Commit
•
838208d
1
Parent(s):
7b54c0f
Upload model
Browse files- config.json +32 -0
- generation_config.json +7 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +347 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +59 -0
- tokenizer.json +0 -0
- tokenizer_config.json +319 -0
- trainer_state.json +1083 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "output_m_01IR-10_train_2e-11_3_26/checkpoint-10",
|
3 |
+
"architectures": [
|
4 |
+
"StableLmForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 100257,
|
8 |
+
"eos_token_id": 100257,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_dropout": 0.0,
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"layer_norm_eps": 1e-05,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"model_type": "stablelm",
|
17 |
+
"num_attention_heads": 32,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"pad_token_id": 100257,
|
21 |
+
"partial_rotary_factor": 0.25,
|
22 |
+
"qk_layernorm": false,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 10000,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.41.2",
|
28 |
+
"use_cache": false,
|
29 |
+
"use_parallel_residual": false,
|
30 |
+
"use_qkv_bias": true,
|
31 |
+
"vocab_size": 100352
|
32 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 100257,
|
4 |
+
"do_sample": true,
|
5 |
+
"eos_token_id": 100257,
|
6 |
+
"transformers_version": "4.41.2"
|
7 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f00c26338afb8e94f0374a800ae0f0581dd3fdece8fe14650ed6bfc9a18f1c12
|
3 |
+
size 4984037184
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1bec6af3762088adef39551c5aedf38e4cd5870caa6b9aa84e3c8974b8435db
|
3 |
+
size 1594062688
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,347 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 6578061312
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
7 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
8 |
+
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
74 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
76 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"model.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
93 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
94 |
+
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
98 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
100 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
101 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
102 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
103 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
104 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
106 |
+
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
107 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
108 |
+
"model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
110 |
+
"model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"model.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
112 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
115 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
116 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
117 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
118 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
119 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
120 |
+
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
121 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
122 |
+
"model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
124 |
+
"model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
125 |
+
"model.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
126 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
128 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
130 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
131 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
133 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
134 |
+
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
135 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
136 |
+
"model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
138 |
+
"model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
139 |
+
"model.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
140 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
142 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
143 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
144 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
145 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
146 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
148 |
+
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
152 |
+
"model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
153 |
+
"model.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
154 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
155 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
156 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
157 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
158 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
159 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
160 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
161 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
162 |
+
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
163 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
164 |
+
"model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.20.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
191 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
192 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
193 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
194 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
195 |
+
"model.layers.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
196 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
197 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
200 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
201 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
202 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
203 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
204 |
+
"model.layers.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
205 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
206 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
207 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
