DrNicefellow
commited on
Upload 13 files
Browse files- config.json +27 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +233 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +16 -0
- tokenizer.json +0 -0
- tokenizer_config.json +238 -0
- trainer_state.json +280 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"OlmoForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"clip_qkv": null,
|
8 |
+
"eos_token_id": 50279,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8192,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "olmo",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 4,
|
18 |
+
"pad_token_id": 1,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"rope_theta": 10000.0,
|
22 |
+
"tie_word_embeddings": true,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.40.2",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 50304
|
27 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 50279,
|
4 |
+
"pad_token_id": 1,
|
5 |
+
"transformers_version": "4.40.2"
|
6 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c81507ae8ae0498e3bb2bf4f6b34463b3414fa8fe404261cd55061f1b3f23e80
|
3 |
+
size 16393633958
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aae3a5d8723978c157852938f528320284fe393d40d7d0d7ded7bb69bef63a6b
|
3 |
+
size 4967152029
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70e8336ef01ab80245d82da38bfc156af474a66acd08983818b4839553a3b47d
|
3 |
+
size 3229646818
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,233 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 8196718592
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00001-of-00002.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
79 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
86 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
87 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
88 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
89 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
90 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
91 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
92 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
100 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
101 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
102 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
103 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
104 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
105 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
106 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
107 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
108 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
109 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
110 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
111 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
112 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
113 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
114 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
115 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
116 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
117 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
118 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
119 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
120 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
121 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
122 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
123 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
124 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
125 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
126 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
127 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
128 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
129 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
130 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
131 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
132 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
133 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
134 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
135 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
136 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
137 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
138 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
139 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
140 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
141 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
142 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
143 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
144 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
145 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
146 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
147 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
148 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
149 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
150 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
151 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
152 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
153 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
154 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
155 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
156 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
157 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
