Training in progress, step 500
Browse files- model.safetensors +1 -1
- run-3/checkpoint-6500/config.json +26 -0
- run-3/checkpoint-6500/model.safetensors +3 -0
- run-3/checkpoint-6500/optimizer.pt +3 -0
- run-3/checkpoint-6500/rng_state.pth +3 -0
- run-3/checkpoint-6500/scheduler.pt +3 -0
- run-3/checkpoint-6500/special_tokens_map.json +7 -0
- run-3/checkpoint-6500/tokenizer.json +0 -0
- run-3/checkpoint-6500/tokenizer_config.json +55 -0
- run-3/checkpoint-6500/trainer_state.json +187 -0
- run-3/checkpoint-6500/training_args.bin +3 -0
- run-3/checkpoint-6500/vocab.txt +0 -0
- run-3/checkpoint-7000/config.json +26 -0
- run-3/checkpoint-7000/model.safetensors +3 -0
- run-3/checkpoint-7000/optimizer.pt +3 -0
- run-3/checkpoint-7000/rng_state.pth +3 -0
- run-3/checkpoint-7000/scheduler.pt +3 -0
- run-3/checkpoint-7000/special_tokens_map.json +7 -0
- run-3/checkpoint-7000/tokenizer.json +0 -0
- run-3/checkpoint-7000/tokenizer_config.json +55 -0
- run-3/checkpoint-7000/trainer_state.json +203 -0
- run-3/checkpoint-7000/training_args.bin +3 -0
- run-3/checkpoint-7000/vocab.txt +0 -0
- run-4/checkpoint-500/config.json +26 -0
- run-4/checkpoint-500/model.safetensors +3 -0
- run-4/checkpoint-500/optimizer.pt +3 -0
- run-4/checkpoint-500/rng_state.pth +3 -0
- run-4/checkpoint-500/scheduler.pt +3 -0
- run-4/checkpoint-500/special_tokens_map.json +7 -0
- run-4/checkpoint-500/tokenizer.json +0 -0
- run-4/checkpoint-500/tokenizer_config.json +55 -0
- run-4/checkpoint-500/trainer_state.json +31 -0
- run-4/checkpoint-500/training_args.bin +3 -0
- run-4/checkpoint-500/vocab.txt +0 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1340618660
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc6d5d7b39b3893580c52210ee5a58e9a8c2eccf9e6ffe2680b58d66f2c31759
|
3 |
size 1340618660
|
run-3/checkpoint-6500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-3/checkpoint-6500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779d76a7351ed49d9710e3de95ec453194f02dc7db7f4edc81bf283c15d3a215
|
3 |
+
size 1340618660
|
run-3/checkpoint-6500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c21194ed1e86d8c7d40561c63a042b5a4f6cde63c97d6191aae6c85741cd810
|
3 |
+
size 2681472237
|
run-3/checkpoint-6500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1f6d894359f3e2243c392a48bf280d75a9d7da29d55346796c8f588e0ed80ca
|
3 |
+
size 14244
|
run-3/checkpoint-6500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5fdc83b1c93d155696db5333a2d2f4184e90feceac9ae6889f1604a1d4f122e
|
3 |
+
size 1064
|
run-3/checkpoint-6500/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-3/checkpoint-6500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-6500/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-3/checkpoint-6500/trainer_state.json
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.71313672922252,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6500,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 1.8121609687805176,
|
14 |
+
"learning_rate": 4.400558387583305e-05,
|
15 |
+
"loss": 0.6264,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.5072075128555298,
|
21 |
+
"eval_loss": 0.6931472420692444,
|
22 |
+
"eval_runtime": 9.1548,
|
23 |
+
"eval_samples_per_second": 325.839,
|
24 |
+
"eval_steps_per_second": 20.426,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 1.8386740684509277,
|
30 |
+
"learning_rate": 4.0844263195097915e-05,
|
31 |
+
"loss": 0.7039,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.49882668256759644,
|
37 |
+
"eval_loss": 0.6931472420692444,
|
38 |
+
"eval_runtime": 9.1028,
|
39 |
+
"eval_samples_per_second": 327.702,
|
40 |
+
"eval_steps_per_second": 20.543,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 1.775593876838684,
|
46 |
+
"learning_rate": 3.768294251436278e-05,
|
47 |
+
"loss": 0.7008,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.680965147453083,
|
52 |
+
"grad_norm": 1.6979082822799683,
|
53 |
+
"learning_rate": 3.452162183362765e-05,
|
54 |
+
"loss": 0.7034,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.5015085339546204,
|
60 |
+
"eval_loss": 0.6931472420692444,
|
61 |
+
"eval_runtime": 9.1903,
|