208 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
209 |
+
"model.layers.21.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
210 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
211 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
212 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
213 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
214 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
215 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
216 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
217 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
218 |
+
"model.layers.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
219 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
220 |
+
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
221 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
222 |
+
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
223 |
+
"model.layers.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
224 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
225 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
226 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
227 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
228 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
229 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
230 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
231 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
232 |
+
"model.layers.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
233 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
234 |
+
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
235 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
236 |
+
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
237 |
+
"model.layers.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
|
238 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
239 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
240 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
241 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
242 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
243 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
244 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
245 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
246 |
+
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
247 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
248 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
249 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
250 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
251 |
+
"model.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
252 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
253 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
254 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
255 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
256 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
257 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
258 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
259 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
260 |
+
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
261 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
262 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
263 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
264 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
265 |
+
"model.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
266 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
267 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
268 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
269 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
270 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
271 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
272 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
273 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
274 |
+
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
275 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
276 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
277 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
278 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
279 |
+
"model.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
280 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
281 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
282 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
283 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
284 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
285 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
286 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
287 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
288 |
+
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
289 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
290 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
291 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
292 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
293 |
+
"model.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
294 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
295 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
296 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
297 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
298 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
299 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
300 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
301 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
302 |
+
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
303 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
304 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
305 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
306 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
307 |
+
"model.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
308 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
309 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
310 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
311 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
312 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
313 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
314 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
