "learning_rate": 4.735376044568246e-06,
127
+ "loss": 1.3374,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.8013355592654424,
132
+ "grad_norm": 2.90625,
133
+ "learning_rate": 5.013927576601672e-06,
134
+ "loss": 1.3524,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.8458542014468559,
139
+ "grad_norm": 2.5625,
140
+ "learning_rate": 5.292479108635098e-06,
141
+ "loss": 1.3153,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.8903728436282693,
146
+ "grad_norm": 2.375,
147
+ "learning_rate": 5.571030640668524e-06,
148
+ "loss": 1.3519,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.9348914858096828,
153
+ "grad_norm": 3.140625,
154
+ "learning_rate": 5.849582172701951e-06,
155
+ "loss": 1.348,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.9794101279910963,
160
+ "grad_norm": 2.8125,
161
+ "learning_rate": 6.128133704735376e-06,
162
+ "loss": 1.3062,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 1.0261547022815805,
167
+ "grad_norm": 2.5,
168
+ "learning_rate": 6.406685236768803e-06,
169
+ "loss": 1.4358,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 1.070673344462994,
174
+ "grad_norm": 2.40625,
175
+ "learning_rate": 6.685236768802229e-06,
176
+ "loss": 1.2481,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 1.1151919866444073,
181
+ "grad_norm": 2.8125,
182
+ "learning_rate": 6.963788300835655e-06,
183
+ "loss": 1.2833,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 1.1597106288258208,
188
+ "grad_norm": 2.140625,
189
+ "learning_rate": 7.242339832869081e-06,
190
+ "loss": 1.1941,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 1.2042292710072342,
195
+ "grad_norm": 2.46875,
196
+ "learning_rate": 7.5208913649025075e-06,
197
+ "loss": 1.2831,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 1.2487479131886476,
202
+ "grad_norm": 2.671875,
203
+ "learning_rate": 7.799442896935934e-06,
204
+ "loss": 1.2854,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 1.293266555370061,
209
+ "grad_norm": 2.46875,
210
+ "learning_rate": 8.07799442896936e-06,
211
+ "loss": 1.257,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 1.3377851975514747,
216
+ "grad_norm": 2.03125,
217
+ "learning_rate": 8.356545961002787e-06,
218
+ "loss": 1.2468,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 1.3823038397328882,
223
+ "grad_norm": 2.0625,
224
+ "learning_rate": 8.635097493036211e-06,
225
+ "loss": 1.2743,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 1.4268224819143016,
230
+ "grad_norm": 2.109375,
231
+ "learning_rate": 8.913649025069639e-06,
232
+ "loss": 1.2265,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 1.471341124095715,
237
+ "grad_norm": 2.078125,
238
+ "learning_rate": 9.192200557103064e-06,
239
+ "loss": 1.2898,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 1.5158597662771287,
244
+ "grad_norm": 2.0,
245
+ "learning_rate": 9.470752089136492e-06,
246
+ "loss": 1.2406,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 1.5603784084585421,
251
+ "grad_norm": 2.21875,
252
+ "learning_rate": 9.749303621169918e-06,
253
+ "loss": 1.2098,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 1.6048970506399556,
258
+ "grad_norm": 1.953125,
259
+ "learning_rate": 9.9999976276417e-06,
260
+ "loss": 1.2067,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 1.649415692821369,
265
+ "grad_norm": 1.9765625,
266
+ "learning_rate": 9.999712947369595e-06,
267
+ "loss": 1.2338,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 1.6939343350027825,
272
+ "grad_norm": 1.859375,
273
+ "learning_rate": 9.998953826391322e-06,
274
+ "loss": 1.2546,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 1.738452977184196,
279
+ "grad_norm": 2.015625,
280
+ "learning_rate": 9.997720336742596e-06,
281
+ "loss": 1.201,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 1.7829716193656093,
286
+ "grad_norm": 2.09375,
287
+ "learning_rate": 9.996012595473676e-06,
288
+ "loss": 1.1761,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 1.8274902615470228,
293
+ "grad_norm": 2.015625,
294
+ "learning_rate": 9.993830764638262e-06,
295
+ "loss": 1.1884,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 1.8720089037284362,
300
+ "grad_norm": 1.90625,
301
+ "learning_rate": 9.991175051278111e-06,
302
+ "loss": 1.1951,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 1.9165275459098496,
307
+ "grad_norm": 2.09375,
308
+ "learning_rate": 9.988045707403394e-06,
309
+ "loss": 1.175,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 1.961046188091263,
314
+ "grad_norm": 2.0625,
315
+ "learning_rate": 9.984443029968786e-06,
316
+ "loss": 1.2045,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 2.0077907623817475,
321
+ "grad_norm": 2.03125,
322
+ "learning_rate": 9.980367360845278e-06,
323
+ "loss": 1.3052,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 2.052309404563161,
328
+ "grad_norm": 1.984375,
329
+ "learning_rate": 9.975819086787743e-06,
330
+ "loss": 1.1092,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 2.0968280467445743,
335
+ "grad_norm": 2.1875,
336
+ "learning_rate": 9.970798639398228e-06,
337
+ "loss": 1.1435,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 2.141346688925988,
342
+ "grad_norm": 1.8828125,
343
+ "learning_rate": 9.965306495085005e-06,
344
+ "loss": 1.0927,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 2.185865331107401,
349
+ "grad_norm": 2.03125,
350
+ "learning_rate": 9.959343175017362e-06,
351
+ "loss": 1.0692,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 2.2303839732888147,
356
+ "grad_norm": 1.8671875,
357
+ "learning_rate": 9.952909245076141e-06,
358
+ "loss": 1.0603,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 2.274902615470228,
363
+ "grad_norm": 2.03125,
364
+ "learning_rate": 9.946005315800047e-06,
365
+ "loss": 1.0717,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 2.3194212576516415,
370
+ "grad_norm": 1.9140625,
371
+ "learning_rate": 9.93863204232771e-06,
372
+ "loss": 1.0808,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 2.363939899833055,
377
+ "grad_norm": 1.609375,
378
+ "learning_rate": 9.930790124335511e-06,
379
+ "loss": 1.0297,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 2.4084585420144684,
384
+ "grad_norm": 1.84375,
385
+ "learning_rate": 9.922480305971193e-06,
386
+ "loss": 1.0481,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 2.452977184195882,
391
+ "grad_norm": 1.90625,
392
+ "learning_rate": 9.91370337578325e-06,
393
+ "loss": 1.0919,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 2.4974958263772953,
398
+ "grad_norm": 2.09375,
399
+ "learning_rate": 9.904460166646084e-06,
400
+ "loss": 1.0835,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 2.542014468558709,
405
+ "grad_norm": 1.8046875,
406
+ "learning_rate": 9.894751555680988e-06,
407
+ "loss": 1.0336,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 2.586533110740122,
412
+ "grad_norm": 2.0625,
413
+ "learning_rate": 9.884578464172901e-06,
414
+ "loss": 1.0728,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 2.631051752921536,
419
+ "grad_norm": 1.6484375,
420
+ "learning_rate": 9.873941857482988e-06,
421
+ "loss": 1.0493,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 2.6755703951029495,
426
+ "grad_norm": 1.796875,
427
+ "learning_rate": 9.862842744957037e-06,
428
+ "loss": 1.0346,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 2.720089037284363,
433
+ "grad_norm": 1.7421875,
434
+ "learning_rate": 9.85128217982967e-06,
435
+ "loss": 1.0483,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 2.7646076794657763,
440
+ "grad_norm": 1.6796875,
