dlibf commited on
Commit
5349189
1 Parent(s): 1d24ca0

Model save

Browse files
README.md ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - trl
4
+ - dpo
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: zephyr-6b-dpo-full
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # zephyr-6b-dpo-full
15
+
16
+ This model was trained from scratch on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 0.5676
19
+ - Rewards/chosen: -0.5685
20
+ - Rewards/rejected: -1.1091
21
+ - Rewards/accuracies: 0.7305
22
+ - Rewards/margins: 0.5407
23
+ - Logps/rejected: -384.2899
24
+ - Logps/chosen: -336.4684
25
+ - Logits/rejected: -0.9166
26
+ - Logits/chosen: -0.9852
27
+
28
+ ## Model description
29
+
30
+ More information needed
31
+
32
+ ## Intended uses & limitations
33
+
34
+ More information needed
35
+
36
+ ## Training and evaluation data
37
+
38
+ More information needed
39
+
40
+ ## Training procedure
41
+
42
+ ### Training hyperparameters
43
+
44
+ The following hyperparameters were used during training:
45
+ - learning_rate: 5e-07
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 8
48
+ - seed: 42
49
+ - distributed_type: multi-GPU
50
+ - num_devices: 8
51
+ - gradient_accumulation_steps: 2
52
+ - total_train_batch_size: 128
53
+ - total_eval_batch_size: 64
54
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
55
+ - lr_scheduler_type: cosine
56
+ - lr_scheduler_warmup_ratio: 0.1
57
+ - num_epochs: 1
58
+
59
+ ### Training results
60
+
61
+ | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
62
+ |:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
63
+ | 0.6548 | 0.21 | 100 | 0.6548 | -0.1060 | -0.2092 | 0.6680 | 0.1032 | -294.2936 | -290.2218 | -0.6577 | -0.7018 |
64
+ | 0.5881 | 0.42 | 200 | 0.5968 | -0.3050 | -0.6575 | 0.6875 | 0.3525 | -339.1259 | -310.1252 | -0.7415 | -0.8023 |
65
+ | 0.5753 | 0.63 | 300 | 0.5734 | -0.4917 | -0.9768 | 0.7227 | 0.4851 | -371.0564 | -328.7914 | -0.7579 | -0.8263 |
66
+ | 0.5602 | 0.84 | 400 | 0.5689 | -0.4964 | -1.0157 | 0.7344 | 0.5193 | -374.9490 | -329.2605 | -0.8579 | -0.9263 |
67
+
68
+
69
+ ### Framework versions
70
+
71
+ - Transformers 4.36.2
72
+ - Pytorch 2.1.2+cu121
73
+ - Datasets 2.14.6
74
+ - Tokenizers 0.15.1
all_results.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -0.9851527214050293,
4
+ "eval_logits/rejected": -0.9165840148925781,
5
+ "eval_logps/chosen": -336.4683837890625,
6
+ "eval_logps/rejected": -384.2898864746094,
7
+ "eval_loss": 0.5675918459892273,
8
+ "eval_rewards/accuracies": 0.73046875,
9
+ "eval_rewards/chosen": -0.5684676766395569,
10
+ "eval_rewards/margins": 0.5406599044799805,
11
+ "eval_rewards/rejected": -1.1091275215148926,
12
+ "eval_runtime": 143.0981,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 13.976,
15
+ "eval_steps_per_second": 0.224,
16
+ "train_loss": 0.6029723678173879,
17
+ "train_runtime": 7448.3301,
18
+ "train_samples": 61135,
19
+ "train_samples_per_second": 8.208,
20
+ "train_steps_per_second": 0.064
21
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/workspace/donghao/alignment-handbook/data/zephyr-6b-sft-full",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 4096,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 11008,
14
+ "max_position_embeddings": 200000,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 32,
17
+ "num_hidden_layers": 32,
18
+ "num_key_value_heads": 4,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 5000000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.36.2",
27
+ "use_cache": false,
28
+ "vocab_size": 64000
29
+ }
eval_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "eval_logits/chosen": -0.9851527214050293,
4
+ "eval_logits/rejected": -0.9165840148925781,
5
+ "eval_logps/chosen": -336.4683837890625,
6
+ "eval_logps/rejected": -384.2898864746094,
7
+ "eval_loss": 0.5675918459892273,
8
+ "eval_rewards/accuracies": 0.73046875,
9
+ "eval_rewards/chosen": -0.5684676766395569,
10
+ "eval_rewards/margins": 0.5406599044799805,
11
+ "eval_rewards/rejected": -1.1091275215148926,
12
+ "eval_runtime": 143.0981,
13
+ "eval_samples": 2000,
14
+ "eval_samples_per_second": 13.976,
15
+ "eval_steps_per_second": 0.224
16
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.36.2"
7
+ }
model-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d89f1789a60d2420071e2c058b7121d632c62da433bed83e1eb554c7e5ea4ee4
3
+ size 4932711424