315 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
316 |
+
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
317 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
318 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
319 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
320 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
321 |
+
"model.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
322 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
323 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
324 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
325 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
326 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
327 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
328 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
329 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
330 |
+
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
331 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
332 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
333 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
334 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
335 |
+
"model.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
|
336 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
337 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
338 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
339 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
340 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
341 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
342 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
343 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
344 |
+
"model.norm.bias": "model-00002-of-00002.safetensors",
|
345 |
+
"model.norm.weight": "model-00002-of-00002.safetensors"
|
346 |
+
}
|
347 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a148f052d360ce6169fb3c442ff74ba55793f102958f744eda7c9287eb92353a
|
3 |
+
size 411849948
|
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 sha256:2e9233fd73340c857eb5d9ed7d538f3cda2965de7ca74cd437a6d7478e4e1c63
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|reg_extra|>",
|
4 |
+
"<|endoftext|>",
|
5 |
+
"<|fim_prefix|>",
|
6 |
+
"<|fim_middle|>",
|
7 |
+
"<|fim_suffix|>",
|
8 |
+
"<|fim_pad|>",
|
9 |
+
"<gh_stars>",
|
10 |
+
"<filename>",
|
11 |
+
"<issue_start>",
|
12 |
+
"<issue_comment>",
|
13 |
+
"<issue_closed>",
|
14 |
+
"<jupyter_start>",
|
15 |
+
"<jupyter_text>",
|
16 |
+
"<jupyter_code>",
|
17 |
+
"<jupyter_output>",
|
18 |
+
"<empty_output>",
|
19 |
+
"<commit_before>",
|
20 |
+
"<commit_msg>",
|
21 |
+
"<commit_after>",
|
22 |
+
"<reponame>",
|
23 |
+
"<|endofprompt|>",
|
24 |
+
"<|im_start|>",
|
25 |
+
"<|im_end|>",
|
26 |
+
"<|pause|>",
|
27 |
+
"<|reg0|>",
|
28 |
+
"<|reg1|>",
|
29 |
+
"<|reg2|>",
|
30 |
+
"<|reg3|>",
|
31 |
+
"<|reg4|>",
|
32 |
+
"<|reg5|>",
|
33 |
+
"<|reg6|>",
|
34 |
+
"<|reg7|>",
|
35 |
+
"<|extra0|>"
|
36 |
+
],
|
37 |
+
"bos_token": {
|
38 |
+
"content": "<|endoftext|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"eos_token": {
|
45 |
+
"content": "<|endoftext|>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
},
|
51 |
+
"pad_token": "<|endoftext|>",
|
52 |
+
"unk_token": {
|
53 |
+
"content": "<|endoftext|>",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false
|
58 |
+
}
|
59 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"100256": {
|
6 |
+
"content": "<|reg_extra|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"100257": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"100258": {
|
22 |
+
"content": "<|fim_prefix|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"100259": {
|
30 |
+
"content": "<|fim_middle|>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"100260": {
|
38 |
+
"content": "<|fim_suffix|>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"100261": {
|
46 |
+
"content": "<|fim_pad|>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"100262": {
|
54 |
+
"content": "<gh_stars>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"100263": {
|
62 |
+
"content": "<filename>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"100264": {
|
70 |
+
"content": "<issue_start>",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"100265": {
|
78 |
+
"content": "<issue_comment>",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"100266": {
|
86 |
+
"content": "<issue_closed>",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"100267": {
|
94 |
+
"content": "<jupyter_start>",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"100268": {
|
102 |
+
"content": "<jupyter_text>",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"100269": {
|
110 |
+
"content": "<jupyter_code>",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"100270": {
|
118 |
+
"content": "<jupyter_output>",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"100271": {
|
126 |
+
"content": "<empty_output>",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"100272": {
|
134 |
+
"content": "<commit_before>",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"100273": {
|
142 |
+
"content": "<commit_msg>",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"100274": {
|
150 |
+
"content": "<commit_after>",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"100275": {
|
158 |
+
"content": "<reponame>",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"100276": {
|
166 |
+
"content": "<|endofprompt|>",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"100277": {
|
174 |
+
"content": "<|im_start|>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
},
|
181 |
+
"100278": {
|
182 |
+
"content": "<|im_end|>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": true
|
188 |
+
},
|
189 |
+
"100279": {
|
190 |
+
"content": "<|pause|>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": true
|
196 |
+
},
|
197 |
+
"100280": {
|
198 |
+
"content": "<|reg0|>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": true
|
204 |
+
},
|
205 |
+
"100281": {
|
206 |
+
"content": "<|reg1|>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
"100282": {
|
214 |
+
"content": "<|reg2|>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": true
|
220 |
+
},
|
221 |
+
"100283": {
|
222 |
+
"content": "<|reg3|>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": true
|
228 |
+
},
|
229 |
+
"100284": {
|
230 |
+
"content": "<|reg4|>",
|
231 |
+
"lstrip": false,