441
+ "learning_rate": 9.8392612591244e-06,
442
+ "loss": 1.0384,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 2.80912632164719,
447
+ "grad_norm": 1.765625,
448
+ "learning_rate": 9.826781123549542e-06,
449
+ "loss": 1.0266,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 2.853644963828603,
454
+ "grad_norm": 1.578125,
455
+ "learning_rate": 9.813842957389953e-06,
456
+ "loss": 1.0352,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 2.8981636060100167,
461
+ "grad_norm": 1.796875,
462
+ "learning_rate": 9.800447988394657e-06,
463
+ "loss": 1.009,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 2.94268224819143,
468
+ "grad_norm": 1.796875,
469
+ "learning_rate": 9.786597487660336e-06,
470
+ "loss": 1.0834,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 2.9872008903728435,
475
+ "grad_norm": 1.8046875,
476
+ "learning_rate": 9.772292769510718e-06,
477
+ "loss": 1.0735,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 3.033945464663328,
482
+ "grad_norm": 1.6484375,
483
+ "learning_rate": 9.75753519137185e-06,
484
+ "loss": 1.0532,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 3.0784641068447414,
489
+ "grad_norm": 1.8125,
490
+ "learning_rate": 9.742326153643285e-06,
491
+ "loss": 0.9169,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 3.122982749026155,
496
+ "grad_norm": 1.671875,
497
+ "learning_rate": 9.726667099565202e-06,
498
+ "loss": 0.9443,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 3.1675013912075682,
503
+ "grad_norm": 1.6015625,
504
+ "learning_rate": 9.710559515081446e-06,
505
+ "loss": 0.9023,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 3.2120200333889817,
510
+ "grad_norm": 1.7265625,
511
+ "learning_rate": 9.69400492869852e-06,
512
+ "loss": 0.9227,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 3.256538675570395,
517
+ "grad_norm": 1.71875,
518
+ "learning_rate": 9.677004911340539e-06,
519
+ "loss": 0.9329,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 3.3010573177518086,
524
+ "grad_norm": 1.875,
525
+ "learning_rate": 9.659561076200173e-06,
526
+ "loss": 0.903,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 3.345575959933222,
531
+ "grad_norm": 1.484375,
532
+ "learning_rate": 9.64167507858554e-06,
533
+ "loss": 0.9046,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 3.3900946021146354,
538
+ "grad_norm": 1.65625,
539
+ "learning_rate": 9.62334861576315e-06,
540
+ "loss": 0.927,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 3.434613244296049,
545
+ "grad_norm": 1.8046875,
546
+ "learning_rate": 9.604583426796837e-06,
547
+ "loss": 0.9274,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 3.4791318864774623,
552
+ "grad_norm": 1.53125,
553
+ "learning_rate": 9.585381292382734e-06,
554
+ "loss": 0.9127,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 3.5236505286588757,
559
+ "grad_norm": 1.59375,
560
+ "learning_rate": 9.565744034680291e-06,
561
+ "loss": 0.9269,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 3.5681691708402896,
566
+ "grad_norm": 1.6796875,
567
+ "learning_rate": 9.545673517139376e-06,
568
+ "loss": 0.8863,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 3.6126878130217026,
573
+ "grad_norm": 1.359375,
574
+ "learning_rate": 9.52517164432343e-06,
575
+ "loss": 0.8776,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 3.6572064552031165,
580
+ "grad_norm": 1.3359375,
581
+ "learning_rate": 9.50424036172875e-06,
582
+ "loss": 0.9424,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 3.70172509738453,
587
+ "grad_norm": 1.4296875,
588
+ "learning_rate": 9.482881655599867e-06,
589
+ "loss": 0.8712,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 3.7462437395659434,
594
+ "grad_norm": 1.5390625,
595
+ "learning_rate": 9.461097552741065e-06,
596
+ "loss": 0.9157,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 3.790762381747357,
601
+ "grad_norm": 1.296875,
602
+ "learning_rate": 9.438890120324049e-06,
603
+ "loss": 0.8571,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 3.8352810239287702,
608
+ "grad_norm": 1.328125,
609
+ "learning_rate": 9.416261465691786e-06,
610
+ "loss": 0.861,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 3.8797996661101837,
615
+ "grad_norm": 1.265625,
616
+ "learning_rate": 9.393213736158532e-06,
617
+ "loss": 0.8952,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 3.924318308291597,
622
+ "grad_norm": 1.328125,
623
+ "learning_rate": 9.369749118806063e-06,
624
+ "loss": 0.8598,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 3.9688369504730105,
629
+ "grad_norm": 1.3359375,
630
+ "learning_rate": 9.345869840276138e-06,
631
+ "loss": 0.8614,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 4.015581524763495,
636
+ "grad_norm": 1.0625,
637
+ "learning_rate": 9.321578166559202e-06,
638
+ "loss": 0.8842,
639
+ "step": 900
640
+ },
641
+ {
642
+ "epoch": 4.060100166944908,
643
+ "grad_norm": 1.25,
644
+ "learning_rate": 9.296876402779357e-06,
645
+ "loss": 0.7889,
646
+ "step": 910
647
+ },
648
+ {
649
+ "epoch": 4.104618809126322,
650
+ "grad_norm": 1.2109375,
651
+ "learning_rate": 9.271766892975632e-06,
652
+ "loss": 0.8188,
653
+ "step": 920
654
+ },
655
+ {
656
+ "epoch": 4.149137451307735,
657
+ "grad_norm": 1.1796875,
658
+ "learning_rate": 9.246252019879526e-06,
659
+ "loss": 0.7822,
660
+ "step": 930
661
+ },
662
+ {
663
+ "epoch": 4.193656093489149,
664
+ "grad_norm": 1.0546875,
665
+ "learning_rate": 9.22033420468893e-06,
666
+ "loss": 0.8268,
667
+ "step": 940
668
+ },
669
+ {
670
+ "epoch": 4.238174735670562,
671
+ "grad_norm": 1.015625,
672
+ "learning_rate": 9.194015906838345e-06,
673
+ "loss": 0.7838,
674
+ "step": 950
675
+ },
676
+ {
677
+ "epoch": 4.282693377851976,
678
+ "grad_norm": 1.2109375,
679
+ "learning_rate": 9.167299623765515e-06,
680
+ "loss": 0.7691,
681
+ "step": 960
682
+ },
683
+ {
684
+ "epoch": 4.3272120200333895,
685
+ "grad_norm": 1.171875,
686
+ "learning_rate": 9.14018789067443e-06,
687
+ "loss": 0.7575,
688
+ "step": 970
689
+ },
690
+ {
691
+ "epoch": 4.371730662214802,
692
+ "grad_norm": 1.1640625,
693
+ "learning_rate": 9.11268328029475e-06,
694
+ "loss": 0.8305,
695
+ "step": 980
696
+ },
697
+ {
698
+ "epoch": 4.416249304396216,
699
+ "grad_norm": 1.0390625,
700
+ "learning_rate": 9.08478840263767e-06,
701
+ "loss": 0.7607,
702
+ "step": 990
703
+ },
704
+ {
705
+ "epoch": 4.460767946577629,
706
+ "grad_norm": 0.99609375,
707
+ "learning_rate": 9.05650590474825e-06,
708
+ "loss": 0.7759,
709
+ "step": 1000
710
+ },
711
+ {
712
+ "epoch": 4.460767946577629,
713
+ "eval_loss": 1.0106589794158936,
714
+ "eval_runtime": 46.0703,
715
+ "eval_samples_per_second": 8.682,
716
+ "eval_steps_per_second": 8.682,
717
+ "step": 1000
718
+ },
719
+ {
720
+ "epoch": 4.505286588759043,
721
+ "grad_norm": 0.9140625,
722
+ "learning_rate": 9.027838470454222e-06,
723
+ "loss": 0.7025,
724
+ "step": 1010
725
+ },
726
+ {
727
+ "epoch": 4.549805230940456,
728
+ "grad_norm": 1.046875,
729
+ "learning_rate": 8.998788820111323e-06,
730
+ "loss": 0.776,
731
+ "step": 1020
732
+ },
733
+ {
734
+ "epoch": 4.59432387312187,
735
+ "grad_norm": 1.0078125,
736
+ "learning_rate": 8.969359710345132e-06,
737
+ "loss": 0.8328,
738
+ "step": 1030
739
+ },
740
+ {
741
+ "epoch": 4.638842515303283,
742
+ "grad_norm": 1.0546875,
743
+ "learning_rate": 8.939553933789499e-06,
744
+ "loss": 0.7564,
745
+ "step": 1040
746
+ },
747
+ {
748
+ "epoch": 4.683361157484697,
749
+ "grad_norm": 1.1796875,
750
+ "learning_rate": 8.90937431882154e-06,
751
+ "loss": 0.7684,
752
+ "step": 1050
753
+ },
754
+ {