model-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b582f6878eddfc6378c6b915acc45534cd37f968879710f517be8c7ac4dada8
3
+ size 4976802816
model-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c7debb85969e479bb9fd661ee2d74514d86322f80518b7ee6e3c559f3c1a166
3
+ size 2212590568
model.safetensors.index.json ADDED
@@ -0,0 +1,298 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12122071040
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00003-of-00003.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
242
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
243
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
244
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
245
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
246
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
247
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
248
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
249
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
250
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
251
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
252
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
253
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
254
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
255
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
256
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
257
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
258
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
259
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
260
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
261
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
262
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
263
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
264
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
265
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
266
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
267
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
268
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
269
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
270
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
271
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
272
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
273
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
274
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
275
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
276
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
277
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
278
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
279
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
280
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
281
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
282
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
283
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
284
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
285
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
286
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
287
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
288
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
289
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
290
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
291
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
292
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
293
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
294
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
295
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
296
+ "model.norm.weight": "model-00003-of-00003.safetensors"
297
+ }
298
+ }
runs/Feb05_13-07-36_dsw-691-5496b4c68c-rxngp/events.out.tfevents.1707138888.dsw-691-5496b4c68c-rxngp.3332070.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddc5d95b1260a914bef955fc00cffbf084a017d794324c7126044ecd39d0634b
3
+ size 38210
runs/Feb05_13-07-36_dsw-691-5496b4c68c-rxngp/events.out.tfevents.1707146480.dsw-691-5496b4c68c-rxngp.3332070.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69f77380888817195000524a14686bb513a4cd1e7bae517ff61ae6a1f8d5636e
3
+ size 828
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
3
+ size 1033105
tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<|startoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<|startoftext|>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "<|endoftext|>",