|
232 |
+
"normalized": false,
|
233 |
+
"rstrip": false,
|
234 |
+
"single_word": false,
|
235 |
+
"special": true
|
236 |
+
},
|
237 |
+
"100285": {
|
238 |
+
"content": "<|reg5|>",
|
239 |
+
"lstrip": false,
|
240 |
+
"normalized": false,
|
241 |
+
"rstrip": false,
|
242 |
+
"single_word": false,
|
243 |
+
"special": true
|
244 |
+
},
|
245 |
+
"100286": {
|
246 |
+
"content": "<|reg6|>",
|
247 |
+
"lstrip": false,
|
248 |
+
"normalized": false,
|
249 |
+
"rstrip": false,
|
250 |
+
"single_word": false,
|
251 |
+
"special": true
|
252 |
+
},
|
253 |
+
"100287": {
|
254 |
+
"content": "<|reg7|>",
|
255 |
+
"lstrip": false,
|
256 |
+
"normalized": false,
|
257 |
+
"rstrip": false,
|
258 |
+
"single_word": false,
|
259 |
+
"special": true
|
260 |
+
},
|
261 |
+
"100288": {
|
262 |
+
"content": "<|extra0|>",
|
263 |
+
"lstrip": false,
|
264 |
+
"normalized": false,
|
265 |
+
"rstrip": false,
|
266 |
+
"single_word": false,
|
267 |
+
"special": true
|
268 |
+
}
|
269 |
+
},
|
270 |
+
"additional_special_tokens": [
|
271 |
+
"<|reg_extra|>",
|
272 |
+
"<|endoftext|>",
|
273 |
+
"<|fim_prefix|>",
|
274 |
+
"<|fim_middle|>",
|
275 |
+
"<|fim_suffix|>",
|
276 |
+
"<|fim_pad|>",
|
277 |
+
"<gh_stars>",
|
278 |
+
"<filename>",
|
279 |
+
"<issue_start>",
|
280 |
+
"<issue_comment>",
|
281 |
+
"<issue_closed>",
|
282 |
+
"<jupyter_start>",
|
283 |
+
"<jupyter_text>",
|
284 |
+
"<jupyter_code>",
|
285 |
+
"<jupyter_output>",
|
286 |
+
"<empty_output>",
|
287 |
+
"<commit_before>",
|
288 |
+
"<commit_msg>",
|
289 |
+
"<commit_after>",
|
290 |
+
"<reponame>",
|
291 |
+
"<|endofprompt|>",
|
292 |
+
"<|im_start|>",
|
293 |
+
"<|im_end|>",
|
294 |
+
"<|pause|>",
|
295 |
+
"<|reg0|>",
|
296 |
+
"<|reg1|>",
|
297 |
+
"<|reg2|>",
|
298 |
+
"<|reg3|>",
|
299 |
+
"<|reg4|>",
|
300 |
+
"<|reg5|>",
|
301 |
+
"<|reg6|>",
|
302 |
+
"<|reg7|>",
|
303 |
+
"<|extra0|>"
|
304 |
+
],
|
305 |
+
"bos_token": "<|endoftext|>",
|
306 |
+
"clean_up_tokenization_spaces": true,
|
307 |
+
"eos_token": "<|endoftext|>",
|
308 |
+
"max_length": 3896,
|
309 |
+
"model_max_length": 1000000000000000019884624838656,
|
310 |
+
"pad_to_multiple_of": null,
|
311 |
+
"pad_token": "<|endoftext|>",
|
312 |
+
"pad_token_type_id": 0,
|
313 |
+
"padding_side": "left",
|
314 |
+
"stride": 0,
|
315 |
+
"tokenizer_class": "GPT2Tokenizer",
|
316 |
+
"truncation_side": "right",
|
317 |
+
"truncation_strategy": "longest_first",
|
318 |
+
"unk_token": "<|endoftext|>"
|
319 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1083 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.46345811051693403,
|
5 |
+
"eval_steps": 202,
|
6 |
+
"global_step": 150,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0030897207367795603,
|
13 |
+
"grad_norm": 122071.1171875,
|
14 |
+
"learning_rate": 4.0000000000000004e-11,
|
15 |
+
"loss": 28.8142,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.006179441473559121,
|
20 |
+
"grad_norm": 119214.984375,
|
21 |
+
"learning_rate": 8.000000000000001e-11,
|
22 |
+
"loss": 28.2909,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.009269162210338681,
|
27 |
+
"grad_norm": 126446.515625,
|
28 |
+
"learning_rate": 1.2e-10,
|
29 |
+
"loss": 27.4632,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.012358882947118241,
|
34 |
+
"grad_norm": 113183.5078125,
|
35 |
+
"learning_rate": 1.6000000000000002e-10,
|
36 |
+
"loss": 29.2478,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.015448603683897801,
|
41 |
+
"grad_norm": 122417.453125,
|
42 |
+
"learning_rate": 2e-10,
|
43 |
+
"loss": 27.6777,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.018538324420677363,
|
48 |
+
"grad_norm": 122875.0234375,
|
49 |
+
"learning_rate": 1.9998728465660104e-10,
|
50 |
+
"loss": 26.864,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02162804515745692,
|
55 |
+
"grad_norm": 123327.859375,
|
56 |
+
"learning_rate": 1.9994914186000328e-10,
|
57 |
+
"loss": 27.4961,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.024717765894236483,
|
62 |
+
"grad_norm": 125148.296875,
|
63 |
+
"learning_rate": 1.9988558131018187e-10,
|
64 |
+
"loss": 27.0758,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.027807486631016044,
|
69 |
+
"grad_norm": 123805.0078125,
|
70 |
+
"learning_rate": 1.9979661917102113e-10,
|
71 |
+
"loss": 26.7955,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.030897207367795602,
|
76 |
+
"grad_norm": 137252.546875,
|
77 |
+
"learning_rate": 1.996822780662041e-10,
|
78 |
+
"loss": 23.848,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.03398692810457516,
|
83 |
+
"grad_norm": 123848.6953125,
|
84 |
+
"learning_rate": 1.99542587073459e-10,
|
85 |
+
"loss": 26.2061,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.037076648841354726,
|
90 |
+
"grad_norm": 103722.9296875,
|
91 |
+
"learning_rate": 1.9937758171716467e-10,
|
92 |
+
"loss": 30.3732,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.040166369578134284,
|
97 |
+
"grad_norm": 132914.09375,
|
98 |
+
"learning_rate": 1.9918730395931647e-10,
|
99 |
+
"loss": 25.836,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.04325609031491384,
|
104 |
+
"grad_norm": 122652.0546875,
|
105 |
+
"learning_rate": 1.9897180218885506e-10,
|
106 |
+
"loss": 26.7338,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.04634581105169341,
|
111 |
+
"grad_norm": 125711.875,
|
112 |
+
"learning_rate": 1.9873113120936074e-10,
|
113 |
+
"loss": 27.9079,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.049435531788472965,
|
118 |
+
"grad_norm": 131257.78125,
|
119 |
+
"learning_rate": 1.9846535222511647e-10,
|
120 |
+
"loss": 25.2777,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.052525252525252523,
|
125 |
+
"grad_norm": 135439.875,
|
126 |
+
"learning_rate": 1.9817453282554334e-10,
|
127 |
+
"loss": 25.622,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.05561497326203209,
|
132 |
+
"grad_norm": 112875.90625,
|
133 |
+
"learning_rate": 1.97858746968012e-10,
|
134 |
+
"loss": 28.8657,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05870469399881165,
|
139 |
+
"grad_norm": 124934.046875,
|
140 |
+
"learning_rate": 1.9751807495903485e-10,
|
141 |
+
"loss": 27.4469,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.061794414735591205,
|
146 |
+
"grad_norm": 126672.046875,
|
147 |
+
"learning_rate": 1.9715260343384348e-10,
|
148 |
+
"loss": 26.0207,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.06488413547237076,