755
+ "epoch": 4.72787979966611,
756
+ "grad_norm": 1.109375,
757
+ "learning_rate": 8.878823729293238e-06,
758
+ "loss": 0.8135,
759
+ "step": 1060
760
+ },
761
+ {
762
+ "epoch": 4.772398441847524,
763
+ "grad_norm": 1.1953125,
764
+ "learning_rate": 8.847905064259683e-06,
765
+ "loss": 0.8271,
766
+ "step": 1070
767
+ },
768
+ {
769
+ "epoch": 4.816917084028937,
770
+ "grad_norm": 1.0625,
771
+ "learning_rate": 8.816621257703969e-06,
772
+ "loss": 0.8179,
773
+ "step": 1080
774
+ },
775
+ {
776
+ "epoch": 4.861435726210351,
777
+ "grad_norm": 1.0546875,
778
+ "learning_rate": 8.784975278258783e-06,
779
+ "loss": 0.7721,
780
+ "step": 1090
781
+ },
782
+ {
783
+ "epoch": 4.905954368391764,
784
+ "grad_norm": 1.0546875,
785
+ "learning_rate": 8.752970128924696e-06,
786
+ "loss": 0.7752,
787
+ "step": 1100
788
+ },
789
+ {
790
+ "epoch": 4.950473010573178,
791
+ "grad_norm": 0.91015625,
792
+ "learning_rate": 8.7206088467852e-06,
793
+ "loss": 0.788,
794
+ "step": 1110
795
+ },
796
+ {
797
+ "epoch": 4.994991652754591,
798
+ "grad_norm": 0.9609375,
799
+ "learning_rate": 8.687894502718503e-06,
800
+ "loss": 0.8012,
801
+ "step": 1120
802
+ },
803
+ {
804
+ "epoch": 5.041736227045075,
805
+ "grad_norm": 0.8984375,
806
+ "learning_rate": 8.654830201106133e-06,
807
+ "loss": 0.8055,
808
+ "step": 1130
809
+ },
810
+ {
811
+ "epoch": 5.086254869226488,
812
+ "grad_norm": 0.98046875,
813
+ "learning_rate": 8.621419079538337e-06,
814
+ "loss": 0.7483,
815
+ "step": 1140
816
+ },
817
+ {
818
+ "epoch": 5.130773511407902,
819
+ "grad_norm": 0.9375,
820
+ "learning_rate": 8.587664308516361e-06,
821
+ "loss": 0.7349,
822
+ "step": 1150
823
+ },
824
+ {
825
+ "epoch": 5.175292153589315,
826
+ "grad_norm": 0.80859375,
827
+ "learning_rate": 8.553569091151576e-06,
828
+ "loss": 0.7454,
829
+ "step": 1160
830
+ },
831
+ {
832
+ "epoch": 5.219810795770729,
833
+ "grad_norm": 0.953125,
834
+ "learning_rate": 8.519136662861531e-06,
835
+ "loss": 0.6866,
836
+ "step": 1170
837
+ },
838
+ {
839
+ "epoch": 5.264329437952142,
840
+ "grad_norm": 0.859375,
841
+ "learning_rate": 8.484370291062927e-06,
842
+ "loss": 0.7269,
843
+ "step": 1180
844
+ },
845
+ {
846
+ "epoch": 5.308848080133556,
847
+ "grad_norm": 0.94140625,
848
+ "learning_rate": 8.449273274861566e-06,
849
+ "loss": 0.6977,
850
+ "step": 1190
851
+ },
852
+ {
853
+ "epoch": 5.353366722314969,
854
+ "grad_norm": 0.8984375,
855
+ "learning_rate": 8.413848944739282e-06,
856
+ "loss": 0.6814,
857
+ "step": 1200
858
+ },
859
+ {
860
+ "epoch": 5.397885364496383,
861
+ "grad_norm": 0.97265625,
862
+ "learning_rate": 8.378100662237904e-06,
863
+ "loss": 0.7206,
864
+ "step": 1210
865
+ },
866
+ {
867
+ "epoch": 5.442404006677796,
868
+ "grad_norm": 0.85546875,
869
+ "learning_rate": 8.342031819640263e-06,
870
+ "loss": 0.7317,
871
+ "step": 1220
872
+ },
873
+ {
874
+ "epoch": 5.48692264885921,
875
+ "grad_norm": 0.859375,
876
+ "learning_rate": 8.305645839648287e-06,
877
+ "loss": 0.7149,
878
+ "step": 1230
879
+ },
880
+ {
881
+ "epoch": 5.531441291040624,
882
+ "grad_norm": 0.8984375,
883
+ "learning_rate": 8.268946175058214e-06,
884
+ "loss": 0.6568,
885
+ "step": 1240
886
+ },
887
+ {
888
+ "epoch": 5.575959933222037,
889
+ "grad_norm": 0.859375,
890
+ "learning_rate": 8.231936308432935e-06,
891
+ "loss": 0.7292,
892
+ "step": 1250
893
+ },
894
+ {
895
+ "epoch": 5.6204785754034505,
896
+ "grad_norm": 0.82421875,
897
+ "learning_rate": 8.194619751771527e-06,
898
+ "loss": 0.6966,
899
+ "step": 1260
900
+ },
901
+ {
902
+ "epoch": 5.6649972175848635,
903
+ "grad_norm": 0.85546875,
904
+ "learning_rate": 8.157000046175984e-06,
905
+ "loss": 0.7128,
906
+ "step": 1270
907
+ },
908
+ {
909
+ "epoch": 5.709515859766277,
910
+ "grad_norm": 0.77734375,
911
+ "learning_rate": 8.119080761515197e-06,
912
+ "loss": 0.7343,
913
+ "step": 1280
914
+ },
915
+ {
916
+ "epoch": 5.75403450194769,
917
+ "grad_norm": 0.953125,
918
+ "learning_rate": 8.080865496086177e-06,
919
+ "loss": 0.7454,
920
+ "step": 1290
921
+ },
922
+ {
923
+ "epoch": 5.798553144129104,
924
+ "grad_norm": 0.89453125,
925
+ "learning_rate": 8.042357876272626e-06,
926
+ "loss": 0.7337,
927
+ "step": 1300
928
+ },
929
+ {
930
+ "epoch": 5.843071786310517,
931
+ "grad_norm": 0.796875,
932
+ "learning_rate": 8.003561556200796e-06,
933
+ "loss": 0.7011,
934
+ "step": 1310
935
+ },
936
+ {
937
+ "epoch": 5.887590428491931,
938
+ "grad_norm": 0.83984375,
939
+ "learning_rate": 7.964480217392739e-06,
940
+ "loss": 0.6969,
941
+ "step": 1320
942
+ },
943
+ {
944
+ "epoch": 5.932109070673344,
945
+ "grad_norm": 0.96484375,
946
+ "learning_rate": 7.925117568416966e-06,
947
+ "loss": 0.7272,
948
+ "step": 1330
949
+ },
950
+ {
951
+ "epoch": 5.976627712854758,
952
+ "grad_norm": 0.89453125,
953
+ "learning_rate": 7.885477344536516e-06,
954
+ "loss": 0.6795,
955
+ "step": 1340
956
+ },
957
+ {
958
+ "epoch": 6.023372287145242,
959
+ "grad_norm": 0.8828125,
960
+ "learning_rate": 7.845563307354506e-06,
961
+ "loss": 0.7507,
962
+ "step": 1350
963
+ },
964
+ {
965
+ "epoch": 6.067890929326656,
966
+ "grad_norm": 0.83984375,
967
+ "learning_rate": 7.80537924445718e-06,
968
+ "loss": 0.6812,
969
+ "step": 1360
970
+ },
971
+ {
972
+ "epoch": 6.112409571508069,
973
+ "grad_norm": 0.94921875,
974
+ "learning_rate": 7.764928969054493e-06,
975
+ "loss": 0.694,
976
+ "step": 1370
977
+ },
978
+ {
979
+ "epoch": 6.156928213689483,
980
+ "grad_norm": 0.87890625,
981
+ "learning_rate": 7.724216319618257e-06,
982
+ "loss": 0.6636,
983
+ "step": 1380
984
+ },
985
+ {
986
+ "epoch": 6.201446855870896,
987
+ "grad_norm": 0.828125,
988
+ "learning_rate": 7.683245159517903e-06,
989
+ "loss": 0.6817,
990
+ "step": 1390
991
+ },
992
+ {
993
+ "epoch": 6.24596549805231,
994
+ "grad_norm": 1.0546875,
995
+ "learning_rate": 7.642019376653858e-06,
996
+ "loss": 0.6709,
997
+ "step": 1400
998
+ },
999
+ {
1000
+ "epoch": 6.290484140233723,
1001
+ "grad_norm": 0.8515625,
1002
+ "learning_rate": 7.600542883088629e-06,
1003
+ "loss": 0.6755,
1004
+ "step": 1410
1005
+ },
1006
+ {
1007
+ "epoch": 6.3350027824151365,
1008
+ "grad_norm": 1.03125,
1009
+ "learning_rate": 7.5588196146755526e-06,
1010
+ "loss": 0.7135,
1011
+ "step": 1420
1012
+ },
1013
+ {
1014
+ "epoch": 6.3795214245965495,
1015
+ "grad_norm": 0.78515625,
1016
+ "learning_rate": 7.5168535306853155e-06,
1017
+ "loss": 0.6461,
1018
+ "step": 1430
1019
+ },
1020
+ {
1021
+ "epoch": 6.424040066777963,
1022
+ "grad_norm": 0.77734375,
1023
+ "learning_rate": 7.474648613430252e-06,
1024
+ "loss": 0.6194,
1025
+ "step": 1440
1026
+ },
1027
+ {
1028
+ "epoch": 6.468558708959376,
1029
+ "grad_norm": 1.2421875,
1030
+ "learning_rate": 7.432208867886439e-06,
1031
+ "loss": 0.6871,
1032
+ "step": 1450
1033
+ },
1034
+ {
1035
+ "epoch": 6.51307735114079,
1036
+ "grad_norm": 1.3828125,
1037
+ "learning_rate": 7.389538321313652e-06,
1038
+ "loss": 0.6691,
1039
+ "step": 1460
1040
+ },
1041
+ {
1042
+ "epoch": 6.557595993322204,
1043
+ "grad_norm": 1.625,
1044
+ "learning_rate": 7.346641022873205e-06,
1045
+ "loss": 0.6686,
1046
+ "step": 1470
1047
+ },
1048
+ {
1049
+ "epoch": 6.602114635503617,
1050
+ "grad_norm": 1.8046875,
1051
+ "learning_rate": 7.303521043243711e-06,
1052
+ "loss": 0.648,
1053
+ "step": 1480
1054
+ },
1055
+ {
1056
+ "epoch": 6.646633277685031,
1057
+ "grad_norm": 2.40625,
1058
+ "learning_rate": 7.2601824742347985e-06,
1059
+ "loss": 0.7131,
1060
+ "step": 1490
1061
+ },
1062
+ {
1063
+ "epoch": 6.691151919866444,
1064
+ "grad_norm": 1.09375,
1065
+ "learning_rate": 7.2166294283988315e-06,
1066