34
+ "legacy": true,
35
+ "model_max_length": 2048,
36
+ "pad_token": "<unk>",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 0.6029723678173879,
4
+ "train_runtime": 7448.3301,
5
+ "train_samples": 61135,
6
+ "train_samples_per_second": 8.208,
7
+ "train_steps_per_second": 0.064
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,766 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 100,
6
+ "global_step": 478,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 1.0416666666666666e-08,
14
+ "logits/chosen": -0.3017902672290802,
15
+ "logits/rejected": -0.4429064989089966,
16
+ "logps/chosen": -319.77001953125,
17
+ "logps/rejected": -256.397705078125,
18
+ "loss": 0.6931,
19
+ "rewards/accuracies": 0.0,
20
+ "rewards/chosen": 0.0,
21
+ "rewards/margins": 0.0,
22
+ "rewards/rejected": 0.0,
23
+ "step": 1
24
+ },
25
+ {
26
+ "epoch": 0.02,
27
+ "learning_rate": 1.0416666666666667e-07,
28
+ "logits/chosen": -0.6185635924339294,
29
+ "logits/rejected": -0.6267194747924805,
30
+ "logps/chosen": -266.4049072265625,
31
+ "logps/rejected": -226.4547576904297,
32
+ "loss": 0.6938,
33
+ "rewards/accuracies": 0.5347222089767456,
34
+ "rewards/chosen": -0.0314086489379406,
35
+ "rewards/margins": 0.004176241811364889,
36
+ "rewards/rejected": -0.035584889352321625,
37
+ "step": 10
38
+ },
39
+ {
40
+ "epoch": 0.04,
41
+ "learning_rate": 2.0833333333333333e-07,
42
+ "logits/chosen": -0.5040268301963806,
43
+ "logits/rejected": -0.5066824555397034,
44
+ "logps/chosen": -294.06231689453125,
45
+ "logps/rejected": -256.36572265625,
46
+ "loss": 0.6919,
47
+ "rewards/accuracies": 0.512499988079071,
48
+ "rewards/chosen": 0.0255455132573843,
49
+ "rewards/margins": 0.0022588702850043774,
50
+ "rewards/rejected": 0.023286638781428337,
51
+ "step": 20
52
+ },
53
+ {
54
+ "epoch": 0.06,
55
+ "learning_rate": 3.1249999999999997e-07,
56
+ "logits/chosen": -0.47493982315063477,
57
+ "logits/rejected": -0.4304034113883972,
58
+ "logps/chosen": -294.8653869628906,
59
+ "logps/rejected": -278.9495544433594,
60
+ "loss": 0.6909,
61
+ "rewards/accuracies": 0.543749988079071,
62
+ "rewards/chosen": 0.011051720939576626,
63
+ "rewards/margins": 0.003937236033380032,
64
+ "rewards/rejected": 0.007114484906196594,
65
+ "step": 30
66
+ },
67
+ {
68
+ "epoch": 0.08,
69
+ "learning_rate": 4.1666666666666667e-07,
70
+ "logits/chosen": -0.6350118517875671,
71
+ "logits/rejected": -0.6409525871276855,
72
+ "logps/chosen": -302.514404296875,
73
+ "logps/rejected": -264.9754943847656,
74
+ "loss": 0.6886,
75
+ "rewards/accuracies": 0.5562499761581421,
76
+ "rewards/chosen": -0.00148511934094131,
77
+ "rewards/margins": 0.005857478827238083,
78
+ "rewards/rejected": -0.007342599332332611,
79
+ "step": 40
80
+ },
81
+ {
82
+ "epoch": 0.1,
83
+ "learning_rate": 4.999733114418725e-07,
84
+ "logits/chosen": -0.6464229226112366,
85
+ "logits/rejected": -0.6577852964401245,
86
+ "logps/chosen": -318.97540283203125,
87
+ "logps/rejected": -295.6136169433594,
88
+ "loss": 0.6858,
89
+ "rewards/accuracies": 0.625,
90
+ "rewards/chosen": 0.002440870273858309,
91
+ "rewards/margins": 0.01247528288513422,
92
+ "rewards/rejected": -0.010034412145614624,
93
+ "step": 50
94
+ },
95
+ {
96
+ "epoch": 0.13,
97
+ "learning_rate": 4.990398100856366e-07,
98
+ "logits/chosen": -0.7159032821655273,
99
+ "logits/rejected": -0.6997270584106445,
100
+ "logps/chosen": -257.1394958496094,
101
+ "logps/rejected": -223.77249145507812,
102
+ "loss": 0.6834,
103
+ "rewards/accuracies": 0.6187499761581421,
104
+ "rewards/chosen": 0.008302798494696617,
105
+ "rewards/margins": 0.01499713771045208,
106
+ "rewards/rejected": -0.006694340147078037,
107
+ "step": 60
108
+ },
109
+ {
110
+ "epoch": 0.15,
111
+ "learning_rate": 4.967775735898179e-07,
112
+ "logits/chosen": -0.6443796157836914,
113
+ "logits/rejected": -0.6453703045845032,
114
+ "logps/chosen": -287.23919677734375,
115
+ "logps/rejected": -253.98779296875,
116
+ "loss": 0.6809,
117
+ "rewards/accuracies": 0.612500011920929,
118
+ "rewards/chosen": 0.012265635654330254,
119
+ "rewards/margins": 0.02614836022257805,
120
+ "rewards/rejected": -0.013882724568247795,
121
+ "step": 70
122
+ },
123
+ {
124
+ "epoch": 0.17,
125
+ "learning_rate": 4.931986719649298e-07,
126
+ "logits/chosen": -0.6774781346321106,
127
+ "logits/rejected": -0.6471685171127319,
128
+ "logps/chosen": -281.8182067871094,
129
+ "logps/rejected": -281.8425598144531,