|
153 |
+
"grad_norm": 121388.1953125,
|
154 |
+
"learning_rate": 1.9676242533435677e-10,
|
155 |
+
"loss": 28.2452,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.06797385620915032,
|
160 |
+
"grad_norm": 126791.9921875,
|
161 |
+
"learning_rate": 1.963476398855452e-10,
|
162 |
+
"loss": 27.0343,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.0710635769459299,
|
167 |
+
"grad_norm": 120207.7734375,
|
168 |
+
"learning_rate": 1.9590835257019716e-10,
|
169 |
+
"loss": 27.06,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.07415329768270945,
|
174 |
+
"grad_norm": 119256.28125,
|
175 |
+
"learning_rate": 1.9544467510209388e-10,
|
176 |
+
"loss": 27.0009,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07724301841948901,
|
181 |
+
"grad_norm": 132457.265625,
|
182 |
+
"learning_rate": 1.9495672539760009e-10,
|
183 |
+
"loss": 26.5873,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.08033273915626857,
|
188 |
+
"grad_norm": 130291.3515625,
|
189 |
+
"learning_rate": 1.9444462754567682e-10,
|
190 |
+
"loss": 27.6641,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.08342245989304813,
|
195 |
+
"grad_norm": 122393.9375,
|
196 |
+
"learning_rate": 1.9390851177632496e-10,
|
197 |
+
"loss": 26.8649,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.08651218062982768,
|
202 |
+
"grad_norm": 123576.078125,
|
203 |
+
"learning_rate": 1.9334851442746664e-10,
|
204 |
+
"loss": 28.0714,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.08960190136660724,
|
209 |
+
"grad_norm": 121570.703125,
|
210 |
+
"learning_rate": 1.9276477791027375e-10,
|
211 |
+
"loss": 26.8387,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.09269162210338681,
|
216 |
+
"grad_norm": 117390.9921875,
|
217 |
+
"learning_rate": 1.9215745067295168e-10,
|
218 |
+
"loss": 28.8172,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09578134284016637,
|
223 |
+
"grad_norm": 127661.9609375,
|
224 |
+
"learning_rate": 1.9152668716298797e-10,
|
225 |
+
"loss": 27.3977,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.09887106357694593,
|
230 |
+
"grad_norm": 129576.4453125,
|
231 |
+
"learning_rate": 1.9087264778787533e-10,
|
232 |
+
"loss": 25.7966,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.10196078431372549,
|
237 |
+
"grad_norm": 117011.7578125,
|
238 |
+
"learning_rate": 1.9019549887431877e-10,
|
239 |
+
"loss": 29.9255,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.10505050505050505,
|
244 |
+
"grad_norm": 120770.2265625,
|
245 |
+
"learning_rate": 1.894954126259376e-10,
|
246 |
+
"loss": 27.4423,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.1081402257872846,
|
251 |
+
"grad_norm": 118635.3671875,
|
252 |
+
"learning_rate": 1.8877256707947306e-10,
|
253 |
+
"loss": 29.0251,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.11122994652406418,
|
258 |
+
"grad_norm": 122824.8203125,
|
259 |
+
"learning_rate": 1.88027146059512e-10,
|
260 |
+
"loss": 28.9256,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11431966726084374,
|
265 |
+
"grad_norm": 126411.421875,
|
266 |
+
"learning_rate": 1.872593391317394e-10,
|
267 |
+
"loss": 26.5279,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.1174093879976233,
|
272 |
+
"grad_norm": 132717.421875,
|
273 |
+
"learning_rate": 1.8646934155473023e-10,
|
274 |
+
"loss": 24.6933,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.12049910873440285,
|
279 |
+
"grad_norm": 121920.703125,
|
280 |
+
"learning_rate": 1.8565735423029405e-10,
|
281 |
+
"loss": 27.9129,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.12358882947118241,
|
286 |
+
"grad_norm": 118110.3515625,
|
287 |
+
"learning_rate": 1.8482358365238414e-10,
|
288 |
+
"loss": 28.6163,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.12667855020796198,
|
293 |
+
"grad_norm": 120299.3359375,
|
294 |
+
"learning_rate": 1.839682418545848e-10,
|
295 |
+
"loss": 28.5066,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.12976827094474153,
|
300 |
+
"grad_norm": 140847.53125,
|
301 |
+
"learning_rate": 1.8309154635618964e-10,
|
302 |
+
"loss": 26.3515,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.1328579916815211,
|
307 |
+
"grad_norm": 112302.9609375,
|
308 |
+
"learning_rate": 1.8219372010688515e-10,
|
309 |
+
"loss": 28.644,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.13594771241830064,
|
314 |
+
"grad_norm": 123308.875,
|
315 |
+
"learning_rate": 1.8127499143005265e-10,
|
316 |
+
"loss": 27.6619,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.13903743315508021,
|
321 |
+
"grad_norm": 125378.4921875,
|
322 |
+
"learning_rate": 1.8033559396470454e-10,
|
323 |
+
"loss": 26.452,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.1421271538918598,
|
328 |
+
"grad_norm": 123326.15625,
|
329 |
+
"learning_rate": 1.7937576660606797e-10,
|
330 |
+
"loss": 26.3463,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.14521687462863933,
|
335 |
+
"grad_norm": 117453.265625,
|
336 |
+
"learning_rate": 1.7839575344483237e-10,
|
337 |
+
"loss": 29.4332,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.1483065953654189,
|
342 |
+
"grad_norm": 118000.7265625,
|
343 |
+
"learning_rate": 1.773958037050753e-10,
|
344 |
+
"loss": 28.7868,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.15139631610219845,
|
349 |
+
"grad_norm": 127199.6953125,
|
350 |
+
"learning_rate": 1.7637617168088326e-10,
|
351 |
+
"loss": 25.8592,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.15448603683897802,
|
356 |
+
"grad_norm": 115966.7265625,
|
357 |
+
"learning_rate": 1.753371166716828e-10,
|
358 |
+
"loss": 28.3176,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.15757575757575756,
|
363 |
+
"grad_norm": 120307.578125,
|
364 |
+
"learning_rate": 1.7427890291629892e-10,
|
365 |
+
"loss": 28.7395,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.16066547831253714,
|
370 |
+
"grad_norm": 110086.4296875,
|
371 |
+
"learning_rate": 1.732017995257575e-10,
|
372 |
+
"loss": 29.0903,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.1637551990493167,
|
377 |
+
"grad_norm": 125848.5,
|
378 |
+
"learning_rate": 1.721060804148482e-10,
|
379 |
+
"loss": 27.0135,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.16684491978609625,
|
384 |
+
"grad_norm": 138127.296875,
|
385 |
+
"learning_rate": 1.7099202423246632e-10,
|
386 |
+
"loss": 24.2078,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16993464052287582,
|
391 |