62 |
+
"eval_samples_per_second": 324.583,
|
63 |
+
"eval_steps_per_second": 20.348,
|
64 |
+
"step": 2238
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.351206434316354,
|
68 |
+
"grad_norm": 1.7350631952285767,
|
69 |
+
"learning_rate": 3.136030115289252e-05,
|
70 |
+
"loss": 0.7017,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.5065370202064514,
|
76 |
+
"eval_loss": 0.6931472420692444,
|
77 |
+
"eval_runtime": 9.2185,
|
78 |
+
"eval_samples_per_second": 323.589,
|
79 |
+
"eval_steps_per_second": 20.285,
|
80 |
+
"step": 2984
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.021447721179625,
|
84 |
+
"grad_norm": 1.841038465499878,
|
85 |
+
"learning_rate": 2.8198980472157382e-05,
|
86 |
+
"loss": 0.7019,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.6916890080428955,
|
91 |
+
"grad_norm": 1.6272307634353638,
|
92 |
+
"learning_rate": 2.5037659791422253e-05,
|
93 |
+
"loss": 0.6994,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.5095541477203369,
|
99 |
+
"eval_loss": 0.6931472420692444,
|
100 |
+
"eval_runtime": 9.0976,
|
101 |
+
"eval_samples_per_second": 327.89,
|
102 |
+
"eval_steps_per_second": 20.555,
|
103 |
+
"step": 3730
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.361930294906166,
|
107 |
+
"grad_norm": 1.7355244159698486,
|
108 |
+
"learning_rate": 2.1876339110687117e-05,
|
109 |
+
"loss": 0.7006,
|
110 |
+
"step": 4000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.0,
|
114 |
+
"eval_accuracy": 0.49446865916252136,
|
115 |
+
"eval_loss": 0.6931472420692444,
|
116 |
+
"eval_runtime": 9.0977,
|
117 |
+
"eval_samples_per_second": 327.885,
|
118 |
+
"eval_steps_per_second": 20.555,
|
119 |
+
"step": 4476
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 6.032171581769437,
|
123 |
+
"grad_norm": 1.6792231798171997,
|
124 |
+
"learning_rate": 1.8715018429951985e-05,
|
125 |
+
"loss": 0.7005,
|
126 |
+
"step": 4500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.702412868632708,
|
130 |
+
"grad_norm": 1.7535431385040283,
|
131 |
+
"learning_rate": 1.5553697749216852e-05,
|
132 |
+
"loss": 0.701,
|
133 |
+
"step": 5000
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 7.0,
|
137 |
+
"eval_accuracy": 0.4941334128379822,
|
138 |
+
"eval_loss": 0.6931472420692444,
|
139 |
+
"eval_runtime": 9.0431,
|
140 |
+
"eval_samples_per_second": 329.865,
|
141 |
+
"eval_steps_per_second": 20.679,
|
142 |
+
"step": 5222
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 7.372654155495979,
|
146 |
+
"grad_norm": 1.7443852424621582,
|
147 |
+
"learning_rate": 1.239237706848172e-05,
|
148 |
+
"loss": 0.7015,
|
149 |
+
"step": 5500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.5122359991073608,
|
154 |
+
"eval_loss": 0.6931472420692444,
|
155 |
+
"eval_runtime": 9.0713,
|
156 |
+
"eval_samples_per_second": 328.839,
|
157 |
+
"eval_steps_per_second": 20.614,
|
158 |
+
"step": 5968
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 8.04289544235925,
|
162 |
+
"grad_norm": 1.6793931722640991,
|
163 |
+
"learning_rate": 9.231056387746587e-06,
|
164 |
+
"loss": 0.7003,
|
165 |
+
"step": 6000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 8.71313672922252,
|
169 |
+
"grad_norm": 1.6744327545166016,
|
170 |
+
"learning_rate": 6.069735707011455e-06,
|
171 |
+
"loss": 0.7013,
|
172 |
+
"step": 6500
|
173 |
+
}
|
174 |
+
],
|
175 |
+
"logging_steps": 500,
|
176 |
+
"max_steps": 7460,
|
177 |
+
"num_input_tokens_seen": 0,
|
178 |
+
"num_train_epochs": 10,
|
179 |
+
"save_steps": 500,
|
180 |
+
"total_flos": 1.6928810928603216e+16,
|
181 |
+
"train_batch_size": 16,
|
182 |
+
"trial_name": null,
|
183 |
+
"trial_params": {
|
184 |
+
"learning_rate": 4.716690455656818e-05,
|
185 |
+
"per_device_train_batch_size": 16
|
186 |
+
}
|
187 |
+
}
|
run-3/checkpoint-6500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
|
3 |
+
size 5048
|
run-3/checkpoint-6500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-7000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-3/checkpoint-7000/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5622888e4da207e8221644fc21e881b36138ec5e66d9c5318d19d01952d0c0d1
