manbeast3b
commited on
Commit
•
cf80632
1
Parent(s):
2a86304
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 +453 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "TapiwaWorknesh/sccc-19",
|
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:ed3cb2f2fbd122c8f9e8d34902184fff72ebd98077e9e18fbf8849a799dd68a7
|
3 |
+
size 4984037184
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9fbdab73662bbe9d6594e4749432c8ab196571749b4f32eb7634470ef0a821ca
|
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 sha256:18b8d90e3e0e8758764f312147cb8619e101319fb089d3674ef330efebb0916e
|
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 sha256:6b831d235758fda0ce9d75eb43df0f5131f7cab9ca58408d44ec73d9436751bb
|
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 +1,453 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.18538324420677363,
|
5 |
+
"eval_steps": 72,
|
6 |
+
"global_step": 60,
|
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": 121222.5390625,
|
14 |
+
"learning_rate": 4.0000000000000007e-10,
|
15 |
+
"loss": 28.6291,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.006179441473559121,
|
20 |
+
"grad_norm": 118161.796875,
|
21 |
+
"learning_rate": 8.000000000000001e-10,
|
22 |
+
"loss": 28.0625,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.009269162210338681,
|
27 |
+
"grad_norm": 125806.6796875,
|
28 |
+
"learning_rate": 1.2e-09,
|
29 |
+
"loss": 27.2823,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.012358882947118241,
|
34 |
+
"grad_norm": 112738.1484375,
|
35 |
+
"learning_rate": 1.6000000000000003e-09,
|
36 |
+
"loss": 29.0227,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.015448603683897801,
|
41 |
+
"grad_norm": 121833.5390625,
|
42 |
+
"learning_rate": 2e-09,
|
43 |
+
"loss": 27.4845,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.018538324420677363,
|
48 |
+
"grad_norm": 122112.65625,
|
49 |
+
"learning_rate": 1.9989008914857113e-09,
|
50 |
+
"loss": 26.6542,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.02162804515745692,
|
55 |
+
"grad_norm": 122619.7265625,
|
56 |
+
"learning_rate": 1.995605982021898e-09,
|
57 |
+
"loss": 27.3283,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.024717765894236483,
|
62 |
+
"grad_norm": 124364.53125,
|
63 |
+
"learning_rate": 1.990122514534651e-09,
|
64 |
+
"loss": 26.9111,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.027807486631016044,
|
69 |
+
"grad_norm": 123087.8671875,
|
70 |
+
"learning_rate": 1.9824625428755763e-09,
|
71 |
+
"loss": 26.6357,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.030897207367795602,
|
76 |
+
"grad_norm": 136198.734375,
|
77 |
+
"learning_rate": 1.972642905324813e-09,
|
78 |
+
"loss": 23.6223,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.03398692810457516,
|
83 |
+
"grad_norm": 123133.7578125,
|
84 |
+
"learning_rate": 1.9606851875768402e-09,
|
85 |
+
"loss": 25.9946,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.037076648841354726,
|
90 |
+
"grad_norm": 103042.3515625,
|
91 |
+
"learning_rate": 1.946615675290434e-09,
|
92 |
+
"loss": 30.1162,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.040166369578134284,
|
97 |
+
"grad_norm": 131866.765625,
|
98 |
+
"learning_rate": 1.930465296307087e-09,
|
99 |
+
"loss": 25.6211,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.04325609031491384,
|
104 |
+
"grad_norm": 122014.0625,
|
105 |
+
"learning_rate": 1.9122695526648967e-09,
|
106 |
+
"loss": 26.5086,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.04634581105169341,
|
111 |
+
"grad_norm": 124875.875,
|
112 |
+
"learning_rate": 1.8920684425573866e-09,
|
113 |
+
"loss": 27.6806,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.049435531788472965,
|
118 |
+
"grad_norm": 130853.09375,
|
119 |
+
"learning_rate": 1.8699063724087904e-09,
|
120 |
+
"loss": 25.0591,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.052525252525252523,
|
125 |
+
"grad_norm": 134673.421875,
|
126 |
+
"learning_rate": 1.8458320592590975e-09,
|
127 |
+
"loss": 25.3938,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.05561497326203209,
|
132 |
+
"grad_norm": 112125.9765625,
|
133 |
+
"learning_rate": 1.8198984236734246e-09,
|
134 |
+
"loss": 28.5848,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.05870469399881165,
|
139 |
+
"grad_norm": 123824.6875,
|