+
"grad_norm": 126173.71875,
|
392 |
+
"learning_rate": 1.6985991429075038e-10,
|
393 |
+
"loss": 27.1029,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.17302436125965537,
|
398 |
+
"grad_norm": 113517.828125,
|
399 |
+
"learning_rate": 1.687100384930338e-10,
|
400 |
+
"loss": 28.6511,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.17611408199643494,
|
405 |
+
"grad_norm": 125443.1640625,
|
406 |
+
"learning_rate": 1.6754268926062938e-10,
|
407 |
+
"loss": 28.0516,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.17920380273321448,
|
412 |
+
"grad_norm": 120414.265625,
|
413 |
+
"learning_rate": 1.6635816345846412e-10,
|
414 |
+
"loss": 26.6481,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.18229352346999406,
|
419 |
+
"grad_norm": 142621.21875,
|
420 |
+
"learning_rate": 1.6515676231958488e-10,
|
421 |
+
"loss": 24.7811,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.18538324420677363,
|
426 |
+
"grad_norm": 128307.296875,
|
427 |
+
"learning_rate": 1.6393879136855248e-10,
|
428 |
+
"loss": 24.9562,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.18847296494355317,
|
433 |
+
"grad_norm": 131207.0625,
|
434 |
+
"learning_rate": 1.6270456034374474e-10,
|
435 |
+
"loss": 26.3174,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.19156268568033274,
|
440 |
+
"grad_norm": 126856.7578125,
|
441 |
+
"learning_rate": 1.6145438311858797e-10,
|
442 |
+
"loss": 24.581,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.1946524064171123,
|
447 |
+
"grad_norm": 130663.9921875,
|
448 |
+
"learning_rate": 1.601885776217367e-10,
|
449 |
+
"loss": 24.543,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.19774212715389186,
|
454 |
+
"grad_norm": 117330.453125,
|
455 |
+
"learning_rate": 1.589074657562223e-10,
|
456 |
+
"loss": 26.1565,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.20083184789067143,
|
461 |
+
"grad_norm": 126654.546875,
|
462 |
+
"learning_rate": 1.5761137331759085e-10,
|
463 |
+
"loss": 26.9999,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.20392156862745098,
|
468 |
+
"grad_norm": 122709.8984375,
|
469 |
+
"learning_rate": 1.5630062991105098e-10,
|
470 |
+
"loss": 26.9336,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.20701128936423055,
|
475 |
+
"grad_norm": 111839.421875,
|
476 |
+
"learning_rate": 1.5497556886765316e-10,
|
477 |
+
"loss": 29.4629,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.2101010101010101,
|
482 |
+
"grad_norm": 115566.3515625,
|
483 |
+
"learning_rate": 1.536365271595212e-10,
|
484 |
+
"loss": 28.8732,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.21319073083778967,
|
489 |
+
"grad_norm": 120251.84375,
|
490 |
+
"learning_rate": 1.5228384531415808e-10,
|
491 |
+
"loss": 28.2254,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.2162804515745692,
|
496 |
+
"grad_norm": 109853.484375,
|
497 |
+
"learning_rate": 1.5091786732784717e-10,
|
498 |
+
"loss": 28.8846,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.21937017231134878,
|
503 |
+
"grad_norm": 124965.2890625,
|
504 |
+
"learning_rate": 1.495389405781719e-10,
|
505 |
+
"loss": 27.476,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.22245989304812835,
|
510 |
+
"grad_norm": 123831.765625,
|
511 |
+
"learning_rate": 1.4814741573567514e-10,
|
512 |
+
"loss": 28.3641,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.2255496137849079,
|
517 |
+
"grad_norm": 122635.5625,
|
518 |
+
"learning_rate": 1.467436466746814e-10,
|
519 |
+
"loss": 26.8985,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.22863933452168747,
|
524 |
+
"grad_norm": 114768.140625,
|
525 |
+
"learning_rate": 1.4532799038330386e-10,
|
526 |
+
"loss": 27.3799,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.23172905525846701,
|
531 |
+
"grad_norm": 126590.0,
|
532 |
+
"learning_rate": 1.4390080687266012e-10,
|
533 |
+
"loss": 27.1862,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.2348187759952466,
|
538 |
+
"grad_norm": 121103.6640625,
|
539 |
+
"learning_rate": 1.4246245908531884e-10,
|
540 |
+
"loss": 28.5261,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.23790849673202613,
|
545 |
+
"grad_norm": 116113.4765625,
|
546 |
+
"learning_rate": 1.410133128030009e-10,
|
547 |
+
"loss": 29.2815,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.2409982174688057,
|
552 |
+
"grad_norm": 124221.265625,
|
553 |
+
"learning_rate": 1.3955373655355853e-10,
|
554 |
+
"loss": 28.5093,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.24408793820558528,
|
559 |
+
"grad_norm": 122242.0625,
|
560 |
+
"learning_rate": 1.3808410151725631e-10,
|
561 |
+
"loss": 27.9406,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.24717765894236482,
|
566 |
+
"grad_norm": 129292.234375,
|
567 |
+
"learning_rate": 1.3660478143237748e-10,
|
568 |
+
"loss": 25.4098,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.25026737967914436,
|
573 |
+
"grad_norm": 113323.875,
|
574 |
+
"learning_rate": 1.351161525001795e-10,
|
575 |
+
"loss": 30.2781,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 0.25335710041592396,
|
580 |
+
"grad_norm": 120109.671875,
|
581 |
+
"learning_rate": 1.3361859328922368e-10,
|
582 |
+
"loss": 28.7683,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 0.2564468211527035,
|
587 |
+
"grad_norm": 131119.078125,
|
588 |
+
"learning_rate": 1.3211248463910263e-10,
|
589 |
+
"loss": 26.0915,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 0.25953654188948305,
|
594 |
+
"grad_norm": 133106.078125,
|
595 |
+
"learning_rate": 1.3059820956358996e-10,
|
596 |
+
"loss": 25.8208,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.26262626262626265,
|
601 |
+
"grad_norm": 117423.5859375,
|
602 |
+
"learning_rate": 1.290761531532374e-10,
|
603 |
+
"loss": 28.491,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 0.2657159833630422,
|
608 |
+
"grad_norm": 135454.3125,
|
609 |
+
"learning_rate": 1.2754670247744354e-10,
|
610 |
+
"loss": 24.7346,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.26880570409982174,
|
615 |
+
"grad_norm": 125783.6484375,
|
616 |
+
"learning_rate": 1.260102464860195e-10,
|
617 |
+
"loss": 25.684,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.2718954248366013,
|
622 |
+
"grad_norm": 124170.6484375,
|
623 |
+
"learning_rate": 1.2446717591027624e-10,
|
624 |
+
"loss": 27.912,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 0.2749851455733809,
|
629 |
+
"grad_norm": 123135.8984375,