130
+ "loss": 0.6743,
131
+ "rewards/accuracies": 0.6937500238418579,
132
+ "rewards/chosen": -0.0038391489069908857,
133
+ "rewards/margins": 0.02816380001604557,
134
+ "rewards/rejected": -0.032002948224544525,
135
+ "step": 80
136
+ },
137
+ {
138
+ "epoch": 0.19,
139
+ "learning_rate": 4.883222001996351e-07,
140
+ "logits/chosen": -0.7065152525901794,
141
+ "logits/rejected": -0.692989706993103,
142
+ "logps/chosen": -276.53753662109375,
143
+ "logps/rejected": -264.0567932128906,
144
+ "loss": 0.6657,
145
+ "rewards/accuracies": 0.6499999761581421,
146
+ "rewards/chosen": -0.04013616591691971,
147
+ "rewards/margins": 0.060574889183044434,
148
+ "rewards/rejected": -0.10071107000112534,
149
+ "step": 90
150
+ },
151
+ {
152
+ "epoch": 0.21,
153
+ "learning_rate": 4.821741763807186e-07,
154
+ "logits/chosen": -0.6360586881637573,
155
+ "logits/rejected": -0.6389707326889038,
156
+ "logps/chosen": -301.81329345703125,
157
+ "logps/rejected": -287.9957580566406,
158
+ "loss": 0.6548,
159
+ "rewards/accuracies": 0.668749988079071,
160
+ "rewards/chosen": -0.07365767657756805,
161
+ "rewards/margins": 0.08726193010807037,
162
+ "rewards/rejected": -0.16091960668563843,
163
+ "step": 100
164
+ },
165
+ {
166
+ "epoch": 0.21,
167
+ "eval_logits/chosen": -0.7018380165100098,
168
+ "eval_logits/rejected": -0.6576583981513977,
169
+ "eval_logps/chosen": -290.2217712402344,
170
+ "eval_logps/rejected": -294.29364013671875,
171
+ "eval_loss": 0.6548193693161011,
172
+ "eval_rewards/accuracies": 0.66796875,
173
+ "eval_rewards/chosen": -0.1060016080737114,
174
+ "eval_rewards/margins": 0.10316330194473267,
175
+ "eval_rewards/rejected": -0.20916491746902466,
176
+ "eval_runtime": 117.0477,
177
+ "eval_samples_per_second": 17.087,
178
+ "eval_steps_per_second": 0.273,
179
+ "step": 100
180
+ },
181
+ {
182
+ "epoch": 0.23,
183
+ "learning_rate": 4.747874028753375e-07,
184
+ "logits/chosen": -0.6454014778137207,
185
+ "logits/rejected": -0.5620900988578796,
186
+ "logps/chosen": -347.7331237792969,
187
+ "logps/rejected": -300.71112060546875,
188
+ "loss": 0.651,
189
+ "rewards/accuracies": 0.6875,
190
+ "rewards/chosen": -0.11785294860601425,
191
+ "rewards/margins": 0.12140049040317535,
192
+ "rewards/rejected": -0.23925340175628662,
193
+ "step": 110
194
+ },
195
+ {
196
+ "epoch": 0.25,
197
+ "learning_rate": 4.662012913161997e-07,
198
+ "logits/chosen": -0.70166015625,
199
+ "logits/rejected": -0.727249801158905,
200
+ "logps/chosen": -303.4729919433594,
201
+ "logps/rejected": -263.29583740234375,
202
+ "loss": 0.6384,
203
+ "rewards/accuracies": 0.706250011920929,
204
+ "rewards/chosen": -0.18253406882286072,
205
+ "rewards/margins": 0.14989741146564484,
206
+ "rewards/rejected": -0.33243149518966675,
207
+ "step": 120
208
+ },
209
+ {
210
+ "epoch": 0.27,
211
+ "learning_rate": 4.5646165232345103e-07,
212
+ "logits/chosen": -0.6562562584877014,
213
+ "logits/rejected": -0.5979722142219543,
214
+ "logps/chosen": -306.23516845703125,
215
+ "logps/rejected": -346.08197021484375,
216
+ "loss": 0.6379,
217
+ "rewards/accuracies": 0.699999988079071,
218
+ "rewards/chosen": -0.28600436449050903,
219
+ "rewards/margins": 0.16408249735832214,
220
+ "rewards/rejected": -0.45008689165115356,
221
+ "step": 130
222
+ },
223
+ {
224
+ "epoch": 0.29,
225
+ "learning_rate": 4.456204510851956e-07,
226
+ "logits/chosen": -0.5730563402175903,
227
+ "logits/rejected": -0.5727633237838745,
228
+ "logps/chosen": -335.1769714355469,
229
+ "logps/rejected": -309.3208312988281,
230
+ "loss": 0.6268,
231
+ "rewards/accuracies": 0.768750011920929,
232
+ "rewards/chosen": -0.16110344231128693,
233
+ "rewards/margins": 0.21982815861701965,
234
+ "rewards/rejected": -0.38093167543411255,
235
+ "step": 140
236
+ },
237
+ {
238
+ "epoch": 0.31,
239
+ "learning_rate": 4.337355301007335e-07,
240
+ "logits/chosen": -0.6809996366500854,
241
+ "logits/rejected": -0.6591669321060181,
242
+ "logps/chosen": -328.6540832519531,
243
+ "logps/rejected": -292.2736511230469,
244
+ "loss": 0.6047,
245
+ "rewards/accuracies": 0.668749988079071,
246
+ "rewards/chosen": -0.33402004837989807,
247
+ "rewards/margins": 0.2206876277923584,
248
+ "rewards/rejected": -0.5547076463699341,
249
+ "step": 150
250
+ },
251
+ {
252
+ "epoch": 0.33,
253
+ "learning_rate": 4.2087030056579986e-07,
254
+ "logits/chosen": -0.6660237312316895,
255
+ "logits/rejected": -0.6344098448753357,
256