+ "loss": 0.7121,
1067
+ "step": 1500
1068
+ },
1069
+ {
1070
+ "epoch": 6.735670562047858,
1071
+ "grad_norm": 0.9765625,
1072
+ "learning_rate": 7.172866038640644e-06,
1073
+ "loss": 0.6216,
1074
+ "step": 1510
1075
+ },
1076
+ {
1077
+ "epoch": 6.780189204229271,
1078
+ "grad_norm": 1.0390625,
1079
+ "learning_rate": 7.128896457825364e-06,
1080
+ "loss": 0.6726,
1081
+ "step": 1520
1082
+ },
1083
+ {
1084
+ "epoch": 6.824707846410685,
1085
+ "grad_norm": 1.1328125,
1086
+ "learning_rate": 7.084724858384326e-06,
1087
+ "loss": 0.6597,
1088
+ "step": 1530
1089
+ },
1090
+ {
1091
+ "epoch": 6.869226488592098,
1092
+ "grad_norm": 1.0546875,
1093
+ "learning_rate": 7.04035543191914e-06,
1094
+ "loss": 0.6608,
1095
+ "step": 1540
1096
+ },
1097
+ {
1098
+ "epoch": 6.913745130773512,
1099
+ "grad_norm": 1.78125,
1100
+ "learning_rate": 6.995792388803929e-06,
1101
+ "loss": 0.6419,
1102
+ "step": 1550
1103
+ },
1104
+ {
1105
+ "epoch": 6.958263772954925,
1106
+ "grad_norm": 1.7734375,
1107
+ "learning_rate": 6.9510399577857976e-06,
1108
+ "loss": 0.6505,
1109
+ "step": 1560
1110
+ },
1111
+ {
1112
+ "epoch": 7.005008347245409,
1113
+ "grad_norm": 2.015625,
1114
+ "learning_rate": 6.906102385583548e-06,
1115
+ "loss": 0.734,
1116
+ "step": 1570
1117
+ },
1118
+ {
1119
+ "epoch": 7.049526989426822,
1120
+ "grad_norm": 1.9140625,
1121
+ "learning_rate": 6.860983936484689e-06,
1122
+ "loss": 0.6262,
1123
+ "step": 1580
1124
+ },
1125
+ {
1126
+ "epoch": 7.094045631608236,
1127
+ "grad_norm": 1.953125,
1128
+ "learning_rate": 6.815688891940796e-06,
1129
+ "loss": 0.6499,
1130
+ "step": 1590
1131
+ },
1132
+ {
1133
+ "epoch": 7.138564273789649,
1134
+ "grad_norm": 4.53125,
1135
+ "learning_rate": 6.770221550161214e-06,
1136
+ "loss": 0.6259,
1137
+ "step": 1600
1138
+ },
1139
+ {
1140
+ "epoch": 7.183082915971063,
1141
+ "grad_norm": 5.1875,
1142
+ "learning_rate": 6.724586225705191e-06,
1143
+ "loss": 0.6564,
1144
+ "step": 1610
1145
+ },
1146
+ {
1147
+ "epoch": 7.227601558152476,
1148
+ "grad_norm": 6.1875,
1149
+ "learning_rate": 6.678787249072456e-06,
1150
+ "loss": 0.6358,
1151
+ "step": 1620
1152
+ },
1153
+ {
1154
+ "epoch": 7.27212020033389,
1155
+ "grad_norm": 4.9375,
1156
+ "learning_rate": 6.632828966292279e-06,
1157
+ "loss": 0.6883,
1158
+ "step": 1630
1159
+ },
1160
+ {
1161
+ "epoch": 7.316638842515303,
1162
+ "grad_norm": 4.625,
1163
+ "learning_rate": 6.586715738511067e-06,
1164
+ "loss": 0.6618,
1165
+ "step": 1640
1166
+ },
1167
+ {
1168
+ "epoch": 7.361157484696717,
1169
+ "grad_norm": 10.9375,
1170
+ "learning_rate": 6.540451941578505e-06,
1171
+ "loss": 0.6233,
1172
+ "step": 1650
1173
+ },
1174
+ {
1175
+ "epoch": 7.40567612687813,
1176
+ "grad_norm": 12.625,
1177
+ "learning_rate": 6.494041965632335e-06,
1178
+ "loss": 0.6973,
1179
+ "step": 1660
1180
+ },
1181
+ {
1182
+ "epoch": 7.450194769059544,
1183
+ "grad_norm": 11.5,
1184
+ "learning_rate": 6.447490214681742e-06,
1185
+ "loss": 0.6683,
1186
+ "step": 1670
1187
+ },
1188
+ {
1189
+ "epoch": 7.494713411240957,
1190
+ "grad_norm": 10.625,
1191
+ "learning_rate": 6.400801106189457e-06,
1192
+ "loss": 0.5964,
1193
+ "step": 1680
1194
+ },
1195
+ {
1196
+ "epoch": 7.539232053422371,
1197
+ "grad_norm": 9.875,
1198
+ "learning_rate": 6.353979070652555e-06,
1199
+ "loss": 0.6784,
1200
+ "step": 1690
1201
+ },
1202
+ {
1203
+ "epoch": 7.583750695603785,
1204
+ "grad_norm": 3.671875,
1205
+ "learning_rate": 6.307028551182041e-06,
1206
+ "loss": 0.6335,
1207
+ "step": 1700
1208
+ },
1209
+ {
1210
+ "epoch": 7.628269337785198,
1211
+ "grad_norm": 3.421875,
1212
+ "learning_rate": 6.259954003081215e-06,
1213
+ "loss": 0.6539,
1214
+ "step": 1710
1215
+ },
1216
+ {
1217
+ "epoch": 7.6727879799666105,
1218
+ "grad_norm": 2.828125,
1219
+ "learning_rate": 6.212759893422908e-06,
1220
+ "loss": 0.6371,
1221
+ "step": 1720
1222
+ },
1223
+ {
1224
+ "epoch": 7.717306622148024,
1225
+ "grad_norm": 3.734375,
1226
+ "learning_rate": 6.165450700625565e-06,
1227
+ "loss": 0.6426,
1228
+ "step": 1730
1229
+ },
1230
+ {
1231
+ "epoch": 7.761825264329438,
1232
+ "grad_norm": 3.0,
1233
+ "learning_rate": 6.118030914028292e-06,
1234
+ "loss": 0.6587,
1235
+ "step": 1740
1236
+ },
1237
+ {
1238
+ "epoch": 7.806343906510851,
1239
+ "grad_norm": 3.234375,
1240
+ "learning_rate": 6.070505033464835e-06,
1241
+ "loss": 0.5994,
1242
+ "step": 1750
1243
+ },
1244
+ {
1245
+ "epoch": 7.850862548692265,
1246
+ "grad_norm": 3.0,
1247
+ "learning_rate": 6.022877568836579e-06,
1248
+ "loss": 0.6387,
1249
+ "step": 1760
1250
+ },
1251
+ {
1252
+ "epoch": 7.895381190873678,
1253
+ "grad_norm": 2.90625,
1254
+ "learning_rate": 5.975153039684579e-06,
1255
+ "loss": 0.6704,
1256
+ "step": 1770
1257
+ },
1258
+ {
1259
+ "epoch": 7.939899833055092,
1260
+ "grad_norm": 2.609375,
1261
+ "learning_rate": 5.927335974760699e-06,
1262
+ "loss": 0.6274,
1263
+ "step": 1780
1264
+ },
1265
+ {
1266
+ "epoch": 7.984418475236505,
1267
+ "grad_norm": 3.03125,
1268
+ "learning_rate": 5.87943091159785e-06,
1269
+ "loss": 0.6611,
1270
+ "step": 1790
1271
+ },
1272
+ {
1273
+ "epoch": 8.03116304952699,
1274
+ "grad_norm": 2.609375,
1275
+ "learning_rate": 5.831442396079413e-06,
1276
+ "loss": 0.6732,
1277
+ "step": 1800
1278
+ },
1279
+ {
1280
+ "epoch": 8.075681691708404,
1281
+ "grad_norm": 3.078125,
1282
+ "learning_rate": 5.78337498200786e-06,
1283
+ "loss": 0.5774,
1284
+ "step": 1810
1285
+ },
1286
+ {
1287
+ "epoch": 8.120200333889816,
1288
+ "grad_norm": 2.71875,
1289
+ "learning_rate": 5.735233230672636e-06,
1290
+ "loss": 0.6312,
1291
+ "step": 1820
1292
+ },
1293
+ {
1294
+ "epoch": 8.16471897607123,
1295
+ "grad_norm": 2.96875,
1296
+ "learning_rate": 5.687021710417308e-06,
1297
+ "loss": 0.6262,
1298
+ "step": 1830
1299
+ },
1300
+ {
1301
+ "epoch": 8.209237618252644,
1302
+ "grad_norm": 2.765625,
1303
+ "learning_rate": 5.638744996206074e-06,
1304
+ "loss": 0.5604,
1305
+ "step": 1840
1306
+ },
1307
+ {
1308
+ "epoch": 8.253756260434058,
1309
+ "grad_norm": 3.078125,
1310
+ "learning_rate": 5.590407669189612e-06,
1311
+ "loss": 0.6017,
1312
+ "step": 1850
1313
+ },
1314
+ {
1315
+ "epoch": 8.29827490261547,
1316
+ "grad_norm": 2.140625,
1317
+ "learning_rate": 5.542014316270377e-06,
1318
+ "loss": 0.5133,
1319
+ "step": 1860
1320
+ },
1321
+ {
1322
+ "epoch": 8.342793544796884,
1323
+ "grad_norm": 2.5,
1324
+ "learning_rate": 5.493569529667312e-06,
1325
+ "loss": 0.5995,
1326
+ "step": 1870
1327
+ },
1328
+ {
1329
+ "epoch": 8.387312186978297,
1330
+ "grad_norm": 2.96875,
1331
+ "learning_rate": 5.445077906480095e-06,
1332
+ "loss": 0.6081,
1333
+ "step": 1880
1334
+ },
1335
+ {
1336
+ "epoch": 8.431830829159711,
1337
+ "grad_norm": 2.359375,
1338
+ "learning_rate": 5.396544048252893e-06,
1339
+ "loss": 0.6193,
1340
+ "step": 1890
1341
+ },
1342
+ {
1343
+ "epoch": 8.476349471341123,
1344
+ "grad_norm": 2.5625,
1345
+ "learning_rate": 5.3479725605377065e-06,
1346
+ "loss": 0.568,
1347
+ "step": 1900
1348
+ },
1349
+ {
1350
+ "epoch": 8.520868113522537,
1351
+ "grad_norm": 2.59375,
1352
+ "learning_rate": 5.299368052457332e-06,
1353
+ "loss": 0.5966,
1354
+ "step": 1910
1355
+ },
1356
+ {
1357
+ "epoch": 8.565386755703951,
1358
+ "grad_norm": 2.90625,
1359
+ "learning_rate": 5.250735136267993e-06,
1360
+ "loss": 0.6217,
1361
+ "step": 1920
1362
+ },
1363
+ {
1364
+ "epoch": 8.609905397885365,
1365
+ "grad_norm": 2.375,
1366
+ "learning_rate": 5.2020784269216515e-06,
1367
+ "loss": 0.554,
1368
+ "step": 1930
1369
+ },
1370
+ {
1371
+ "epoch": 8.654424040066779,
1372
+ "grad_norm": 2.40625,
1373