|
630 |
+
"learning_rate": 1.2291788316365887e-10,
|
631 |
+
"loss": 27.8059,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 0.27807486631016043,
|
636 |
+
"grad_norm": 127220.2890625,
|
637 |
+
"learning_rate": 1.213627622419535e-10,
|
638 |
+
"loss": 26.8872,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.28116458704694,
|
643 |
+
"grad_norm": 114622.0625,
|
644 |
+
"learning_rate": 1.1980220862309098e-10,
|
645 |
+
"loss": 27.7952,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 0.2842543077837196,
|
650 |
+
"grad_norm": 129463.1484375,
|
651 |
+
"learning_rate": 1.182366191665744e-10,
|
652 |
+
"loss": 25.9395,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 0.2873440285204991,
|
657 |
+
"grad_norm": 138215.8125,
|
658 |
+
"learning_rate": 1.1666639201255506e-10,
|
659 |
+
"loss": 25.4167,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 0.29043374925727866,
|
664 |
+
"grad_norm": 113110.0,
|
665 |
+
"learning_rate": 1.1509192648058249e-10,
|
666 |
+
"loss": 28.0616,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.2935234699940582,
|
671 |
+
"grad_norm": 120913.9765625,
|
672 |
+
"learning_rate": 1.1351362296805485e-10,
|
673 |
+
"loss": 28.1966,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.2966131907308378,
|
678 |
+
"grad_norm": 117201.953125,
|
679 |
+
"learning_rate": 1.1193188284839518e-10,
|
680 |
+
"loss": 27.8393,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.29970291146761735,
|
685 |
+
"grad_norm": 124783.2890625,
|
686 |
+
"learning_rate": 1.1034710836897921e-10,
|
687 |
+
"loss": 26.5054,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 0.3027926322043969,
|
692 |
+
"grad_norm": 127615.96875,
|
693 |
+
"learning_rate": 1.0875970254884129e-10,
|
694 |
+
"loss": 26.9284,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 0.3058823529411765,
|
699 |
+
"grad_norm": 132355.703125,
|
700 |
+
"learning_rate": 1.0717006907618376e-10,
|
701 |
+
"loss": 25.1614,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 0.30897207367795604,
|
706 |
+
"grad_norm": 132260.8125,
|
707 |
+
"learning_rate": 1.0557861220571625e-10,
|
708 |
+
"loss": 24.961,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.3120617944147356,
|
713 |
+
"grad_norm": 117828.6796875,
|
714 |
+
"learning_rate": 1.0398573665585105e-10,
|
715 |
+
"loss": 28.4477,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 0.3151515151515151,
|
720 |
+
"grad_norm": 130773.75,
|
721 |
+
"learning_rate": 1.023918475057803e-10,
|
722 |
+
"loss": 27.1515,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.3182412358882947,
|
727 |
+
"grad_norm": 121530.078125,
|
728 |
+
"learning_rate": 1.0079735009246167e-10,
|
729 |
+
"loss": 27.9482,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.32133095662507427,
|
734 |
+
"grad_norm": 122278.96875,
|
735 |
+
"learning_rate": 9.920264990753837e-11,
|
736 |
+
"loss": 28.2168,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 0.3244206773618538,
|
741 |
+
"grad_norm": 112929.9140625,
|
742 |
+
"learning_rate": 9.760815249421973e-11,
|
743 |
+
"loss": 29.3778,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 0.3275103980986334,
|
748 |
+
"grad_norm": 116076.59375,
|
749 |
+
"learning_rate": 9.601426334414898e-11,
|
750 |
+
"loss": 28.591,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.33060011883541296,
|
755 |
+
"grad_norm": 128873.78125,
|
756 |
+
"learning_rate": 9.442138779428376e-11,
|
757 |
+
"loss": 26.1022,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 0.3336898395721925,
|
762 |
+
"grad_norm": 127668.328125,
|
763 |
+
"learning_rate": 9.282993092381625e-11,
|
764 |
+
"loss": 25.6443,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.33677956030897205,
|
769 |
+
"grad_norm": 122660.5625,
|
770 |
+
"learning_rate": 9.12402974511587e-11,
|
771 |
+
"loss": 26.6564,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 0.33986928104575165,
|
776 |
+
"grad_norm": 120201.34375,
|
777 |
+
"learning_rate": 8.965289163102078e-11,
|
778 |
+
"loss": 25.9894,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 0.3429590017825312,
|
783 |
+
"grad_norm": 127018.890625,
|
784 |
+
"learning_rate": 8.806811715160484e-11,
|
785 |
+
"loss": 25.5922,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.34604872251931074,
|
790 |
+
"grad_norm": 126997.375,
|
791 |
+
"learning_rate": 8.648637703194516e-11,
|
792 |
+
"loss": 27.1782,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 0.34913844325609034,
|
797 |
+
"grad_norm": 111071.9921875,
|
798 |
+
"learning_rate": 8.490807351941753e-11,
|
799 |
+
"loss": 29.0618,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 0.3522281639928699,
|
804 |
+
"grad_norm": 109156.3125,
|
805 |
+
"learning_rate": 8.333360798744496e-11,
|
806 |
+
"loss": 31.8425,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.3553178847296494,
|
811 |
+
"grad_norm": 126704.4375,
|
812 |
+
"learning_rate": 8.17633808334256e-11,
|
813 |
+
"loss": 26.271,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 0.35840760546642897,
|
818 |
+
"grad_norm": 129102.53125,
|
819 |
+
"learning_rate": 8.019779137690906e-11,
|
820 |
+
"loss": 26.1617,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 0.36149732620320857,
|
825 |
+
"grad_norm": 116444.125,
|
826 |
+
"learning_rate": 7.863723775804651e-11,
|
827 |
+
"loss": 29.3636,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 0.3645870469399881,
|
832 |
+
"grad_norm": 119892.703125,
|
833 |
+
"learning_rate": 7.708211683634111e-11,
|
834 |
+
"loss": 28.351,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 0.36767676767676766,
|
839 |
+
"grad_norm": 133809.671875,
|
840 |
+
"learning_rate": 7.553282408972381e-11,
|
841 |
+
"loss": 25.5753,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.37076648841354726,
|
846 |
+
"grad_norm": 131220.359375,
|
847 |
+
"learning_rate": 7.398975351398053e-11,
|
848 |
+
"loss": 26.8812,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.3738562091503268,
|
853 |
+
"grad_norm": 116611.2734375,
|
854 |
+
"learning_rate": 7.245329752255648e-11,
|
855 |
+
"loss": 29.5172,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 0.37694592988710635,
|
860 |
+
"grad_norm": 133015.046875,
|
861 |
+
"learning_rate": 7.092384684676262e-11,
|
862 |
+
"loss": 25.8481,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 0.38003565062388595,
|
867 |
+
"grad_norm": 136814.09375,
|
868 |
+