140 |
+
"learning_rate": 1.7921624734111293e-09,
|
141 |
+
"loss": 27.1392,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.061794414735591205,
|
146 |
+
"grad_norm": 125568.03125,
|
147 |
+
"learning_rate": 1.7626851781103819e-09,
|
148 |
+
"loss": 25.654,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.06488413547237076,
|
153 |
+
"grad_norm": 120140.71875,
|
154 |
+
"learning_rate": 1.7315313352636692e-09,
|
155 |
+
"loss": 27.8295,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.06797385620915032,
|
160 |
+
"grad_norm": 125886.3203125,
|
161 |
+
"learning_rate": 1.6987694277788419e-09,
|
162 |
+
"loss": 26.6647,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.0710635769459299,
|
167 |
+
"grad_norm": 119238.578125,
|
168 |
+
"learning_rate": 1.664471473438822e-09,
|
169 |
+
"loss": 26.6455,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.07415329768270945,
|
174 |
+
"grad_norm": 117924.9921875,
|
175 |
+
"learning_rate": 1.6287128665908851e-09,
|
176 |
+
"loss": 26.5597,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.07724301841948901,
|
181 |
+
"grad_norm": 131537.625,
|
182 |
+
"learning_rate": 1.5915722124135226e-09,
|
183 |
+
"loss": 26.2297,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.08033273915626857,
|
188 |
+
"grad_norm": 129350.40625,
|
189 |
+
"learning_rate": 1.5531311541251995e-09,
|
190 |
+
"loss": 27.3055,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.08342245989304813,
|
195 |
+
"grad_norm": 121738.21875,
|
196 |
+
"learning_rate": 1.513474193514842e-09,
|
197 |
+
"loss": 26.4486,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.08651218062982768,
|
202 |
+
"grad_norm": 122703.90625,
|
203 |
+
"learning_rate": 1.4726885051885652e-09,
|
204 |
+
"loss": 27.6315,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.08960190136660724,
|
209 |
+
"grad_norm": 120508.328125,
|
210 |
+
"learning_rate": 1.4308637449409705e-09,
|
211 |
+
"loss": 26.4159,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.09269162210338681,
|
216 |
+
"grad_norm": 116380.859375,
|
217 |
+
"learning_rate": 1.3880918526722497e-09,
|
218 |
+
"loss": 28.3796,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.09578134284016637,
|
223 |
+
"grad_norm": 126698.1796875,
|
224 |
+
"learning_rate": 1.344466850284333e-09,
|
225 |
+
"loss": 27.0027,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.09887106357694593,
|
230 |
+
"grad_norm": 128378.515625,
|
231 |
+
"learning_rate": 1.3000846350003408e-09,
|
232 |
+
"loss": 25.3418,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.10196078431372549,
|
237 |
+
"grad_norm": 116183.1796875,
|
238 |
+
"learning_rate": 1.2550427685616766e-09,
|
239 |
+
"loss": 29.4539,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.10505050505050505,
|
244 |
+
"grad_norm": 119771.0625,
|
245 |
+
"learning_rate": 1.2094402627661447e-09,
|
246 |
+
"loss": 26.9952,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.1081402257872846,
|
251 |
+
"grad_norm": 117849.8515625,
|
252 |
+
"learning_rate": 1.16337736181853e-09,
|
253 |
+
"loss": 28.5859,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.11122994652406418,
|
258 |
+
"grad_norm": 121979.3359375,
|
259 |
+
"learning_rate": 1.1169553219720828e-09,
|
260 |
+
"loss": 28.5073,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.11431966726084374,
|
265 |
+
"grad_norm": 125324.3984375,
|
266 |
+
"learning_rate": 1.070276188945293e-09,
|
267 |
+
"loss": 26.0588,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.1174093879976233,
|
272 |
+
"grad_norm": 131353.421875,
|
273 |
+
"learning_rate": 1.0234425736032608e-09,
|
274 |
+
"loss": 24.2387,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.12049910873440285,
|
279 |
+
"grad_norm": 120623.5,
|
280 |
+
"learning_rate": 9.765574263967397e-10,
|
281 |
+
"loss": 27.3392,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.12358882947118241,
|
286 |
+
"grad_norm": 117227.8515625,
|
287 |
+
"learning_rate": 9.297238110547074e-10,
|
288 |
+
"loss": 28.0838,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.12667855020796198,
|
293 |
+
"grad_norm": 119083.9375,
|
294 |
+
"learning_rate": 8.830446780279176e-10,
|
295 |
+
"loss": 27.8417,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.12976827094474153,
|
300 |
+
"grad_norm": 139472.0625,
|
301 |