+ "learning_rate": 5.153402541628097e-06,
1374
+ "loss": 0.562,
1375
+ "step": 1940
1376
+ },
1377
+ {
1378
+ "epoch": 8.698942682248191,
1379
+ "grad_norm": 2.203125,
1380
+ "learning_rate": 5.1047120994167855e-06,
1381
+ "loss": 0.598,
1382
+ "step": 1950
1383
+ },
1384
+ {
1385
+ "epoch": 8.743461324429605,
1386
+ "grad_norm": 2.96875,
1387
+ "learning_rate": 5.056011720698536e-06,
1388
+ "loss": 0.6065,
1389
+ "step": 1960
1390
+ },
1391
+ {
1392
+ "epoch": 8.787979966611019,
1393
+ "grad_norm": 2.53125,
1394
+ "learning_rate": 5.007306026827076e-06,
1395
+ "loss": 0.5696,
1396
+ "step": 1970
1397
+ },
1398
+ {
1399
+ "epoch": 8.832498608792433,
1400
+ "grad_norm": 2.171875,
1401
+ "learning_rate": 4.958599639660508e-06,
1402
+ "loss": 0.5824,
1403
+ "step": 1980
1404
+ },
1405
+ {
1406
+ "epoch": 8.877017250973845,
1407
+ "grad_norm": 2.5625,
1408
+ "learning_rate": 4.909897181122725e-06,
1409
+ "loss": 0.6082,
1410
+ "step": 1990
1411
+ },
1412
+ {
1413
+ "epoch": 8.921535893155259,
1414
+ "grad_norm": 2.84375,
1415
+ "learning_rate": 4.861203272764813e-06,
1416
+ "loss": 0.554,
1417
+ "step": 2000
1418
+ },
1419
+ {
1420
+ "epoch": 8.921535893155259,
1421
+ "eval_loss": 0.9391384720802307,
1422
+ "eval_runtime": 17.1717,
1423
+ "eval_samples_per_second": 23.294,
1424
+ "eval_steps_per_second": 23.294,
1425
+ "step": 2000
1426
+ },
1427
+ {
1428
+ "epoch": 8.966054535336673,
1429
+ "grad_norm": 2.125,
1430
+ "learning_rate": 4.8125225353265085e-06,
1431
+ "loss": 0.5373,
1432
+ "step": 2010
1433
+ },
1434
+ {
1435
+ "epoch": 9.012799109627156,
1436
+ "grad_norm": 2.203125,
1437
+ "learning_rate": 4.7638595882977064e-06,
1438
+ "loss": 0.6353,
1439
+ "step": 2020
1440
+ },
1441
+ {
1442
+ "epoch": 9.05731775180857,
1443
+ "grad_norm": 2.25,
1444
+ "learning_rate": 4.71521904948011e-06,
1445
+ "loss": 0.5151,
1446
+ "step": 2030
1447
+ },
1448
+ {
1449
+ "epoch": 9.101836393989982,
1450
+ "grad_norm": 1.9296875,
1451
+ "learning_rate": 4.666605534549021e-06,
1452
+ "loss": 0.5314,
1453
+ "step": 2040
1454
+ },
1455
+ {
1456
+ "epoch": 9.146355036171396,
1457
+ "grad_norm": 2.296875,
1458
+ "learning_rate": 4.618023656615352e-06,
1459
+ "loss": 0.5424,
1460
+ "step": 2050
1461
+ },
1462
+ {
1463
+ "epoch": 9.19087367835281,
1464
+ "grad_norm": 2.21875,
1465
+ "learning_rate": 4.569478025787869e-06,
1466
+ "loss": 0.4959,
1467
+ "step": 2060
1468
+ },
1469
+ {
1470
+ "epoch": 9.235392320534224,
1471
+ "grad_norm": 2.078125,
1472
+ "learning_rate": 4.520973248735715e-06,
1473
+ "loss": 0.5301,
1474
+ "step": 2070
1475
+ },
1476
+ {
1477
+ "epoch": 9.279910962715638,
1478
+ "grad_norm": 2.265625,
1479
+ "learning_rate": 4.472513928251275e-06,
1480
+ "loss": 0.5219,
1481
+ "step": 2080
1482
+ },
1483
+ {
1484
+ "epoch": 9.32442960489705,
1485
+ "grad_norm": 3.078125,
1486
+ "learning_rate": 4.424104662813396e-06,
1487
+ "loss": 0.5537,
1488
+ "step": 2090
1489
+ },
1490
+ {
1491
+ "epoch": 9.368948247078464,
1492
+ "grad_norm": 2.21875,
1493
+ "learning_rate": 4.375750046151023e-06,
1494
+ "loss": 0.5269,
1495
+ "step": 2100
1496
+ },
1497
+ {
1498
+ "epoch": 9.413466889259878,
1499
+ "grad_norm": 1.84375,
1500
+ "learning_rate": 4.3274546668072835e-06,
1501
+ "loss": 0.5535,
1502
+ "step": 2110
1503
+ },
1504
+ {
1505
+ "epoch": 9.457985531441292,
1506
+ "grad_norm": 2.234375,
1507
+ "learning_rate": 4.279223107704058e-06,
1508
+ "loss": 0.5382,
1509
+ "step": 2120
1510
+ },
1511
+ {
1512
+ "epoch": 9.502504173622704,
1513
+ "grad_norm": 2.1875,
1514
+ "learning_rate": 4.2310599457071e-06,
1515
+ "loss": 0.5643,
1516
+ "step": 2130
1517
+ },
1518
+ {
1519
+ "epoch": 9.547022815804118,
1520
+ "grad_norm": 2.171875,
1521
+ "learning_rate": 4.1829697511917146e-06,
1522
+ "loss": 0.5493,
1523
+ "step": 2140
1524
+ },
1525
+ {
1526
+ "epoch": 9.591541457985532,
1527
+ "grad_norm": 2.328125,
1528
+ "learning_rate": 4.134957087609065e-06,
1529
+ "loss": 0.5457,
1530
+ "step": 2150
1531
+ },
1532
+ {
1533
+ "epoch": 9.636060100166945,
1534
+ "grad_norm": 2.484375,
1535
+ "learning_rate": 4.087026511053116e-06,
1536
+ "loss": 0.4859,
1537
+ "step": 2160
1538
+ },
1539
+ {
1540
+ "epoch": 9.680578742348358,
1541
+ "grad_norm": 2.1875,
1542
+ "learning_rate": 4.0391825698283084e-06,
1543
+ "loss": 0.4969,
1544
+ "step": 2170
1545
+ },
1546
+ {
1547
+ "epoch": 9.725097384529771,
1548
+ "grad_norm": 2.125,
1549
+ "learning_rate": 3.991429804017944e-06,
1550
+ "loss": 0.5311,
1551
+ "step": 2180
1552
+ },
1553
+ {
1554
+ "epoch": 9.769616026711185,
1555
+ "grad_norm": 1.9921875,
1556
+ "learning_rate": 3.9437727450533605e-06,
1557
+ "loss": 0.5437,
1558
+ "step": 2190
1559
+ },
1560
+ {
1561
+ "epoch": 9.8141346688926,
1562
+ "grad_norm": 1.9609375,
1563
+ "learning_rate": 3.89621591528393e-06,
1564
+ "loss": 0.5197,
1565
+ "step": 2200
1566
+ },
1567
+ {
1568
+ "epoch": 9.858653311074011,
1569
+ "grad_norm": 1.90625,
1570
+ "learning_rate": 3.848763827547915e-06,
1571
+ "loss": 0.5104,
1572
+ "step": 2210
1573
+ },
1574
+ {
1575
+ "epoch": 9.903171953255425,
1576
+ "grad_norm": 1.859375,
1577
+ "learning_rate": 3.8014209847442345e-06,
1578
+ "loss": 0.55,
1579
+ "step": 2220
1580
+ },
1581
+ {
1582
+ "epoch": 9.947690595436839,
1583
+ "grad_norm": 1.8671875,
1584
+ "learning_rate": 3.7541918794051637e-06,
1585
+ "loss": 0.53,
1586
+ "step": 2230
1587
+ },
1588
+ {
1589
+ "epoch": 9.992209237618253,
1590
+ "grad_norm": 2.203125,
1591
+ "learning_rate": 3.7070809932700134e-06,
1592
+ "loss": 0.4882,
1593
+ "step": 2240
1594
+ },
1595
+ {
1596
+ "epoch": 10.038953811908737,
1597
+ "grad_norm": 1.75,
1598
+ "learning_rate": 3.6600927968598588e-06,
1599
+ "loss": 0.4714,
1600
+ "step": 2250
1601
+ },
1602
+ {
1603
+ "epoch": 10.08347245409015,
1604
+ "grad_norm": 1.90625,
1605
+ "learning_rate": 3.613231749053304e-06,
1606
+ "loss": 0.4774,
1607
+ "step": 2260
1608
+ },
1609
+ {
1610
+ "epoch": 10.127991096271563,
1611
+ "grad_norm": 2.046875,
1612
+ "learning_rate": 3.5665022966633678e-06,
1613
+ "loss": 0.4764,
1614
+ "step": 2270
1615
+ },
1616
+ {
1617
+ "epoch": 10.172509738452977,
1618
+ "grad_norm": 1.953125,
1619
+ "learning_rate": 3.519908874015501e-06,
1620
+ "loss": 0.4632,
1621
+ "step": 2280
1622
+ },
1623
+ {
1624
+ "epoch": 10.21702838063439,
1625
+ "grad_norm": 1.9453125,
1626
+ "learning_rate": 3.473455902526809e-06,
1627
+ "loss": 0.4604,
1628
+ "step": 2290
1629
+ },
1630
+ {
1631
+ "epoch": 10.261547022815805,
1632
+ "grad_norm": 1.6484375,
1633
+ "learning_rate": 3.4271477902864836e-06,
1634
+ "loss": 0.4753,
1635
+ "step": 2300
1636
+ },
1637
+ {
1638
+ "epoch": 10.306065664997218,
1639
+ "grad_norm": 1.6875,
1640
+ "learning_rate": 3.3809889316375012e-06,
1641
+ "loss": 0.4323,
1642
+ "step": 2310
1643
+ },
1644
+ {
1645
+ "epoch": 10.35058430717863,
1646
+ "grad_norm": 1.734375,
1647
+ "learning_rate": 3.334983706759627e-06,
1648
+ "loss": 0.4659,
1649
+ "step": 2320
1650
+ },
1651
+ {
1652
+ "epoch": 10.395102949360044,
1653
+ "grad_norm": 1.9453125,
1654
+ "learning_rate": 3.2891364812537686e-06,
1655
+ "loss": 0.4896,
1656
+ "step": 2330
1657
+ },
1658
+ {
1659
+ "epoch": 10.439621591541458,
1660
+ "grad_norm": 1.8515625,
1661
+ "learning_rate": 3.2434516057277055e-06,
1662
+ "loss": 0.478,
1663
+ "step": 2340
1664
+ },
1665
+ {
1666
+ "epoch": 10.484140233722872,
1667
+ "grad_norm": 1.765625,
1668
+ "learning_rate": 3.1979334153832486e-06,
1669
+ "loss": 0.4453,
1670
+ "step": 2350
1671
+ },
1672
+ {
1673
+ "epoch": 10.528658875904284,
1674
+ "grad_norm": 1.7421875,
1675
+ "learning_rate": 3.1525862296048446e-06,