+ "logps/chosen": -324.8284912109375,
257
+ "logps/rejected": -335.0122985839844,
258
+ "loss": 0.6017,
259
+ "rewards/accuracies": 0.699999988079071,
260
+ "rewards/chosen": -0.30958321690559387,
261
+ "rewards/margins": 0.312285840511322,
262
+ "rewards/rejected": -0.6218689680099487,
263
+ "step": 160
264
+ },
265
+ {
266
+ "epoch": 0.36,
267
+ "learning_rate": 4.070934040463998e-07,
268
+ "logits/chosen": -0.6780328154563904,
269
+ "logits/rejected": -0.6576133370399475,
270
+ "logps/chosen": -300.7780456542969,
271
+ "logps/rejected": -299.3976745605469,
272
+ "loss": 0.6237,
273
+ "rewards/accuracies": 0.6625000238418579,
274
+ "rewards/chosen": -0.4301220774650574,
275
+ "rewards/margins": 0.2145705670118332,
276
+ "rewards/rejected": -0.6446926593780518,
277
+ "step": 170
278
+ },
279
+ {
280
+ "epoch": 0.38,
281
+ "learning_rate": 3.9247834624635404e-07,
282
+ "logits/chosen": -0.6824392080307007,
283
+ "logits/rejected": -0.6258381009101868,
284
+ "logps/chosen": -354.97503662109375,
285
+ "logps/rejected": -370.0382385253906,
286
+ "loss": 0.599,
287
+ "rewards/accuracies": 0.706250011920929,
288
+ "rewards/chosen": -0.4686453938484192,
289
+ "rewards/margins": 0.343492329120636,
290
+ "rewards/rejected": -0.8121377825737,
291
+ "step": 180
292
+ },
293
+ {
294
+ "epoch": 0.4,
295
+ "learning_rate": 3.7710310482256523e-07,
296
+ "logits/chosen": -0.6199353933334351,
297
+ "logits/rejected": -0.6015241146087646,
298
+ "logps/chosen": -320.41021728515625,
299
+ "logps/rejected": -331.60284423828125,
300
+ "loss": 0.5902,
301
+ "rewards/accuracies": 0.6875,
302
+ "rewards/chosen": -0.27603933215141296,
303
+ "rewards/margins": 0.31284210085868835,
304
+ "rewards/rejected": -0.5888813734054565,
305
+ "step": 190
306
+ },
307
+ {
308
+ "epoch": 0.42,
309
+ "learning_rate": 3.610497133404795e-07,
310
+ "logits/chosen": -0.7054450511932373,
311
+ "logits/rejected": -0.6953166723251343,
312
+ "logps/chosen": -338.31829833984375,
313
+ "logps/rejected": -323.37115478515625,
314
+ "loss": 0.5881,
315
+ "rewards/accuracies": 0.612500011920929,
316
+ "rewards/chosen": -0.5281119346618652,
317
+ "rewards/margins": 0.2860097885131836,
318
+ "rewards/rejected": -0.8141217231750488,
319
+ "step": 200
320
+ },
321
+ {
322
+ "epoch": 0.42,
323
+ "eval_logits/chosen": -0.8023231625556946,
324
+ "eval_logits/rejected": -0.7415486574172974,
325
+ "eval_logps/chosen": -310.1252136230469,
326
+ "eval_logps/rejected": -339.1258850097656,
327
+ "eval_loss": 0.5968395471572876,
328
+ "eval_rewards/accuracies": 0.6875,
329
+ "eval_rewards/chosen": -0.3050362467765808,
330
+ "eval_rewards/margins": 0.3524515628814697,
331
+ "eval_rewards/rejected": -0.657487690448761,
332
+ "eval_runtime": 121.2666,
333
+ "eval_samples_per_second": 16.493,
334
+ "eval_steps_per_second": 0.264,
335
+ "step": 200
336
+ },
337
+ {
338
+ "epoch": 0.44,
339
+ "learning_rate": 3.4440382358952115e-07,
340
+ "logits/chosen": -0.7312219738960266,
341
+ "logits/rejected": -0.730713427066803,
342
+ "logps/chosen": -314.7323303222656,
343
+ "logps/rejected": -301.01312255859375,
344
+ "loss": 0.5938,
345
+ "rewards/accuracies": 0.637499988079071,
346
+ "rewards/chosen": -0.23817189037799835,
347
+ "rewards/margins": 0.30586400628089905,
348
+ "rewards/rejected": -0.5440359115600586,
349
+ "step": 210
350
+ },
351
+ {
352
+ "epoch": 0.46,
353
+ "learning_rate": 3.272542485937368e-07,
354
+ "logits/chosen": -0.7227334380149841,
355
+ "logits/rejected": -0.6831812858581543,
356
+ "logps/chosen": -315.691162109375,
357
+ "logps/rejected": -317.9109802246094,
358
+ "loss": 0.5961,
359
+ "rewards/accuracies": 0.706250011920929,
360
+ "rewards/chosen": -0.27428802847862244,
361
+ "rewards/margins": 0.35738009214401245,
362
+ "rewards/rejected": -0.6316681504249573,
363
+ "step": 220
364
+ },
365
+ {
366
+ "epoch": 0.48,
367
+ "learning_rate": 3.096924887558854e-07,
368
+ "logits/chosen": -0.6957461833953857,
369
+ "logits/rejected": -0.6545354723930359,
370
+ "logps/chosen": -313.1252746582031,
371
+ "logps/rejected": -355.5252685546875,
372
+ "loss": 0.5924,
373
+ "rewards/accuracies": 0.699999988079071,
374
+ "rewards/chosen": -0.4048747420310974,
375
+ "rewards/margins": 0.39421346783638,
376
+ "rewards/rejected": -0.7990882992744446,
377
+ "step": 230
378
+ },
379
+ {
380
+ "epoch": 0.5,
381
+ "learning_rate": 2.9181224366319943e-07,
382
+ "logits/chosen": -0.8229473829269409,
383