158 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
159 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
160 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
161 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
162 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
163 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
164 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
165 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
166 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
167 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
168 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
169 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
170 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
171 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
172 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
173 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
174 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
175 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
176 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
177 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
178 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
179 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
180 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
181 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
182 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
183 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
184 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
185 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
186 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
187 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
188 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
189 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
190 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
191 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
192 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
193 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
194 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
195 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
196 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
197 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
198 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
199 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
200 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
201 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
202 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
203 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
204 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
205 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
206 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
207 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
208 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
209 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
210 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
211 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
212 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
213 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
214 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
215 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
216 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
217 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
218 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
220 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
222 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
224 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
225 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
226 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
227 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
228 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
229 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
230 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
231 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin"
|
232 |
+
}
|
233 |
+
}
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14166e5488a21b7db2dbe86eed0ab35c30dcdfaddda6830d9a1250e9a738cd0f
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<|padding|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
}
|
16 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,238 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": false,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "|||IP_ADDRESS|||",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": false
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<|padding|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"50254": {
|
23 |
+
"content": " ",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"50255": {
|
31 |
+
"content": " ",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"50256": {
|
39 |
+
"content": " ",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"50257": {
|
47 |
+
"content": " ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"50258": {
|
55 |
+
"content": " ",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"50259": {
|
63 |
+
"content": " ",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"50260": {
|
71 |
+
"content": " ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"50261": {
|
79 |
+
"content": " ",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"50262": {
|
87 |
+
"content": " ",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"50263": {