1676
+ "loss": 0.5075,
1677
+ "step": 2360
1678
+ },
1679
+ {
1680
+ "epoch": 10.573177518085698,
1681
+ "grad_norm": 1.5546875,
1682
+ "learning_rate": 3.1074143515497114e-06,
1683
+ "loss": 0.4865,
1684
+ "step": 2370
1685
+ },
1686
+ {
1687
+ "epoch": 10.617696160267112,
1688
+ "grad_norm": 1.5234375,
1689
+ "learning_rate": 3.0624220677394854e-06,
1690
+ "loss": 0.5178,
1691
+ "step": 2380
1692
+ },
1693
+ {
1694
+ "epoch": 10.662214802448526,
1695
+ "grad_norm": 2.015625,
1696
+ "learning_rate": 3.017613647653461e-06,
1697
+ "loss": 0.5069,
1698
+ "step": 2390
1699
+ },
1700
+ {
1701
+ "epoch": 10.706733444629938,
1702
+ "grad_norm": 1.4375,
1703
+ "learning_rate": 2.9729933433234402e-06,
1704
+ "loss": 0.4423,
1705
+ "step": 2400
1706
+ },
1707
+ {
1708
+ "epoch": 10.751252086811352,
1709
+ "grad_norm": 1.609375,
1710
+ "learning_rate": 2.9285653889302514e-06,
1711
+ "loss": 0.4359,
1712
+ "step": 2410
1713
+ },
1714
+ {
1715
+ "epoch": 10.795770728992766,
1716
+ "grad_norm": 1.296875,
1717
+ "learning_rate": 2.8843340004019427e-06,
1718
+ "loss": 0.4517,
1719
+ "step": 2420
1720
+ },
1721
+ {
1722
+ "epoch": 10.84028937117418,
1723
+ "grad_norm": 1.578125,
1724
+ "learning_rate": 2.8403033750137255e-06,
1725
+ "loss": 0.4775,
1726
+ "step": 2430
1727
+ },
1728
+ {
1729
+ "epoch": 10.884808013355592,
1730
+ "grad_norm": 1.5,
1731
+ "learning_rate": 2.7964776909896733e-06,
1732
+ "loss": 0.5064,
1733
+ "step": 2440
1734
+ },
1735
+ {
1736
+ "epoch": 10.929326655537006,
1737
+ "grad_norm": 1.4609375,
1738
+ "learning_rate": 2.7528611071062366e-06,
1739
+ "loss": 0.4651,
1740
+ "step": 2450
1741
+ },
1742
+ {
1743
+ "epoch": 10.97384529771842,
1744
+ "grad_norm": 1.4921875,
1745
+ "learning_rate": 2.7094577622976096e-06,
1746
+ "loss": 0.4909,
1747
+ "step": 2460
1748
+ },
1749
+ {
1750
+ "epoch": 11.020589872008903,
1751
+ "grad_norm": 1.3984375,
1752
+ "learning_rate": 2.6662717752629597e-06,
1753
+ "loss": 0.4996,
1754
+ "step": 2470
1755
+ },
1756
+ {
1757
+ "epoch": 11.065108514190317,
1758
+ "grad_norm": 1.3984375,
1759
+ "learning_rate": 2.6233072440755934e-06,
1760
+ "loss": 0.4445,
1761
+ "step": 2480
1762
+ },
1763
+ {
1764
+ "epoch": 11.109627156371731,
1765
+ "grad_norm": 1.375,
1766
+ "learning_rate": 2.580568245794085e-06,
1767
+ "loss": 0.4471,
1768
+ "step": 2490
1769
+ },
1770
+ {
1771
+ "epoch": 11.154145798553143,
1772
+ "grad_norm": 1.0703125,
1773
+ "learning_rate": 2.538058836075373e-06,
1774
+ "loss": 0.49,
1775
+ "step": 2500
1776
+ },
1777
+ {
1778
+ "epoch": 11.198664440734557,
1779
+ "grad_norm": 0.9453125,
1780
+ "learning_rate": 2.4957830487899224e-06,
1781
+ "loss": 0.4148,
1782
+ "step": 2510
1783
+ },
1784
+ {
1785
+ "epoch": 11.243183082915971,
1786
+ "grad_norm": 1.078125,
1787
+ "learning_rate": 2.4537448956389146e-06,
1788
+ "loss": 0.4247,
1789
+ "step": 2520
1790
+ },
1791
+ {
1792
+ "epoch": 11.287701725097385,
1793
+ "grad_norm": 1.1953125,
1794
+ "learning_rate": 2.411948365773588e-06,
1795
+ "loss": 0.4368,
1796
+ "step": 2530
1797
+ },
1798
+ {
1799
+ "epoch": 11.332220367278797,
1800
+ "grad_norm": 1.203125,
1801
+ "learning_rate": 2.3703974254166704e-06,
1802
+ "loss": 0.4273,
1803
+ "step": 2540
1804
+ },
1805
+ {
1806
+ "epoch": 11.376739009460211,
1807
+ "grad_norm": 1.0,
1808
+ "learning_rate": 2.3290960174860293e-06,
1809
+ "loss": 0.4421,
1810
+ "step": 2550
1811
+ },
1812
+ {
1813
+ "epoch": 11.421257651641625,
1814
+ "grad_norm": 0.97265625,
1815
+ "learning_rate": 2.2880480612204925e-06,
1816
+ "loss": 0.4072,
1817
+ "step": 2560
1818
+ },
1819
+ {
1820
+ "epoch": 11.465776293823039,
1821
+ "grad_norm": 1.2421875,
1822
+ "learning_rate": 2.247257451807961e-06,
1823
+ "loss": 0.4472,
1824
+ "step": 2570
1825
+ },
1826
+ {
1827
+ "epoch": 11.510294936004453,
1828
+ "grad_norm": 1.1328125,
1829
+ "learning_rate": 2.206728060015761e-06,
1830
+ "loss": 0.4613,
1831
+ "step": 2580
1832
+ },
1833
+ {
1834
+ "epoch": 11.554813578185865,
1835
+ "grad_norm": 1.34375,
1836
+ "learning_rate": 2.1664637318233484e-06,
1837
+ "loss": 0.4111,
1838
+ "step": 2590
1839
+ },
1840
+ {
1841
+ "epoch": 11.599332220367279,
1842
+ "grad_norm": 1.1796875,
1843
+ "learning_rate": 2.1264682880573374e-06,
1844
+ "loss": 0.4385,
1845
+ "step": 2600
1846
+ },
1847
+ {
1848
+ "epoch": 11.643850862548693,
1849
+ "grad_norm": 0.98046875,
1850
+ "learning_rate": 2.086745524028933e-06,
1851
+ "loss": 0.4448,
1852
+ "step": 2610
1853
+ },
1854
+ {
1855
+ "epoch": 11.688369504730106,
1856
+ "grad_norm": 1.1328125,
1857
+ "learning_rate": 2.0472992091737886e-06,
1858
+ "loss": 0.4292,
1859
+ "step": 2620
1860
+ },
1861
+ {
1862
+ "epoch": 11.732888146911518,
1863
+ "grad_norm": 1.2421875,
1864
+ "learning_rate": 2.0081330866942962e-06,
1865
+ "loss": 0.425,
1866
+ "step": 2630
1867
+ },
1868
+ {
1869
+ "epoch": 11.777406789092932,
1870
+ "grad_norm": 1.0859375,
1871
+ "learning_rate": 1.96925087320439e-06,
1872
+ "loss": 0.4311,
1873
+ "step": 2640
1874
+ },
1875
+ {
1876
+ "epoch": 11.821925431274346,
1877
+ "grad_norm": 0.9375,
1878
+ "learning_rate": 1.930656258376859e-06,
1879
+ "loss": 0.4725,
1880
+ "step": 2650
1881
+ },
1882
+ {
1883
+ "epoch": 11.86644407345576,
1884
+ "grad_norm": 1.0,
1885
+ "learning_rate": 1.8923529045932292e-06,
1886
+ "loss": 0.4149,
1887
+ "step": 2660
1888
+ },
1889
+ {
1890
+ "epoch": 11.910962715637172,
1891
+ "grad_norm": 1.0625,
1892
+ "learning_rate": 1.8543444465962147e-06,
1893
+ "loss": 0.4436,
1894
+ "step": 2670
1895
+ },
1896
+ {
1897
+ "epoch": 11.955481357818586,
1898
+ "grad_norm": 0.9375,
1899
+ "learning_rate": 1.8166344911448115e-06,
1900
+ "loss": 0.4254,
1901
+ "step": 2680
1902
+ },
1903
+ {
1904
+ "epoch": 12.00222593210907,
1905
+ "grad_norm": 3.515625,
1906
+ "learning_rate": 1.7792266166720368e-06,
1907
+ "loss": 0.5129,
1908
+ "step": 2690
1909
+ },
1910
+ {
1911
+ "epoch": 12.046744574290484,
1912
+ "grad_norm": 1.0625,
1913
+ "learning_rate": 1.742124372945364e-06,
1914
+ "loss": 0.4114,
1915
+ "step": 2700
1916
+ },
1917
+ {
1918
+ "epoch": 12.091263216471898,
1919
+ "grad_norm": 0.98046875,
1920
+ "learning_rate": 1.7053312807298633e-06,
1921
+ "loss": 0.4351,
1922
+ "step": 2710
1923
+ },
1924
+ {
1925
+ "epoch": 12.135781858653312,
1926
+ "grad_norm": 0.890625,
1927
+ "learning_rate": 1.6688508314541086e-06,
1928
+ "loss": 0.404,
1929
+ "step": 2720
1930
+ },
1931
+ {
1932
+ "epoch": 12.180300500834724,
1933
+ "grad_norm": 0.99609375,
1934
+ "learning_rate": 1.6326864868788678e-06,
1935
+ "loss": 0.4349,
1936
+ "step": 2730
1937
+ },
1938
+ {
1939
+ "epoch": 12.224819143016138,
1940
+ "grad_norm": 1.0234375,
1941
+ "learning_rate": 1.5968416787685919e-06,
1942
+ "loss": 0.4581,
1943
+ "step": 2740
1944
+ },
1945
+ {
1946
+ "epoch": 12.269337785197552,
1947
+ "grad_norm": 0.9921875,
1948
+ "learning_rate": 1.5613198085657804e-06,
1949
+ "loss": 0.4589,
1950
+ "step": 2750
1951
+ },
1952
+ {
1953
+ "epoch": 12.313856427378965,
1954
+ "grad_norm": 0.95703125,
1955
+ "learning_rate": 1.5261242470681813e-06,
1956
+ "loss": 0.4357,
1957
+ "step": 2760
1958
+ },
1959
+ {
1960
+ "epoch": 12.358375069560378,
1961
+ "grad_norm": 0.78515625,
1962
+ "learning_rate": 1.4912583341089516e-06,
1963
+ "loss": 0.3949,
1964
+ "step": 2770
1965
+ },
1966
+ {
1967
+ "epoch": 12.402893711741791,
1968
+ "grad_norm": 0.9140625,
1969
+ "learning_rate": 1.4567253782397073e-06,
1970
+ "loss": 0.4184,
1971
+ "step": 2780
1972
+ },
1973
+ {
1974
+ "epoch": 12.447412353923205,
1975
+ "grad_norm": 0.91796875,
1976
+ "learning_rate": 1.4225286564165785e-06,
1977
