Upload 9 files
Browse files- config.json +32 -0
- model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- trainer_state.json +504 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./kcelectra-base",
|
3 |
+
"architectures": [
|
4 |
+
"ElectraForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 768,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "electra",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 3,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"problem_type": "single_label_classification",
|
22 |
+
"summary_activation": "gelu",
|
23 |
+
"summary_last_dropout": 0.1,
|
24 |
+
"summary_type": "first",
|
25 |
+
"summary_use_proj": true,
|
26 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
27 |
+
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.40.0.dev0",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 30000
|
32 |
+
}
|
model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c0dc13256fbd6e2149b13d3d8b3f7d01b6d314a000ba5acc251340254c0f568c
|
3 |
+
size 436383686
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2816ef23bed716419c3ec0799bb3820c72f9a3fd34d73fc776b8b493d916e669
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b3acb7811de5b0b1cb853812cb70bdfb1ff8ebffd91ce345ba622ba586815a8
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[UNK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[CLS]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[SEP]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[PAD]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": false,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": null,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,504 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 48.184357541899445,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 34500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.7,
|
13 |
+
"grad_norm": 4.0421319007873535,
|
14 |
+
"learning_rate": 1.9720670391061455e-05,
|
15 |
+
"loss": 0.408,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.4,
|
20 |
+
"grad_norm": 4.579340934753418,
|
21 |
+
"learning_rate": 1.9441340782122907e-05,
|
22 |
+
"loss": 0.303,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 2.09,
|
27 |
+
"grad_norm": 5.2814459800720215,
|
28 |
+
"learning_rate": 1.9162011173184357e-05,
|
29 |
+
"loss": 0.2487,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 2.79,
|
34 |
+
"grad_norm": 4.263625144958496,
|
35 |
+
"learning_rate": 1.888268156424581e-05,
|
36 |
+
"loss": 0.1642,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 3.49,
|
41 |
+
"grad_norm": 16.92409896850586,
|
42 |
+
"learning_rate": 1.8603351955307266e-05,
|
43 |
+
"loss": 0.1116,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 4.19,
|
48 |
+
"grad_norm": 0.10890375822782516,
|
49 |
+
"learning_rate": 1.8324022346368716e-05,
|
50 |
+
"loss": 0.0992,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 4.89,
|
55 |
+
"grad_norm": 4.843805313110352,
|
56 |
+
"learning_rate": 1.804469273743017e-05,
|
57 |
+
"loss": 0.0723,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 5.59,
|
62 |
+
"grad_norm": 0.6422103643417358,
|
63 |
+
"learning_rate": 1.776536312849162e-05,
|
64 |
+
"loss": 0.0543,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 6.28,
|
69 |
+
"grad_norm": 0.04145967587828636,
|
70 |
+
"learning_rate": 1.7486033519553075e-05,
|
71 |
+
"loss": 0.0479,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 6.98,
|
76 |
+
"grad_norm": 0.18585649132728577,
|
77 |
+
"learning_rate": 1.7206703910614527e-05,
|
78 |
+
"loss": 0.0472,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 7.68,
|
83 |
+
"grad_norm": 1.1734449863433838,
|
84 |
+
"learning_rate": 1.6927374301675977e-05,
|
85 |
+
"loss": 0.037,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 8.38,