|
95 |
+
"content": " ",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"50264": {
|
103 |
+
"content": " ",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"50265": {
|
111 |
+
"content": " ",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": false
|
117 |
+
},
|
118 |
+
"50266": {
|
119 |
+
"content": " ",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": false
|
125 |
+
},
|
126 |
+
"50267": {
|
127 |
+
"content": " ",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"50268": {
|
135 |
+
"content": " ",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"50269": {
|
143 |
+
"content": " ",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"50270": {
|
151 |
+
"content": " ",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"50271": {
|
159 |
+
"content": " ",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"50272": {
|
167 |
+
"content": " ",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"50273": {
|
175 |
+
"content": " ",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": false
|
181 |
+
},
|
182 |
+
"50274": {
|
183 |
+
"content": " ",
|
184 |
+
"lstrip": false,
|
185 |
+
"normalized": true,
|
186 |
+
"rstrip": false,
|
187 |
+
"single_word": false,
|
188 |
+
"special": false
|
189 |
+
},
|
190 |
+
"50275": {
|
191 |
+
"content": " ",
|
192 |
+
"lstrip": false,
|
193 |
+
"normalized": true,
|
194 |
+
"rstrip": false,
|
195 |
+
"single_word": false,
|
196 |
+
"special": false
|
197 |
+
},
|
198 |
+
"50276": {
|
199 |
+
"content": " ",
|
200 |
+
"lstrip": false,
|
201 |
+
"normalized": true,
|
202 |
+
"rstrip": false,
|
203 |
+
"single_word": false,
|
204 |
+
"special": false
|
205 |
+
},
|
206 |
+
"50277": {
|
207 |
+
"content": "|||EMAIL_ADDRESS|||",
|
208 |
+
"lstrip": false,
|
209 |
+
"normalized": true,
|
210 |
+
"rstrip": false,
|
211 |
+
"single_word": false,
|
212 |
+
"special": false
|
213 |
+
},
|
214 |
+
"50278": {
|
215 |
+
"content": "|||PHONE_NUMBER|||",
|
216 |
+
"lstrip": false,
|
217 |
+
"normalized": true,
|
218 |
+
"rstrip": false,
|
219 |
+
"single_word": false,
|
220 |
+
"special": false
|
221 |
+
},
|
222 |
+
"50279": {
|
223 |
+
"content": "<|endoftext|>",
|
224 |
+
"lstrip": false,
|
225 |
+
"normalized": false,
|
226 |
+
"rstrip": false,
|
227 |
+
"single_word": false,
|
228 |
+
"special": true
|
229 |
+
}
|
230 |
+
},
|
231 |
+
"bos_token": null,
|
232 |
+
"clean_up_tokenization_spaces": true,
|
233 |
+
"eos_token": "<|endoftext|>",
|
234 |
+
"model_max_length": 1000000000000000019884624838656,
|
235 |
+
"pad_token": "<|padding|>",
|
236 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
237 |
+
"unk_token": null
|
238 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,280 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.008965138752331828,
|
5 |
+
"eval_steps": 100000000,
|
6 |
+
"global_step": 1100,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 8.15012613848348e-06,
|
13 |
+
"grad_norm": 3.4710192680358887,
|
14 |
+
"learning_rate": 1.0000000000000001e-07,
|
15 |
+
"loss": 11.2605,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0002445037841545044,
|
20 |
+
"grad_norm": 5.464046955108643,
|
21 |
+
"learning_rate": 3e-06,
|
22 |
+
"loss": 10.9977,
|
23 |
+
"step": 30
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.0004890075683090088,
|
27 |
+
"grad_norm": 1.1376756429672241,
|
28 |
+
"learning_rate": 6e-06,
|
29 |
+
"loss": 9.4082,
|
30 |
+
"step": 60
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.0007335113524635132,
|
34 |
+
"grad_norm": 1.2878344058990479,
|
35 |
+
"learning_rate": 9e-06,
|
36 |
+
"loss": 8.549,
|
37 |
+
"step": 90
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.0009780151366180175,
|
41 |
+
"grad_norm": 1.2800588607788086,
|
42 |
+
"learning_rate": 1.2e-05,
|
43 |
+
"loss": 8.0361,
|
44 |
+
"step": 120
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.001222518920772522,
|
48 |
+
"grad_norm": 1.4315314292907715,
|
49 |
+
"learning_rate": 1.5e-05,
|
50 |
+
"loss": 7.653,
|
51 |
+
"step": 150
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0014670227049270264,
|
55 |
+
"grad_norm": 1.381317377090454,
|
56 |
+
"learning_rate": 1.8e-05,
|
57 |
+
"loss": 7.4179,
|
58 |
+
"step": 180
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.0017115264890815308,
|
62 |
+
"grad_norm": 1.7989460229873657,
|
63 |
+
"learning_rate": 2.1e-05,
|
64 |
+
"loss": 7.2012,
|
65 |
+
"step": 210
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.001956030273236035,
|
69 |
+
"grad_norm": 1.3431414365768433,
|
70 |
+
"learning_rate": 2.4e-05,
|
71 |
+
"loss": 7.0383,
|
72 |
+
"step": 240
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.0022005340573905395,
|
76 |
+
"grad_norm": 1.028826117515564,
|
77 |
+
"learning_rate": 2.7000000000000002e-05,
|
78 |
+
"loss": 6.866,
|
79 |
+
"step": 270
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.002445037841545044,
|
83 |
+
"grad_norm": 1.201025128364563,
|
84 |
+
"learning_rate": 3e-05,
|
85 |
+
"loss": 6.717,
|
86 |
+
"step": 300
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.0026895416256995483,
|
90 |
+
"grad_norm": 1.1023098230361938,
|
91 |
+
"learning_rate": 3.3e-05,
|
92 |
+
"loss": 6.5535,
|
93 |
+
"step": 330
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.0029340454098540527,
|
97 |
+
"grad_norm": 1.2839674949645996,
|
98 |
+
"learning_rate": 3.6e-05,
|
99 |
+
"loss": 6.4022,
|
100 |
+
"step": 360
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.003178549194008557,
|
104 |