+ "logits/rejected": -0.8242266774177551,
384
+ "logps/chosen": -316.42327880859375,
385
+ "logps/rejected": -329.6378173828125,
386
+ "loss": 0.5973,
387
+ "rewards/accuracies": 0.6312500238418579,
388
+ "rewards/chosen": -0.5616710186004639,
389
+ "rewards/margins": 0.3975863456726074,
390
+ "rewards/rejected": -0.9592572450637817,
391
+ "step": 240
392
+ },
393
+ {
394
+ "epoch": 0.52,
395
+ "learning_rate": 2.7370891215954565e-07,
396
+ "logits/chosen": -0.7482638955116272,
397
+ "logits/rejected": -0.7271997332572937,
398
+ "logps/chosen": -325.5633850097656,
399
+ "logps/rejected": -347.3030700683594,
400
+ "loss": 0.5769,
401
+ "rewards/accuracies": 0.675000011920929,
402
+ "rewards/chosen": -0.5051977038383484,
403
+ "rewards/margins": 0.35222890973091125,
404
+ "rewards/rejected": -0.857426643371582,
405
+ "step": 250
406
+ },
407
+ {
408
+ "epoch": 0.54,
409
+ "learning_rate": 2.55479083351317e-07,
410
+ "logits/chosen": -0.8334507942199707,
411
+ "logits/rejected": -0.8130620718002319,
412
+ "logps/chosen": -333.03924560546875,
413
+ "logps/rejected": -325.97979736328125,
414
+ "loss": 0.5666,
415
+ "rewards/accuracies": 0.7250000238418579,
416
+ "rewards/chosen": -0.482491672039032,
417
+ "rewards/margins": 0.45697951316833496,
418
+ "rewards/rejected": -0.9394710659980774,
419
+ "step": 260
420
+ },
421
+ {
422
+ "epoch": 0.56,
423
+ "learning_rate": 2.3722002126275822e-07,
424
+ "logits/chosen": -0.8548744320869446,
425
+ "logits/rejected": -0.839653491973877,
426
+ "logps/chosen": -324.4539794921875,
427
+ "logps/rejected": -357.67169189453125,
428
+ "loss": 0.5678,
429
+ "rewards/accuracies": 0.75,
430
+ "rewards/chosen": -0.45763128995895386,
431
+ "rewards/margins": 0.48610082268714905,
432
+ "rewards/rejected": -0.9437320828437805,
433
+ "step": 270
434
+ },
435
+ {
436
+ "epoch": 0.59,
437
+ "learning_rate": 2.19029145890313e-07,
438
+ "logits/chosen": -0.814782440662384,
439
+ "logits/rejected": -0.7766333222389221,
440
+ "logps/chosen": -330.60662841796875,
441
+ "logps/rejected": -326.7635192871094,
442
+ "loss": 0.5829,
443
+ "rewards/accuracies": 0.699999988079071,
444
+ "rewards/chosen": -0.46811041235923767,
445
+ "rewards/margins": 0.3988150358200073,
446
+ "rewards/rejected": -0.8669255375862122,
447
+ "step": 280
448
+ },
449
+ {
450
+ "epoch": 0.61,
451
+ "learning_rate": 2.0100351342479216e-07,
452
+ "logits/chosen": -0.714547336101532,
453
+ "logits/rejected": -0.656903862953186,
454
+ "logps/chosen": -347.14349365234375,
455
+ "logps/rejected": -363.637451171875,
456
+ "loss": 0.5845,
457
+ "rewards/accuracies": 0.6875,
458
+ "rewards/chosen": -0.4874221384525299,
459
+ "rewards/margins": 0.36368709802627563,
460
+ "rewards/rejected": -0.8511092066764832,
461
+ "step": 290
462
+ },
463
+ {
464
+ "epoch": 0.63,
465
+ "learning_rate": 1.8323929841460178e-07,
466
+ "logits/chosen": -0.7814041376113892,
467
+ "logits/rejected": -0.7600786089897156,
468
+ "logps/chosen": -350.5426025390625,
469
+ "logps/rejected": -373.58282470703125,
470
+ "loss": 0.5753,
471
+ "rewards/accuracies": 0.6625000238418579,
472
+ "rewards/chosen": -0.4952825903892517,
473
+ "rewards/margins": 0.3200310170650482,
474
+ "rewards/rejected": -0.8153136372566223,
475
+ "step": 300
476
+ },
477
+ {
478
+ "epoch": 0.63,
479
+ "eval_logits/chosen": -0.8262501955032349,
480
+ "eval_logits/rejected": -0.7578529119491577,
481
+ "eval_logps/chosen": -328.7913513183594,
482
+ "eval_logps/rejected": -371.0563659667969,
483
+ "eval_loss": 0.5733634233474731,
484
+ "eval_rewards/accuracies": 0.72265625,
485
+ "eval_rewards/chosen": -0.4916972815990448,
486
+ "eval_rewards/margins": 0.48509520292282104,
487
+ "eval_rewards/rejected": -0.9767925143241882,
488
+ "eval_runtime": 130.1337,
489
+ "eval_samples_per_second": 15.369,
490
+ "eval_steps_per_second": 0.246,
491
+ "step": 300
492
+ },
493
+ {
494
+ "epoch": 0.65,
495
+ "learning_rate": 1.6583128063291573e-07,
496
+ "logits/chosen": -0.8206486701965332,
497
+ "logits/rejected": -0.8467684984207153,
498
+ "logps/chosen": -335.5056457519531,
499
+ "logps/rejected": -316.3816833496094,
500
+ "loss": 0.5633,
501
+ "rewards/accuracies": 0.71875,
502
+ "rewards/chosen": -0.5007157325744629,
503
+ "rewards/margins": 0.4249514937400818,
504
+ "rewards/rejected": -0.9256671667098999,
505
+ "step": 310
506
+ },
507
+ {
508
+ "epoch": 0.67,
509
+ "learning_rate": 1.488723393865766e-07,
510
+ "logits/chosen": -0.9328675270080566,