|
90 |
+
"grad_norm": 5.980381965637207,
|
91 |
+
"learning_rate": 1.664804469273743e-05,
|
92 |
+
"loss": 0.0352,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 9.08,
|
97 |
+
"grad_norm": 0.02630673162639141,
|
98 |
+
"learning_rate": 1.6368715083798886e-05,
|
99 |
+
"loss": 0.031,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 9.78,
|
104 |
+
"grad_norm": 0.34635427594184875,
|
105 |
+
"learning_rate": 1.6089385474860336e-05,
|
106 |
+
"loss": 0.0249,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 10.47,
|
111 |
+
"grad_norm": 0.038617122918367386,
|
112 |
+
"learning_rate": 1.581005586592179e-05,
|
113 |
+
"loss": 0.0236,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 11.17,
|
118 |
+
"grad_norm": 0.011197003535926342,
|
119 |
+
"learning_rate": 1.553072625698324e-05,
|
120 |
+
"loss": 0.024,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 11.87,
|
125 |
+
"grad_norm": 0.04000287503004074,
|
126 |
+
"learning_rate": 1.5251396648044694e-05,
|
127 |
+
"loss": 0.0257,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 12.57,
|
132 |
+
"grad_norm": 0.01364846620708704,
|
133 |
+
"learning_rate": 1.4972067039106146e-05,
|
134 |
+
"loss": 0.0185,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 13.27,
|
139 |
+
"grad_norm": 0.030796006321907043,
|
140 |
+
"learning_rate": 1.4692737430167599e-05,
|
141 |
+
"loss": 0.0193,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 13.97,
|
146 |
+
"grad_norm": 0.008376175537705421,
|
147 |
+
"learning_rate": 1.4413407821229052e-05,
|
148 |
+
"loss": 0.0177,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 14.66,
|
153 |
+
"grad_norm": 0.004392937291413546,
|
154 |
+
"learning_rate": 1.4134078212290503e-05,
|
155 |
+
"loss": 0.0127,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 15.36,
|
160 |
+
"grad_norm": 0.0029910472221672535,
|
161 |
+
"learning_rate": 1.3854748603351957e-05,
|
162 |
+
"loss": 0.014,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 16.06,
|
167 |
+
"grad_norm": 0.0029884399846196175,
|
168 |
+
"learning_rate": 1.357541899441341e-05,
|
169 |
+
"loss": 0.0156,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 16.76,
|
174 |
+
"grad_norm": 7.065054416656494,
|
175 |
+
"learning_rate": 1.3296089385474861e-05,
|
176 |
+
"loss": 0.0132,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 17.46,
|
181 |
+
"grad_norm": 0.002008031355217099,
|
182 |
+
"learning_rate": 1.3016759776536314e-05,
|
183 |
+
"loss": 0.0105,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 18.16,
|
188 |
+
"grad_norm": 0.004853041376918554,
|
189 |
+
"learning_rate": 1.2737430167597766e-05,
|
190 |
+
"loss": 0.0091,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 18.85,
|
195 |
+
"grad_norm": 0.009278771467506886,
|
196 |
+
"learning_rate": 1.2458100558659219e-05,
|
197 |
+
"loss": 0.0144,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 19.55,
|
202 |
+
"grad_norm": 0.002231143182143569,
|
203 |
+
"learning_rate": 1.2178770949720671e-05,
|
204 |
+
"loss": 0.0099,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 20.25,
|
209 |
+
"grad_norm": 0.003844016930088401,
|
210 |
+
"learning_rate": 1.1899441340782123e-05,
|
211 |
+
"loss": 0.0132,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 20.95,
|
216 |
+
"grad_norm": 0.0021888066548854113,
|
217 |
+
"learning_rate": 1.1620111731843577e-05,
|
218 |
+
"loss": 0.0126,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 21.65,
|
223 |
+
"grad_norm": 16.925048828125,
|
224 |
+
"learning_rate": 1.134078212290503e-05,
|
225 |
+
"loss": 0.0077,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 22.35,
|
230 |
+
"grad_norm": 0.0013325487961992621,
|
231 |
+
"learning_rate": 1.1061452513966481e-05,
|
232 |
+
"loss": 0.0108,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 23.04,