+
"grad_norm": 2.267265796661377,
|
105 |
+
"learning_rate": 3.9000000000000006e-05,
|
106 |
+
"loss": 6.2858,
|
107 |
+
"step": 390
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.0034230529781630616,
|
111 |
+
"grad_norm": 1.0635628700256348,
|
112 |
+
"learning_rate": 4.2e-05,
|
113 |
+
"loss": 6.1681,
|
114 |
+
"step": 420
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.0036675567623175656,
|
118 |
+
"grad_norm": 1.263838768005371,
|
119 |
+
"learning_rate": 4.5e-05,
|
120 |
+
"loss": 6.0728,
|
121 |
+
"step": 450
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.00391206054647207,
|
125 |
+
"grad_norm": 1.4611454010009766,
|
126 |
+
"learning_rate": 4.8e-05,
|
127 |
+
"loss": 5.972,
|
128 |
+
"step": 480
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0041565643306265745,
|
132 |
+
"grad_norm": 1.0120561122894287,
|
133 |
+
"learning_rate": 4.999999990869806e-05,
|
134 |
+
"loss": 5.8619,
|
135 |
+
"step": 510
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.004401068114781079,
|
139 |
+
"grad_norm": 1.1349974870681763,
|
140 |
+
"learning_rate": 4.999999853916893e-05,
|
141 |
+
"loss": 5.785,
|
142 |
+
"step": 540
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.004645571898935583,
|
146 |
+
"grad_norm": 1.0840613842010498,
|
147 |
+
"learning_rate": 4.9999995526204936e-05,
|
148 |
+
"loss": 5.7071,
|
149 |
+
"step": 570
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.004890075683090088,
|
153 |
+
"grad_norm": 1.258074402809143,
|
154 |
+
"learning_rate": 4.999999086980628e-05,
|
155 |
+
"loss": 5.6199,
|
156 |
+
"step": 600
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.005134579467244592,
|
160 |
+
"grad_norm": 1.284726858139038,
|
161 |
+
"learning_rate": 4.999998456997326e-05,
|
162 |
+
"loss": 5.5465,
|
163 |
+
"step": 630
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.005379083251399097,
|
167 |
+
"grad_norm": 1.2079874277114868,
|
168 |
+
"learning_rate": 4.999997662670628e-05,
|
169 |
+
"loss": 5.4816,
|
170 |
+
"step": 660
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.005623587035553601,
|
174 |
+
"grad_norm": 1.3364052772521973,
|
175 |
+
"learning_rate": 4.999996704000589e-05,
|
176 |
+
"loss": 5.4079,
|
177 |
+
"step": 690
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.0058680908197081055,
|
181 |
+
"grad_norm": 0.9860705137252808,
|
182 |
+
"learning_rate": 4.99999558098727e-05,
|
183 |
+
"loss": 5.3598,
|
184 |
+
"step": 720
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.00611259460386261,
|
188 |
+
"grad_norm": 1.2071930170059204,
|
189 |
+
"learning_rate": 4.9999942936307445e-05,
|
190 |
+
"loss": 5.2884,
|
191 |
+
"step": 750
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.006357098388017114,
|
195 |
+
"grad_norm": 0.8959563970565796,
|
196 |
+
"learning_rate": 4.9999928419310994e-05,
|
197 |
+
"loss": 5.2391,
|
198 |
+
"step": 780
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.006601602172171619,
|
202 |
+
"grad_norm": 1.2356096506118774,
|
203 |
+
"learning_rate": 4.999991225888427e-05,
|
204 |
+
"loss": 5.1879,
|
205 |
+
"step": 810
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.006846105956326123,
|
209 |
+
"grad_norm": 0.9705113172531128,
|
210 |
+
"learning_rate": 4.999989445502837e-05,
|
211 |
+
"loss": 5.1424,
|
212 |
+
"step": 840
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.007090609740480627,
|
216 |
+
"grad_norm": 0.9504437446594238,
|
217 |
+
"learning_rate": 4.9999875007744436e-05,
|
218 |
+
"loss": 5.0966,
|
219 |
+
"step": 870
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.007335113524635131,
|
223 |
+
"grad_norm": 0.9488673806190491,
|
224 |
+
"learning_rate": 4.9999853917033756e-05,
|
225 |
+
"loss": 5.0424,
|
226 |
+
"step": 900
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.007579617308789636,
|
230 |
+
"grad_norm": 0.959373950958252,
|
231 |
+
"learning_rate": 4.999983118289773e-05,
|
232 |
+
"loss": 5.0387,
|
233 |
+
"step": 930
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.00782412109294414,
|
237 |
+
"grad_norm": 0.8465414643287659,
|
238 |
+
"learning_rate": 4.999980680533782e-05,
|
239 |
+
"loss": 4.9769,
|
240 |
+
"step": 960
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.008068624877098645,
|
244 |
+
"grad_norm": 0.8328993916511536,
|
245 |
+
"learning_rate": 4.999978078435567e-05,
|
246 |
+
"loss": 4.9335,
|
247 |
+
"step": 990
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.008313128661253149,
|
251 |
+
"grad_norm": 0.8107655644416809,
|
252 |
+
"learning_rate": 4.999975311995295e-05,
|
253 |
+
"loss": 4.9214,
|
254 |
+
"step": 1020
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.008557632445407654,
|
258 |
+
"grad_norm": 0.8149654865264893,
|
259 |
+
"learning_rate": 4.99997238121315e-05,
|
260 |
+
"loss": 4.8651,
|
261 |
+
"step": 1050
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.008802136229562158,
|
265 |
+
"grad_norm": 0.8837414979934692,
|
266 |
+
"learning_rate": 4.999969286089325e-05,
|
267 |
+
"loss": 4.8327,
|
268 |
+
"step": 1080
|
269 |
+
}
|
270 |
+
],
|
271 |
+
"logging_steps": 30,
|
272 |
+
"max_steps": 368091,
|
273 |
+
"num_input_tokens_seen": 0,
|
274 |
+
"num_train_epochs": 3,
|
275 |
+
"save_steps": 100,
|
276 |
+
"total_flos": 1.052232627781632e+18,
|
277 |
+
"train_batch_size": 2,
|
278 |
+
"trial_name": null,
|
279 |
+
"trial_params": null
|
280 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f909d8205eae6d012dc965e337249e1d014ef52c5b7115301085202b50cb6566
|
3 |
+
size 4984
|