+ "loss": 0.4309,
1978
+ "step": 2790
1979
+ },
1980
+ {
1981
+ "epoch": 12.49193099610462,
1982
+ "grad_norm": 0.9453125,
1983
+ "learning_rate": 1.3886714136892287e-06,
1984
+ "loss": 0.4539,
1985
+ "step": 2800
1986
+ },
1987
+ {
1988
+ "epoch": 12.536449638286033,
1989
+ "grad_norm": 0.77734375,
1990
+ "learning_rate": 1.3551568628929434e-06,
1991
+ "loss": 0.4243,
1992
+ "step": 2810
1993
+ },
1994
+ {
1995
+ "epoch": 12.580968280467445,
1996
+ "grad_norm": 0.83984375,
1997
+ "learning_rate": 1.321988184343732e-06,
1998
+ "loss": 0.4039,
1999
+ "step": 2820
2000
+ },
2001
+ {
2002
+ "epoch": 12.625486922648859,
2003
+ "grad_norm": 1.0078125,
2004
+ "learning_rate": 1.2891685255365517e-06,
2005
+ "loss": 0.4182,
2006
+ "step": 2830
2007
+ },
2008
+ {
2009
+ "epoch": 12.670005564830273,
2010
+ "grad_norm": 0.96875,
2011
+ "learning_rate": 1.256701000846619e-06,
2012
+ "loss": 0.4146,
2013
+ "step": 2840
2014
+ },
2015
+ {
2016
+ "epoch": 12.714524207011687,
2017
+ "grad_norm": 0.8984375,
2018
+ "learning_rate": 1.22458869123388e-06,
2019
+ "loss": 0.434,
2020
+ "step": 2850
2021
+ },
2022
+ {
2023
+ "epoch": 12.759042849193099,
2024
+ "grad_norm": 0.890625,
2025
+ "learning_rate": 1.1928346439506526e-06,
2026
+ "loss": 0.4356,
2027
+ "step": 2860
2028
+ },
2029
+ {
2030
+ "epoch": 12.803561491374513,
2031
+ "grad_norm": 0.75390625,
2032
+ "learning_rate": 1.1614418722524506e-06,
2033
+ "loss": 0.4073,
2034
+ "step": 2870
2035
+ },
2036
+ {
2037
+ "epoch": 12.848080133555927,
2038
+ "grad_norm": 0.84375,
2039
+ "learning_rate": 1.1304133551120532e-06,
2040
+ "loss": 0.4376,
2041
+ "step": 2880
2042
+ },
2043
+ {
2044
+ "epoch": 12.89259877573734,
2045
+ "grad_norm": 0.72265625,
2046
+ "learning_rate": 1.0997520369368158e-06,
2047
+ "loss": 0.4078,
2048
+ "step": 2890
2049
+ },
2050
+ {
2051
+ "epoch": 12.937117417918753,
2052
+ "grad_norm": 0.87109375,
2053
+ "learning_rate": 1.0694608272892698e-06,
2054
+ "loss": 0.4329,
2055
+ "step": 2900
2056
+ },
2057
+ {
2058
+ "epoch": 12.981636060100167,
2059
+ "grad_norm": 0.9765625,
2060
+ "learning_rate": 1.0395426006110164e-06,
2061
+ "loss": 0.3766,
2062
+ "step": 2910
2063
+ },
2064
+ {
2065
+ "epoch": 13.02838063439065,
2066
+ "grad_norm": 0.8046875,
2067
+ "learning_rate": 1.0100001959499644e-06,
2068
+ "loss": 0.3808,
2069
+ "step": 2920
2070
+ },
2071
+ {
2072
+ "epoch": 13.072899276572064,
2073
+ "grad_norm": 0.64453125,
2074
+ "learning_rate": 9.808364166909256e-07,
2075
+ "loss": 0.4232,
2076
+ "step": 2930
2077
+ },
2078
+ {
2079
+ "epoch": 13.117417918753478,
2080
+ "grad_norm": 0.8046875,
2081
+ "learning_rate": 9.520540302895847e-07,
2082
+ "loss": 0.4332,
2083
+ "step": 2940
2084
+ },
2085
+ {
2086
+ "epoch": 13.161936560934892,
2087
+ "grad_norm": 0.6640625,
2088
+ "learning_rate": 9.236557680098918e-07,
2089
+ "loss": 0.4059,
2090
+ "step": 2950
2091
+ },
2092
+ {
2093
+ "epoch": 13.206455203116304,
2094
+ "grad_norm": 0.83984375,
2095
+ "learning_rate": 8.956443246648771e-07,
2096
+ "loss": 0.3704,
2097
+ "step": 2960
2098
+ },
2099
+ {
2100
+ "epoch": 13.250973845297718,
2101
+ "grad_norm": 0.8046875,
2102
+ "learning_rate": 8.680223583609399e-07,
2103
+ "loss": 0.4327,
2104
+ "step": 2970
2105
+ },
2106
+ {
2107
+ "epoch": 13.295492487479132,
2108
+ "grad_norm": 0.875,
2109
+ "learning_rate": 8.407924902455983e-07,
2110
+ "loss": 0.4229,
2111
+ "step": 2980
2112
+ },
2113
+ {
2114
+ "epoch": 13.340011129660546,
2115
+ "grad_norm": 0.80859375,
2116
+ "learning_rate": 8.139573042587729e-07,
2117
+ "loss": 0.4121,
2118
+ "step": 2990
2119
+ },
2120
+ {
2121
+ "epoch": 13.384529771841958,
2122
+ "grad_norm": 0.70703125,
2123
+ "learning_rate": 7.875193468875719e-07,
2124
+ "loss": 0.423,
2125
+ "step": 3000
2126
+ },
2127
+ {
2128
+ "epoch": 13.384529771841958,
2129
+ "eval_loss": 0.9250730872154236,
2130
+ "eval_runtime": 17.1049,
2131
+ "eval_samples_per_second": 23.385,
2132
+ "eval_steps_per_second": 23.385,
2133
+ "step": 3000
2134
+ },
2135
+ {
2136
+ "epoch": 13.429048414023372,
2137
+ "grad_norm": 0.90234375,
2138
+ "learning_rate": 7.614811269246631e-07,
2139
+ "loss": 0.4316,
2140
+ "step": 3010
2141
+ },
2142
+ {
2143
+ "epoch": 13.473567056204786,
2144
+ "grad_norm": 0.87890625,
2145
+ "learning_rate": 7.35845115230191e-07,
2146
+ "loss": 0.4104,
2147
+ "step": 3020
2148
+ },
2149
+ {
2150
+ "epoch": 13.5180856983862,
2151
+ "grad_norm": 0.76953125,
2152
+ "learning_rate": 7.106137444973177e-07,
2153
+ "loss": 0.4367,
2154
+ "step": 3030
2155
+ },
2156
+ {
2157
+ "epoch": 13.562604340567614,
2158
+ "grad_norm": 0.83984375,
2159
+ "learning_rate": 6.857894090213702e-07,
2160
+ "loss": 0.417,
2161
+ "step": 3040
2162
+ },
2163
+ {
2164
+ "epoch": 13.607122982749026,
2165
+ "grad_norm": 1.4765625,
2166
+ "learning_rate": 6.613744644726383e-07,
2167
+ "loss": 0.394,
2168
+ "step": 3050
2169
+ },
2170
+ {
2171
+ "epoch": 13.65164162493044,
2172
+ "grad_norm": 0.91796875,
2173
+ "learning_rate": 6.3737122767284e-07,
2174
+ "loss": 0.4172,
2175
+ "step": 3060
2176
+ },
2177
+ {
2178
+ "epoch": 13.696160267111853,
2179
+ "grad_norm": 0.86328125,
2180
+ "learning_rate": 6.137819763752656e-07,
2181
+ "loss": 0.4517,
2182
+ "step": 3070
2183
+ },
2184
+ {
2185
+ "epoch": 13.740678909293267,
2186
+ "grad_norm": 1.046875,
2187
+ "learning_rate": 5.90608949048635e-07,
2188
+ "loss": 0.4256,
2189
+ "step": 3080
2190
+ },
2191
+ {
2192
+ "epoch": 13.78519755147468,
2193
+ "grad_norm": 1.21875,
2194
+ "learning_rate": 5.678543446646811e-07,
2195
+ "loss": 0.4019,
2196
+ "step": 3090
2197
+ },
2198
+ {
2199
+ "epoch": 13.829716193656093,
2200
+ "grad_norm": 0.96875,
2201
+ "learning_rate": 5.455203224894857e-07,
2202
+ "loss": 0.453,
2203
+ "step": 3100
2204
+ },
2205
+ {
2206
+ "epoch": 13.874234835837507,
2207
+ "grad_norm": 0.92578125,
2208
+ "learning_rate": 5.236090018785705e-07,
2209
+ "loss": 0.4107,
2210
+ "step": 3110
2211
+ },
2212
+ {
2213
+ "epoch": 13.918753478018921,
2214
+ "grad_norm": 0.8984375,
2215
+ "learning_rate": 5.021224620757914e-07,
2216
+ "loss": 0.4475,
2217
+ "step": 3120
2218
+ },
2219
+ {
2220
+ "epoch": 13.963272120200333,
2221
+ "grad_norm": 0.9296875,
2222
+ "learning_rate": 4.810627420160269e-07,
2223
+ "loss": 0.4322,
2224
+ "step": 3130
2225
+ },
2226
+ {
2227
+ "epoch": 14.010016694490819,
2228
+ "grad_norm": 0.91796875,
2229
+ "learning_rate": 4.604318401317009e-07,
2230
+ "loss": 0.4318,
2231
+ "step": 3140
2232
+ },
2233
+ {
2234
+ "epoch": 14.054535336672231,
2235
+ "grad_norm": 1.3046875,
2236
+ "learning_rate": 4.402317141631407e-07,
2237
+ "loss": 0.4489,
2238
+ "step": 3150
2239
+ },
2240
+ {
2241
+ "epoch": 14.099053978853645,
2242
+ "grad_norm": 1.40625,
2243
+ "learning_rate": 4.2046428097279766e-07,
2244
+ "loss": 0.4381,
2245
+ "step": 3160
2246
+ },
2247
+ {
2248
+ "epoch": 14.143572621035059,
2249
+ "grad_norm": 1.1796875,
2250
+ "learning_rate": 4.011314163633573e-07,
2251
+ "loss": 0.4107,
2252
+ "step": 3170
2253
+ },
2254
+ {
2255
+ "epoch": 14.188091263216473,
2256
+ "grad_norm": 1.3203125,
2257
+ "learning_rate": 3.822349548997295e-07,
2258
+ "loss": 0.4399,
2259
+ "step": 3180
2260
+ },
2261
+ {
2262
+ "epoch": 14.232609905397885,
2263
+ "grad_norm": 1.3984375,
2264
+ "learning_rate": 3.637766897349654e-07,
2265
+ "loss": 0.417,
2266
+ "step": 3190
2267
+ },
2268
+ {
2269
+ "epoch": 14.277128547579299,
2270
+ "grad_norm": 3.5,
2271
+ "learning_rate": 3.4575837244009367e-07,
2272
+ "loss": 0.4449,
2273
+ "step": 3200
2274
+ },
2275
+ {
2276
+ "epoch": 14.321647189760712,
2277
+ "grad_norm": 3.671875,
2278