|
237 |
+
"grad_norm": 0.0013474252773448825,
|
238 |
+
"learning_rate": 1.0782122905027934e-05,
|
239 |
+
"loss": 0.0078,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 23.74,
|
244 |
+
"grad_norm": 0.0014491812326014042,
|
245 |
+
"learning_rate": 1.0502793296089386e-05,
|
246 |
+
"loss": 0.0048,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 24.44,
|
251 |
+
"grad_norm": 0.0027435130905359983,
|
252 |
+
"learning_rate": 1.0223463687150838e-05,
|
253 |
+
"loss": 0.0072,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 25.14,
|
258 |
+
"grad_norm": 0.06291136890649796,
|
259 |
+
"learning_rate": 9.944134078212291e-06,
|
260 |
+
"loss": 0.008,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 25.84,
|
265 |
+
"grad_norm": 0.021899724379181862,
|
266 |
+
"learning_rate": 9.664804469273744e-06,
|
267 |
+
"loss": 0.0087,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 26.54,
|
272 |
+
"grad_norm": 15.27237319946289,
|
273 |
+
"learning_rate": 9.385474860335197e-06,
|
274 |
+
"loss": 0.0052,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 27.23,
|
279 |
+
"grad_norm": 0.009569833986461163,
|
280 |
+
"learning_rate": 9.106145251396648e-06,
|
281 |
+
"loss": 0.0073,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 27.93,
|
286 |
+
"grad_norm": 0.0003999493783339858,
|
287 |
+
"learning_rate": 8.826815642458101e-06,
|
288 |
+
"loss": 0.0048,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 28.63,
|
293 |
+
"grad_norm": 0.0033733926247805357,
|
294 |
+
"learning_rate": 8.547486033519554e-06,
|
295 |
+
"loss": 0.0056,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 29.33,
|
300 |
+
"grad_norm": 0.04343196749687195,
|
301 |
+
"learning_rate": 8.268156424581007e-06,
|
302 |
+
"loss": 0.0056,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 30.03,
|
307 |
+
"grad_norm": 0.0003582398348953575,
|
308 |
+
"learning_rate": 7.988826815642458e-06,
|
309 |
+
"loss": 0.0031,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 30.73,
|
314 |
+
"grad_norm": 0.00021692673908546567,
|
315 |
+
"learning_rate": 7.709497206703911e-06,
|
316 |
+
"loss": 0.0035,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 31.42,
|
321 |
+
"grad_norm": 0.00029874147730879486,
|
322 |
+
"learning_rate": 7.430167597765364e-06,
|
323 |
+
"loss": 0.0026,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 32.12,
|
328 |
+
"grad_norm": 0.0002098192780977115,
|
329 |
+
"learning_rate": 7.150837988826816e-06,
|
330 |
+
"loss": 0.0048,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 32.82,
|
335 |
+
"grad_norm": 0.010424572043120861,
|
336 |
+
"learning_rate": 6.871508379888268e-06,
|
337 |
+
"loss": 0.0054,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 33.52,
|
342 |
+
"grad_norm": 0.1450434923171997,
|
343 |
+
"learning_rate": 6.592178770949721e-06,
|
344 |
+
"loss": 0.0031,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 34.22,
|
349 |
+
"grad_norm": 0.0003349222242832184,
|
350 |
+
"learning_rate": 6.312849162011173e-06,
|
351 |
+
"loss": 0.0029,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 34.92,
|
356 |
+
"grad_norm": 0.0007802957552485168,
|
357 |
+
"learning_rate": 6.033519553072626e-06,
|
358 |
+
"loss": 0.0023,
|
359 |
+
"step": 25000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 35.61,
|
363 |
+
"grad_norm": 0.0005215730634517968,
|
364 |
+
"learning_rate": 5.754189944134078e-06,
|
365 |
+
"loss": 0.0021,
|
366 |
+
"step": 25500
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 36.31,
|
370 |
+
"grad_norm": 0.00011289090616628528,
|
371 |
+
"learning_rate": 5.474860335195531e-06,
|
372 |
+
"loss": 0.0026,
|
373 |
+
"step": 26000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 37.01,
|
377 |
+
"grad_norm": 0.013641629368066788,
|
378 |
+