511
+ "logits/rejected": -0.8487465977668762,
512
+ "logps/chosen": -306.1993103027344,
513
+ "logps/rejected": -342.8832092285156,
514
+ "loss": 0.5693,
515
+ "rewards/accuracies": 0.7562500238418579,
516
+ "rewards/chosen": -0.5110325813293457,
517
+ "rewards/margins": 0.5352452993392944,
518
+ "rewards/rejected": -1.0462777614593506,
519
+ "step": 320
520
+ },
521
+ {
522
+ "epoch": 0.69,
523
+ "learning_rate": 1.3245295796480788e-07,
524
+ "logits/chosen": -0.6851174831390381,
525
+ "logits/rejected": -0.6687122583389282,
526
+ "logps/chosen": -352.14984130859375,
527
+ "logps/rejected": -357.9172668457031,
528
+ "loss": 0.57,
529
+ "rewards/accuracies": 0.7437499761581421,
530
+ "rewards/chosen": -0.570861279964447,
531
+ "rewards/margins": 0.4501311779022217,
532
+ "rewards/rejected": -1.0209925174713135,
533
+ "step": 330
534
+ },
535
+ {
536
+ "epoch": 0.71,
537
+ "learning_rate": 1.1666074087171627e-07,
538
+ "logits/chosen": -0.7861064672470093,
539
+ "logits/rejected": -0.7692282795906067,
540
+ "logps/chosen": -313.29083251953125,
541
+ "logps/rejected": -344.58062744140625,
542
+ "loss": 0.5673,
543
+ "rewards/accuracies": 0.706250011920929,
544
+ "rewards/chosen": -0.48139747977256775,
545
+ "rewards/margins": 0.413718044757843,
546
+ "rewards/rejected": -0.8951154947280884,
547
+ "step": 340
548
+ },
549
+ {
550
+ "epoch": 0.73,
551
+ "learning_rate": 1.0157994641835734e-07,
552
+ "logits/chosen": -0.8523145914077759,
553
+ "logits/rejected": -0.8958388566970825,
554
+ "logps/chosen": -305.7944641113281,
555
+ "logps/rejected": -335.16778564453125,
556
+ "loss": 0.5533,
557
+ "rewards/accuracies": 0.731249988079071,
558
+ "rewards/chosen": -0.4743496775627136,
559
+ "rewards/margins": 0.49316510558128357,
560
+ "rewards/rejected": -0.9675148129463196,
561
+ "step": 350
562
+ },
563
+ {
564
+ "epoch": 0.75,
565
+ "learning_rate": 8.729103716819111e-08,
566
+ "logits/chosen": -0.7652881741523743,
567
+ "logits/rejected": -0.8117391467094421,
568
+ "logps/chosen": -384.6844177246094,
569
+ "logps/rejected": -361.26385498046875,
570
+ "loss": 0.5719,
571
+ "rewards/accuracies": 0.699999988079071,
572
+ "rewards/chosen": -0.47557467222213745,
573
+ "rewards/margins": 0.4706428647041321,
574
+ "rewards/rejected": -0.9462175369262695,
575
+ "step": 360
576
+ },
577
+ {
578
+ "epoch": 0.77,
579
+ "learning_rate": 7.387025063449081e-08,
580
+ "logits/chosen": -0.8511560559272766,
581
+ "logits/rejected": -0.8533377647399902,
582
+ "logps/chosen": -373.3354187011719,
583
+ "logps/rejected": -363.8319396972656,
584
+ "loss": 0.5718,
585
+ "rewards/accuracies": 0.7250000238418579,
586
+ "rewards/chosen": -0.5117169618606567,
587
+ "rewards/margins": 0.5143001675605774,
588
+ "rewards/rejected": -1.026017189025879,
589
+ "step": 370
590
+ },
591
+ {
592
+ "epoch": 0.79,
593
+ "learning_rate": 6.138919252022435e-08,
594
+ "logits/chosen": -0.8471282124519348,
595
+ "logits/rejected": -0.8318672180175781,
596
+ "logps/chosen": -351.12689208984375,
597
+ "logps/rejected": -389.46929931640625,
598
+ "loss": 0.5572,
599
+ "rewards/accuracies": 0.737500011920929,
600
+ "rewards/chosen": -0.6237812042236328,
601
+ "rewards/margins": 0.5021282434463501,
602
+ "rewards/rejected": -1.1259095668792725,
603
+ "step": 380
604
+ },
605
+ {
606
+ "epoch": 0.82,
607
+ "learning_rate": 4.991445467064689e-08,
608
+ "logits/chosen": -0.8562029600143433,
609
+ "logits/rejected": -0.8402010798454285,
610
+ "logps/chosen": -342.40411376953125,
611
+ "logps/rejected": -366.63250732421875,
612
+ "loss": 0.5666,
613
+ "rewards/accuracies": 0.643750011920929,
614
+ "rewards/chosen": -0.5931364297866821,
615
+ "rewards/margins": 0.336722195148468,
616
+ "rewards/rejected": -0.9298585653305054,
617
+ "step": 390
618
+ },
619
+ {
620
+ "epoch": 0.84,
621
+ "learning_rate": 3.9507259776993954e-08,
622
+ "logits/chosen": -0.8323208093643188,
623
+ "logits/rejected": -0.8248344659805298,
624
+ "logps/chosen": -379.9523620605469,
625
+ "logps/rejected": -394.05401611328125,
626
+ "loss": 0.5602,
627
+ "rewards/accuracies": 0.6937500238418579,
628
+ "rewards/chosen": -0.5521629452705383,
629
+ "rewards/margins": 0.45100274682044983,
630
+ "rewards/rejected": -1.003165602684021,
631
+ "step": 400
632
+ },
633
+ {
634
+ "epoch": 0.84,
635
+ "eval_logits/chosen": -0.92626953125,
636
+ "eval_logits/rejected": -0.8578699231147766,
637
+ "eval_logps/chosen": -329.260498046875,