"learning_rate": 6.940179043641005e-11,
|
869 |
+
"loss": 24.7821,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 0.3831253713606655,
|
874 |
+
"grad_norm": 111482.6875,
|
875 |
+
"learning_rate": 6.788751536089739e-11,
|
876 |
+
"loss": 28.6458,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 0.38621509209744503,
|
881 |
+
"grad_norm": 105425.6796875,
|
882 |
+
"learning_rate": 6.638140671077632e-11,
|
883 |
+
"loss": 30.565,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 0.3893048128342246,
|
888 |
+
"grad_norm": 126840.734375,
|
889 |
+
"learning_rate": 6.488384749982054e-11,
|
890 |
+
"loss": 24.9263,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.3923945335710042,
|
895 |
+
"grad_norm": 126449.0078125,
|
896 |
+
"learning_rate": 6.339521856762254e-11,
|
897 |
+
"loss": 27.0906,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.3954842543077837,
|
902 |
+
"grad_norm": 110226.4375,
|
903 |
+
"learning_rate": 6.191589848274368e-11,
|
904 |
+
"loss": 28.7828,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.39857397504456327,
|
909 |
+
"grad_norm": 117383.6171875,
|
910 |
+
"learning_rate": 6.04462634464415e-11,
|
911 |
+
"loss": 27.1669,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 0.40166369578134287,
|
916 |
+
"grad_norm": 129581.0390625,
|
917 |
+
"learning_rate": 5.898668719699914e-11,
|
918 |
+
"loss": 24.9744,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 0.4047534165181224,
|
923 |
+
"grad_norm": 126919.765625,
|
924 |
+
"learning_rate": 5.753754091468115e-11,
|
925 |
+
"loss": 26.5326,
|
926 |
+
"step": 131
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 0.40784313725490196,
|
930 |
+
"grad_norm": 126623.8046875,
|
931 |
+
"learning_rate": 5.6099193127339865e-11,
|
932 |
+
"loss": 28.2028,
|
933 |
+
"step": 132
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.4109328579916815,
|
937 |
+
"grad_norm": 128991.1171875,
|
938 |
+
"learning_rate": 5.467200961669618e-11,
|
939 |
+
"loss": 27.0198,
|
940 |
+
"step": 133
|
941 |
+
},
|
942 |
+
{
|
943 |
+
"epoch": 0.4140225787284611,
|
944 |
+
"grad_norm": 127212.984375,
|
945 |
+
"learning_rate": 5.325635332531864e-11,
|
946 |
+
"loss": 27.5968,
|
947 |
+
"step": 134
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.41711229946524064,
|
951 |
+
"grad_norm": 114877.2421875,
|
952 |
+
"learning_rate": 5.1852584264324866e-11,
|
953 |
+
"loss": 29.2745,
|
954 |
+
"step": 135
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.4202020202020202,
|
958 |
+
"grad_norm": 110463.8828125,
|
959 |
+
"learning_rate": 5.046105942182815e-11,
|
960 |
+
"loss": 28.0633,
|
961 |
+
"step": 136
|
962 |
+
},
|
963 |
+
{
|
964 |
+
"epoch": 0.4232917409387998,
|
965 |
+
"grad_norm": 124949.09375,
|
966 |
+
"learning_rate": 4.908213267215287e-11,
|
967 |
+
"loss": 27.0064,
|
968 |
+
"step": 137
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 0.42638146167557933,
|
972 |
+
"grad_norm": 137615.125,
|
973 |
+
"learning_rate": 4.771615468584194e-11,
|
974 |
+
"loss": 25.8549,
|
975 |
+
"step": 138
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.4294711824123589,
|
979 |
+
"grad_norm": 125163.0,
|
980 |
+
"learning_rate": 4.636347284047877e-11,
|
981 |
+
"loss": 28.2664,
|
982 |
+
"step": 139
|
983 |
+
},
|
984 |
+
{
|
985 |
+
"epoch": 0.4325609031491384,
|
986 |
+
"grad_norm": 120346.09375,
|
987 |
+
"learning_rate": 4.502443113234688e-11,
|
988 |
+
"loss": 27.093,
|
989 |
+
"step": 140
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 0.435650623885918,
|
993 |
+
"grad_norm": 130197.5234375,
|
994 |
+
"learning_rate": 4.3699370088949064e-11,
|
995 |
+
"loss": 25.7805,
|
996 |
+
"step": 141
|
997 |
+
},
|
998 |
+
{
|
999 |
+
"epoch": 0.43874034462269756,
|
1000 |
+
"grad_norm": 141218.203125,
|
1001 |
+
"learning_rate": 4.238862668240919e-11,
|
1002 |
+
"loss": 25.3932,
|
1003 |
+
"step": 142
|
1004 |
+
},
|
1005 |
+
{
|
1006 |
+
"epoch": 0.4418300653594771,
|
1007 |
+
"grad_norm": 124990.84375,
|
1008 |
+
"learning_rate": 4.1092534243777726e-11,
|
1009 |
+
"loss": 25.7902,
|
1010 |
+
"step": 143
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.4449197860962567,
|
1014 |
+
"grad_norm": 131223.625,
|
1015 |
+
"learning_rate": 3.981142237826332e-11,
|
1016 |
+
"loss": 25.7262,
|
1017 |
+
"step": 144
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.44800950683303625,
|
1021 |
+
"grad_norm": 119055.7109375,
|
1022 |
+
"learning_rate": 3.854561688141205e-11,
|
1023 |
+
"loss": 27.7554,
|
1024 |
+
"step": 145
|
1025 |
+
},
|
1026 |
+
{
|
1027 |
+
"epoch": 0.4510992275698158,
|
1028 |
+
"grad_norm": 127996.890625,
|
1029 |
+
"learning_rate": 3.729543965625526e-11,
|
1030 |
+
"loss": 25.1842,
|
1031 |
+
"step": 146
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 0.45418894830659534,
|
1035 |
+
"grad_norm": 130496.4609375,
|
1036 |
+
"learning_rate": 3.606120863144753e-11,
|
1037 |
+
"loss": 26.7469,
|
1038 |
+
"step": 147
|
1039 |
+
},
|
1040 |
+
{
|
1041 |
+
"epoch": 0.45727866904337494,
|
1042 |
+
"grad_norm": 138091.28125,
|
1043 |
+
"learning_rate": 3.484323768041515e-11,
|
1044 |
+
"loss": 24.2791,
|
1045 |
+
"step": 148
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 0.4603683897801545,
|
1049 |
+
"grad_norm": 114539.9140625,
|
1050 |
+
"learning_rate": 3.364183654153592e-11,
|
1051 |
+
"loss": 27.8677,
|
1052 |
+
"step": 149
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 0.46345811051693403,
|
1056 |
+
"grad_norm": 129665.9140625,
|
1057 |
+
"learning_rate": 3.245731073937068e-11,
|
1058 |
+
"loss": 26.8488,
|
1059 |
+
"step": 150
|
1060 |
+
}
|
1061 |
+
],
|
1062 |
+
"logging_steps": 1,
|
1063 |
+
"max_steps": 202,
|
1064 |
+
"num_input_tokens_seen": 0,
|
1065 |
+
"num_train_epochs": 1,
|
1066 |
+
"save_steps": 10,
|
1067 |
+
"stateful_callbacks": {
|
1068 |
+
"TrainerControl": {
|
1069 |
+
"args": {
|
1070 |
+
"should_epoch_stop": false,
|
1071 |
+
"should_evaluate": false,
|
1072 |
+
"should_log": false,
|
1073 |
+
"should_save": true,
|
1074 |
+
"should_training_stop": false
|
1075 |
+
},
|
1076 |
+
"attributes": {}
|
1077 |
+
}
|
1078 |
+
},
|
1079 |
+
"total_flos": 2.489068960874496e+17,
|
1080 |
+
"train_batch_size": 2,
|
1081 |
+
"trial_name": null,
|
1082 |
+
"trial_params": null
|
1083 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ae1cc95d5e39f5cb4178e50f71683ddd694fe8a84ac52421fb6ca6964b31bb4
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|