"learning_rate": 5.195530726256983e-06,
|
379 |
+
"loss": 0.0032,
|
380 |
+
"step": 26500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 37.71,
|
384 |
+
"grad_norm": 0.0002486356534063816,
|
385 |
+
"learning_rate": 4.916201117318436e-06,
|
386 |
+
"loss": 0.002,
|
387 |
+
"step": 27000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 38.41,
|
391 |
+
"grad_norm": 9.347203013021499e-05,
|
392 |
+
"learning_rate": 4.636871508379888e-06,
|
393 |
+
"loss": 0.0012,
|
394 |
+
"step": 27500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 39.11,
|
398 |
+
"grad_norm": 0.00012943429464939982,
|
399 |
+
"learning_rate": 4.357541899441341e-06,
|
400 |
+
"loss": 0.0026,
|
401 |
+
"step": 28000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 39.8,
|
405 |
+
"grad_norm": 0.001636040979065001,
|
406 |
+
"learning_rate": 4.078212290502794e-06,
|
407 |
+
"loss": 0.0021,
|
408 |
+
"step": 28500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 40.5,
|
412 |
+
"grad_norm": 0.009456774219870567,
|
413 |
+
"learning_rate": 3.798882681564246e-06,
|
414 |
+
"loss": 0.0016,
|
415 |
+
"step": 29000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 41.2,
|
419 |
+
"grad_norm": 0.000818349071778357,
|
420 |
+
"learning_rate": 3.5195530726256988e-06,
|
421 |
+
"loss": 0.0011,
|
422 |
+
"step": 29500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 41.9,
|
426 |
+
"grad_norm": 6.146980012999848e-05,
|
427 |
+
"learning_rate": 3.240223463687151e-06,
|
428 |
+
"loss": 0.0016,
|
429 |
+
"step": 30000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 42.6,
|
433 |
+
"grad_norm": 4.060289211338386e-05,
|
434 |
+
"learning_rate": 2.9608938547486037e-06,
|
435 |
+
"loss": 0.0007,
|
436 |
+
"step": 30500
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 43.3,
|
440 |
+
"grad_norm": 0.00016211264301091433,
|
441 |
+
"learning_rate": 2.6815642458100562e-06,
|
442 |
+
"loss": 0.0032,
|
443 |
+
"step": 31000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 43.99,
|
447 |
+
"grad_norm": 0.0002249513054266572,
|
448 |
+
"learning_rate": 2.4022346368715087e-06,
|
449 |
+
"loss": 0.0011,
|
450 |
+
"step": 31500
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 44.69,
|
454 |
+
"grad_norm": 0.00012292143946979195,
|
455 |
+
"learning_rate": 2.1229050279329612e-06,
|
456 |
+
"loss": 0.0006,
|
457 |
+
"step": 32000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 45.39,
|
461 |
+
"grad_norm": 5.348429112927988e-05,
|
462 |
+
"learning_rate": 1.8435754189944135e-06,
|
463 |
+
"loss": 0.0007,
|
464 |
+
"step": 32500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 46.09,
|
468 |
+
"grad_norm": 5.2925995987607166e-05,
|
469 |
+
"learning_rate": 1.564245810055866e-06,
|
470 |
+
"loss": 0.0021,
|
471 |
+
"step": 33000
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 46.79,
|
475 |
+
"grad_norm": 6.103613850427791e-05,
|
476 |
+
"learning_rate": 1.2849162011173185e-06,
|
477 |
+
"loss": 0.0009,
|
478 |
+
"step": 33500
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 47.49,
|
482 |
+
"grad_norm": 0.0004408392414916307,
|
483 |
+
"learning_rate": 1.005586592178771e-06,
|
484 |
+
"loss": 0.0013,
|
485 |
+
"step": 34000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 48.18,
|
489 |
+
"grad_norm": 0.0011864238185808063,
|
490 |
+
"learning_rate": 7.262569832402236e-07,
|
491 |
+
"loss": 0.0013,
|
492 |
+
"step": 34500
|
493 |
+
}
|
494 |
+
],
|
495 |
+
"logging_steps": 500,
|
496 |
+
"max_steps": 35800,
|
497 |
+
"num_input_tokens_seen": 0,
|
498 |
+
"num_train_epochs": 50,
|
499 |
+
"save_steps": 500,
|
500 |
+
"total_flos": 2.970794017734924e+16,
|
501 |
+
"train_batch_size": 32,
|
502 |
+
"trial_name": null,
|
503 |
+
"trial_params": null
|
504 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|