+ "learning_rate": 3.281817128379139e-07,
2279
+ "loss": 0.3875,
2280
+ "step": 3210
2281
+ },
2282
+ {
2283
+ "epoch": 14.366165831942126,
2284
+ "grad_norm": 4.625,
2285
+ "learning_rate": 3.1104837884073866e-07,
2286
+ "loss": 0.4187,
2287
+ "step": 3220
2288
+ },
2289
+ {
2290
+ "epoch": 14.410684474123538,
2291
+ "grad_norm": 3.875,
2292
+ "learning_rate": 2.943599962921279e-07,
2293
+ "loss": 0.41,
2294
+ "step": 3230
2295
+ },
2296
+ {
2297
+ "epoch": 14.455203116304952,
2298
+ "grad_norm": 3.828125,
2299
+ "learning_rate": 2.7811814881259503e-07,
2300
+ "loss": 0.4016,
2301
+ "step": 3240
2302
+ },
2303
+ {
2304
+ "epoch": 14.499721758486366,
2305
+ "grad_norm": 8.1875,
2306
+ "learning_rate": 2.623243776493434e-07,
2307
+ "loss": 0.3906,
2308
+ "step": 3250
2309
+ },
2310
+ {
2311
+ "epoch": 14.54424040066778,
2312
+ "grad_norm": 8.125,
2313
+ "learning_rate": 2.469801815300027e-07,
2314
+ "loss": 0.4241,
2315
+ "step": 3260
2316
+ },
2317
+ {
2318
+ "epoch": 14.588759042849194,
2319
+ "grad_norm": 9.5625,
2320
+ "learning_rate": 2.3208701652041697e-07,
2321
+ "loss": 0.4104,
2322
+ "step": 3270
2323
+ },
2324
+ {
2325
+ "epoch": 14.633277685030606,
2326
+ "grad_norm": 7.59375,
2327
+ "learning_rate": 2.1764629588646667e-07,
2328
+ "loss": 0.4031,
2329
+ "step": 3280
2330
+ },
2331
+ {
2332
+ "epoch": 14.67779632721202,
2333
+ "grad_norm": 7.125,
2334
+ "learning_rate": 2.036593899599615e-07,
2335
+ "loss": 0.3911,
2336
+ "step": 3290
2337
+ },
2338
+ {
2339
+ "epoch": 14.722314969393434,
2340
+ "grad_norm": 2.546875,
2341
+ "learning_rate": 1.9012762600860656e-07,
2342
+ "loss": 0.4137,
2343
+ "step": 3300
2344
+ },
2345
+ {
2346
+ "epoch": 14.766833611574848,
2347
+ "grad_norm": 2.609375,
2348
+ "learning_rate": 1.7705228811005004e-07,
2349
+ "loss": 0.4559,
2350
+ "step": 3310
2351
+ },
2352
+ {
2353
+ "epoch": 14.81135225375626,
2354
+ "grad_norm": 2.640625,
2355
+ "learning_rate": 1.6443461703003427e-07,
2356
+ "loss": 0.3986,
2357
+ "step": 3320
2358
+ },
2359
+ {
2360
+ "epoch": 14.855870895937674,
2361
+ "grad_norm": 2.484375,
2362
+ "learning_rate": 1.5227581010465341e-07,
2363
+ "loss": 0.4073,
2364
+ "step": 3330
2365
+ },
2366
+ {
2367
+ "epoch": 14.900389538119088,
2368
+ "grad_norm": 2.734375,
2369
+ "learning_rate": 1.4057702112673765e-07,
2370
+ "loss": 0.4137,
2371
+ "step": 3340
2372
+ },
2373
+ {
2374
+ "epoch": 14.944908180300501,
2375
+ "grad_norm": 2.25,
2376
+ "learning_rate": 1.2933936023636073e-07,
2377
+ "loss": 0.4283,
2378
+ "step": 3350
2379
+ },
2380
+ {
2381
+ "epoch": 14.989426822481914,
2382
+ "grad_norm": 2.234375,
2383
+ "learning_rate": 1.185638938154976e-07,
2384
+ "loss": 0.4097,
2385
+ "step": 3360
2386
+ },
2387
+ {
2388
+ "epoch": 15.0361713967724,
2389
+ "grad_norm": 2.203125,
2390
+ "learning_rate": 1.08251644386832e-07,
2391
+ "loss": 0.4326,
2392
+ "step": 3370
2393
+ },
2394
+ {
2395
+ "epoch": 15.080690038953811,
2396
+ "grad_norm": 3.0,
2397
+ "learning_rate": 9.84035905167241e-08,
2398
+ "loss": 0.4338,
2399
+ "step": 3380
2400
+ },
2401
+ {
2402
+ "epoch": 15.125208681135225,
2403
+ "grad_norm": 2.359375,
2404
+ "learning_rate": 8.902066672235144e-08,
2405
+ "loss": 0.4197,
2406
+ "step": 3390
2407
+ },
2408
+ {
2409
+ "epoch": 15.16972732331664,
2410
+ "grad_norm": 2.234375,
2411
+ "learning_rate": 8.010376338302872e-08,
2412
+ "loss": 0.4277,
2413
+ "step": 3400
2414
+ },
2415
+ {
2416
+ "epoch": 15.214245965498053,
2417
+ "grad_norm": 2.25,
2418
+ "learning_rate": 7.165372665571879e-08,
2419
+ "loss": 0.4325,
2420
+ "step": 3410
2421
+ },
2422
+ {
2423
+ "epoch": 15.258764607679465,
2424
+ "grad_norm": 2.171875,
2425
+ "learning_rate": 6.367135839473349e-08,
2426
+ "loss": 0.399,
2427
+ "step": 3420
2428
+ },
2429
+ {
2430
+ "epoch": 15.303283249860879,
2431
+ "grad_norm": 2.578125,
2432
+ "learning_rate": 5.6157416075648954e-08,
2433
+ "loss": 0.4368,
2434
+ "step": 3430
2435
+ },
2436
+ {
2437
+ "epoch": 15.347801892042293,
2438
+ "grad_norm": 2.359375,
2439
+ "learning_rate": 4.911261272341872e-08,
2440
+ "loss": 0.4029,
2441
+ "step": 3440
2442
+ },
2443
+ {
2444
+ "epoch": 15.392320534223707,
2445
+ "grad_norm": 2.296875,
2446
+ "learning_rate": 4.25376168447178e-08,
2447
+ "loss": 0.4269,
2448
+ "step": 3450
2449
+ },
2450
+ {
2451
+ "epoch": 15.436839176405119,
2452
+ "grad_norm": 2.359375,
2453
+ "learning_rate": 3.643305236450345e-08,
2454
+ "loss": 0.4442,
2455
+ "step": 3460
2456
+ },
2457
+ {
2458
+ "epoch": 15.481357818586533,
2459
+ "grad_norm": 2.28125,
2460
+ "learning_rate": 3.079949856680975e-08,
2461
+ "loss": 0.4207,
2462
+ "step": 3470
2463
+ },
2464
+ {
2465
+ "epoch": 15.525876460767947,
2466
+ "grad_norm": 2.671875,
2467
+ "learning_rate": 2.5637490039775447e-08,
2468
+ "loss": 0.4257,
2469
+ "step": 3480
2470
+ },
2471
+ {
2472
+ "epoch": 15.57039510294936,
2473
+ "grad_norm": 2.296875,
2474
+ "learning_rate": 2.0947516624917898e-08,
2475
+ "loss": 0.4161,
2476
+ "step": 3490
2477
+ },
2478
+ {
2479
+ "epoch": 15.614913745130773,
2480
+ "grad_norm": 2.015625,
2481
+ "learning_rate": 1.6730023370645775e-08,
2482
+ "loss": 0.3976,
2483
+ "step": 3500
2484
+ },
2485
+ {
2486
+ "epoch": 15.659432387312187,
2487
+ "grad_norm": 2.140625,
2488
+ "learning_rate": 1.298541049003288e-08,
2489
+ "loss": 0.4074,
2490
+ "step": 3510
2491
+ },
2492
+ {
2493
+ "epoch": 15.7039510294936,
2494
+ "grad_norm": 2.421875,
2495
+ "learning_rate": 9.714033322833494e-09,
2496
+ "loss": 0.4155,
2497
+ "step": 3520
2498
+ },
2499
+ {
2500
+ "epoch": 15.748469671675014,
2501
+ "grad_norm": 2.203125,
2502
+ "learning_rate": 6.9162023017699255e-09,
2503
+ "loss": 0.3747,
2504
+ "step": 3530
2505
+ },
2506
+ {
2507
+ "epoch": 15.792988313856428,
2508
+ "grad_norm": 2.09375,
2509
+ "learning_rate": 4.592182923068289e-09,
2510
+ "loss": 0.3766,
2511
+ "step": 3540
2512
+ },
2513
+ {
2514
+ "epoch": 15.83750695603784,
2515
+ "grad_norm": 2.125,
2516
+ "learning_rate": 2.7421957212697692e-09,
2517
+ "loss": 0.4017,
2518
+ "step": 3550
2519
+ },
2520
+ {
2521
+ "epoch": 15.882025598219254,
2522
+ "grad_norm": 1.90625,
2523
+ "learning_rate": 1.3664162482990296e-09,
2524
+ "loss": 0.42,
2525
+ "step": 3560
2526
+ },
2527
+ {
2528
+ "epoch": 15.926544240400668,
2529
+ "grad_norm": 1.7421875,
2530
+ "learning_rate": 4.649750568080924e-10,
2531
+ "loss": 0.44,
2532
+ "step": 3570
2533
+ },
2534
+ {
2535
+ "epoch": 15.971062882582082,
2536
+ "grad_norm": 2.421875,
2537
+ "learning_rate": 3.795768778680487e-11,
2538
+ "loss": 0.4156,
2539
+ "step": 3580
2540
+ },
2541
+ {
2542
+ "epoch": 15.988870339454646,
2543
+ "step": 3584,
2544
+ "total_flos": 8.551781210951516e+17,
2545
+ "train_loss": 0.7042842949075359,
2546
+ "train_runtime": 4850.1152,
2547
+ "train_samples_per_second": 11.853,
2548
+ "train_steps_per_second": 0.739
2549
+ }
2550
+ ],
2551
+ "logging_steps": 10,
2552
+ "max_steps": 3584,
2553
+ "num_input_tokens_seen": 0,
2554
+ "num_train_epochs": 16,
2555
+ "save_steps": 0,
2556
+ "stateful_callbacks": {
2557
+ "TrainerControl": {
2558
+ "args": {
2559
+ "should_epoch_stop": false,
2560
+ "should_evaluate": false,
2561
+ "should_log": false,
2562
+ "should_save": true,
2563
+ "should_training_stop": true
2564
+ },
2565
+ "attributes": {}
2566
+ }
2567
+ },
2568
+ "total_flos": 8.551781210951516e+17,
2569
+ "train_batch_size": 2,
2570
+ "trial_name": null,
2571
+ "trial_params": null
2572
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fd2de371e141510ceb19776c56d7210af443832774f314bb1ed860053df1dca
3
+ size 5432
training_eval_loss.png ADDED
training_loss.png ADDED