+
"learning_rate": 8.366226381814697e-10,
|
302 |
+
"loss": 25.6301,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.1328579916815211,
|
307 |
+
"grad_norm": 110898.171875,
|
308 |
+
"learning_rate": 7.905597372338558e-10,
|
309 |
+
"loss": 27.9009,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.13594771241830064,
|
314 |
+
"grad_norm": 121771.7265625,
|
315 |
+
"learning_rate": 7.449572314383236e-10,
|
316 |
+
"loss": 26.8833,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.13903743315508021,
|
321 |
+
"grad_norm": 123917.234375,
|
322 |
+
"learning_rate": 6.999153649996595e-10,
|
323 |
+
"loss": 25.6374,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.1421271538918598,
|
328 |
+
"grad_norm": 121639.7421875,
|
329 |
+
"learning_rate": 6.555331497156672e-10,
|
330 |
+
"loss": 25.5364,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.14521687462863933,
|
335 |
+
"grad_norm": 116252.3828125,
|
336 |
+
"learning_rate": 6.119081473277502e-10,
|
337 |
+
"loss": 28.6826,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.1483065953654189,
|
342 |
+
"grad_norm": 116441.125,
|
343 |
+
"learning_rate": 5.691362550590297e-10,
|
344 |
+
"loss": 28.0026,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.15139631610219845,
|
349 |
+
"grad_norm": 125541.921875,
|
350 |
+
"learning_rate": 5.273114948114346e-10,
|
351 |
+
"loss": 24.9752,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.15448603683897802,
|
356 |
+
"grad_norm": 114526.9609375,
|
357 |
+
"learning_rate": 4.865258064851579e-10,
|
358 |
+
"loss": 27.5153,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.15757575757575756,
|
363 |
+
"grad_norm": 118780.75,
|
364 |
+
"learning_rate": 4.4686884587480063e-10,
|
365 |
+
"loss": 27.9096,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.16066547831253714,
|
370 |
+
"grad_norm": 108833.6875,
|
371 |
+
"learning_rate": 4.084277875864776e-10,
|
372 |
+
"loss": 28.2642,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.1637551990493167,
|
377 |
+
"grad_norm": 124329.8984375,
|
378 |
+
"learning_rate": 3.7128713340911535e-10,
|
379 |
+
"loss": 26.1074,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.16684491978609625,
|
384 |
+
"grad_norm": 136048.546875,
|
385 |
+
"learning_rate": 3.3552852656117837e-10,
|
386 |
+
"loss": 23.3226,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.16993464052287582,
|
391 |
+
"grad_norm": 124232.1796875,
|
392 |
+
"learning_rate": 3.0123057222115837e-10,
|
393 |
+
"loss": 26.2317,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.17302436125965537,
|
398 |
+
"grad_norm": 112182.0390625,
|
399 |
+
"learning_rate": 2.6846866473633127e-10,
|
400 |
+
"loss": 27.8249,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.17611408199643494,
|
405 |
+
"grad_norm": 123877.953125,
|
406 |
+
"learning_rate": 2.3731482188961816e-10,
|
407 |
+
"loss": 27.2162,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.17920380273321448,
|
412 |
+
"grad_norm": 118916.7421875,
|
413 |
+
"learning_rate": 2.078375265888707e-10,
|
414 |
+
"loss": 25.814,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.18229352346999406,
|
419 |
+
"grad_norm": 140265.84375,
|
420 |
+
"learning_rate": 1.8010157632657544e-10,
|
421 |
+
"loss": 23.8831,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.18538324420677363,
|
426 |
+
"grad_norm": 126473.171875,
|
427 |
+
"learning_rate": 1.5416794074090257e-10,
|
428 |
+
"loss": 24.0671,
|
429 |
+
"step": 60
|
430 |
+
}
|
431 |
+
],
|
432 |
+
"logging_steps": 1,
|
433 |
+
"max_steps": 72,
|
434 |
+
"num_input_tokens_seen": 0,
|
435 |
+
"num_train_epochs": 1,
|
436 |
+
"save_steps": 10,
|
437 |
+
"stateful_callbacks": {
|
438 |
+
"TrainerControl": {
|
439 |
+
"args": {
|
440 |
+
"should_epoch_stop": false,
|
441 |
+
"should_evaluate": false,
|
442 |
+
"should_log": false,
|
443 |
+
"should_save": true,
|
444 |
+
"should_training_stop": false
|
445 |
+
},
|
446 |
+
"attributes": {}
|
447 |
+
}
|
448 |
+
},
|
449 |
+
"total_flos": 9.956275843497984e+16,
|
450 |
+
"train_batch_size": 2,
|
451 |
+
"trial_name": null,
|
452 |
+
"trial_params": null
|
453 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70b980a69146a534041ccc2adffdc8d300c1e69b96d134a0928a3468a04801bc
|
3 |
+
size 5240
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|