638
+ "eval_logps/rejected": -374.94903564453125,
639
+ "eval_loss": 0.5689293742179871,
640
+ "eval_rewards/accuracies": 0.734375,
641
+ "eval_rewards/chosen": -0.49638885259628296,
642
+ "eval_rewards/margins": 0.5193302035331726,
643
+ "eval_rewards/rejected": -1.0157190561294556,
644
+ "eval_runtime": 136.1974,
645
+ "eval_samples_per_second": 14.685,
646
+ "eval_steps_per_second": 0.235,
647
+ "step": 400
648
+ },
649
+ {
650
+ "epoch": 0.86,
651
+ "learning_rate": 3.022313472693447e-08,
652
+ "logits/chosen": -0.9494141340255737,
653
+ "logits/rejected": -0.9114382863044739,
654
+ "logps/chosen": -325.3351135253906,
655
+ "logps/rejected": -346.55963134765625,
656
+ "loss": 0.5736,
657
+ "rewards/accuracies": 0.762499988079071,
658
+ "rewards/chosen": -0.538487434387207,
659
+ "rewards/margins": 0.4442841410636902,
660
+ "rewards/rejected": -0.9827715754508972,
661
+ "step": 410
662
+ },
663
+ {
664
+ "epoch": 0.88,
665
+ "learning_rate": 2.2111614344599684e-08,
666
+ "logits/chosen": -0.9237302541732788,
667
+ "logits/rejected": -0.8802440762519836,
668
+ "logps/chosen": -330.2814025878906,
669
+ "logps/rejected": -381.2386169433594,
670
+ "loss": 0.5607,
671
+ "rewards/accuracies": 0.6875,
672
+ "rewards/chosen": -0.5165634155273438,
673
+ "rewards/margins": 0.437481164932251,
674
+ "rewards/rejected": -0.9540446400642395,
675
+ "step": 420
676
+ },
677
+ {
678
+ "epoch": 0.9,
679
+ "learning_rate": 1.521597710086439e-08,
680
+ "logits/chosen": -0.8156334757804871,
681
+ "logits/rejected": -0.8552393913269043,
682
+ "logps/chosen": -364.59478759765625,
683
+ "logps/rejected": -368.82489013671875,
684
+ "loss": 0.5777,
685
+ "rewards/accuracies": 0.737500011920929,
686
+ "rewards/chosen": -0.5483056306838989,
687
+ "rewards/margins": 0.5216010808944702,
688
+ "rewards/rejected": -1.0699067115783691,
689
+ "step": 430
690
+ },
691
+ {
692
+ "epoch": 0.92,
693
+ "learning_rate": 9.57301420397924e-09,
694
+ "logits/chosen": -0.9248915910720825,
695
+ "logits/rejected": -0.8963875770568848,
696
+ "logps/chosen": -329.3937683105469,
697
+ "logps/rejected": -360.4046325683594,
698
+ "loss": 0.5606,
699
+ "rewards/accuracies": 0.6937500238418579,
700
+ "rewards/chosen": -0.5845829248428345,
701
+ "rewards/margins": 0.42287713289260864,
702
+ "rewards/rejected": -1.007460117340088,
703
+ "step": 440
704
+ },
705
+ {
706
+ "epoch": 0.94,
707
+ "learning_rate": 5.212833302556258e-09,
708
+ "logits/chosen": -1.0620511770248413,
709
+ "logits/rejected": -1.0440218448638916,
710
+ "logps/chosen": -308.4063720703125,
711
+ "logps/rejected": -327.61328125,
712
+ "loss": 0.5911,
713
+ "rewards/accuracies": 0.6937500238418579,
714
+ "rewards/chosen": -0.5545769333839417,
715
+ "rewards/margins": 0.38095879554748535,
716
+ "rewards/rejected": -0.935535728931427,
717
+ "step": 450
718
+ },
719
+ {
720
+ "epoch": 0.96,
721
+ "learning_rate": 2.158697848236607e-09,
722
+ "logits/chosen": -0.9425494074821472,
723
+ "logits/rejected": -0.9231334924697876,
724
+ "logps/chosen": -308.18743896484375,
725
+ "logps/rejected": -333.3728942871094,
726
+ "loss": 0.5588,
727
+ "rewards/accuracies": 0.737500011920929,
728
+ "rewards/chosen": -0.6228442192077637,
729
+ "rewards/margins": 0.42768868803977966,
730
+ "rewards/rejected": -1.0505329370498657,
731
+ "step": 460
732
+ },
733
+ {
734
+ "epoch": 0.98,
735
+ "learning_rate": 4.269029751107489e-10,
736
+ "logits/chosen": -0.9223429560661316,
737
+ "logits/rejected": -0.9098516702651978,
738
+ "logps/chosen": -363.28765869140625,
739
+ "logps/rejected": -387.8728942871094,
740
+ "loss": 0.5479,
741
+ "rewards/accuracies": 0.793749988079071,
742
+ "rewards/chosen": -0.480919748544693,
743
+ "rewards/margins": 0.6743713617324829,
744
+ "rewards/rejected": -1.155290961265564,
745
+ "step": 470
746
+ },
747
+ {
748
+ "epoch": 1.0,
749
+ "step": 478,
750
+ "total_flos": 0.0,
751
+ "train_loss": 0.6029723678173879,
752
+ "train_runtime": 7448.3301,
753
+ "train_samples_per_second": 8.208,
754
+ "train_steps_per_second": 0.064
755
+ }
756
+ ],
757
+ "logging_steps": 10,
758
+ "max_steps": 478,
759
+ "num_input_tokens_seen": 0,
760
+ "num_train_epochs": 1,
761
+ "save_steps": 10000,
762
+ "total_flos": 0.0,
763
+ "train_batch_size": 8,
764
+ "trial_name": null,
765
+ "trial_params": null
766
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c88a0dab76940905c6544a6bc2f4872ba3b4fb06c96efa9cd5068532a448c509
3
+ size 5816