|
3 |
+
size 1340618660
|
run-3/checkpoint-7000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75649bffb1f758a7fa235c024c117141af4463e7393ee5191e97ccfdd673888d
|
3 |
+
size 2681472237
|
run-3/checkpoint-7000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e8822b3ce842a84ff93b4e9e34c5d6cc8389740adb793137e0de79524460bc4
|
3 |
+
size 14244
|
run-3/checkpoint-7000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16a85109ecbb42b33fadd83997c2c55c973870d2e174c1f78f3d45c11656d3e5
|
3 |
+
size 1064
|
run-3/checkpoint-7000/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-3/checkpoint-7000/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-3/checkpoint-7000/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-3/checkpoint-7000/trainer_state.json
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.383378016085791,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7000,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 1.8121609687805176,
|
14 |
+
"learning_rate": 4.400558387583305e-05,
|
15 |
+
"loss": 0.6264,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.5072075128555298,
|
21 |
+
"eval_loss": 0.6931472420692444,
|
22 |
+
"eval_runtime": 9.1548,
|
23 |
+
"eval_samples_per_second": 325.839,
|
24 |
+
"eval_steps_per_second": 20.426,
|
25 |
+
"step": 746
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.3404825737265416,
|
29 |
+
"grad_norm": 1.8386740684509277,
|
30 |
+
"learning_rate": 4.0844263195097915e-05,
|
31 |
+
"loss": 0.7039,
|
32 |
+
"step": 1000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.49882668256759644,
|
37 |
+
"eval_loss": 0.6931472420692444,
|
38 |
+
"eval_runtime": 9.1028,
|
39 |
+
"eval_samples_per_second": 327.702,
|
40 |
+
"eval_steps_per_second": 20.543,
|
41 |
+
"step": 1492
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0107238605898123,
|
45 |
+
"grad_norm": 1.775593876838684,
|
46 |
+
"learning_rate": 3.768294251436278e-05,
|
47 |
+
"loss": 0.7008,
|
48 |
+
"step": 1500
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.680965147453083,
|
52 |
+
"grad_norm": 1.6979082822799683,
|
53 |
+
"learning_rate": 3.452162183362765e-05,
|
54 |
+
"loss": 0.7034,
|
55 |
+
"step": 2000
|
56 |
+
},
|
57 |
+
{
|
58 |
+
"epoch": 3.0,
|
59 |
+
"eval_accuracy": 0.5015085339546204,
|
60 |
+
"eval_loss": 0.6931472420692444,
|
61 |
+
"eval_runtime": 9.1903,
|
62 |
+
"eval_samples_per_second": 324.583,
|
63 |
+
"eval_steps_per_second": 20.348,
|
64 |
+
"step": 2238
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 3.351206434316354,
|
68 |
+
"grad_norm": 1.7350631952285767,
|
69 |
+
"learning_rate": 3.136030115289252e-05,
|
70 |
+
"loss": 0.7017,
|
71 |
+
"step": 2500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_accuracy": 0.5065370202064514,
|
76 |
+
"eval_loss": 0.6931472420692444,
|
77 |
+
"eval_runtime": 9.2185,
|
78 |
+
"eval_samples_per_second": 323.589,
|
79 |
+
"eval_steps_per_second": 20.285,
|
80 |
+
"step": 2984
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 4.021447721179625,
|
84 |
+
"grad_norm": 1.841038465499878,
|
85 |
+
"learning_rate": 2.8198980472157382e-05,
|
86 |
+
"loss": 0.7019,
|
87 |
+
"step": 3000
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.6916890080428955,
|
91 |
+
"grad_norm": 1.6272307634353638,
|
92 |
+
"learning_rate": 2.5037659791422253e-05,
|
93 |
+
"loss": 0.6994,
|
94 |
+
"step": 3500
|
95 |
+
},
|
96 |
+
{
|
97 |
+
"epoch": 5.0,
|
98 |
+
"eval_accuracy": 0.5095541477203369,
|
99 |
+
"eval_loss": 0.6931472420692444,
|
100 |
+
"eval_runtime": 9.0976,
|
101 |
+
"eval_samples_per_second": 327.89,
|
102 |
+
"eval_steps_per_second": 20.555,
|
103 |
+
"step": 3730
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 5.361930294906166,
|
107 |
+
"grad_norm": 1.7355244159698486,
|
108 |
+
"learning_rate": 2.1876339110687117e-05,
|
109 |
+
"loss": 0.7006,
|
110 |
+
"step": 4000
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 6.0,
|
114 |
+
"eval_accuracy": 0.49446865916252136,
|
115 |
+
"eval_loss": 0.6931472420692444,
|
116 |
+
"eval_runtime": 9.0977,
|
117 |
+
"eval_samples_per_second": 327.885,
|
118 |
+
"eval_steps_per_second": 20.555,
|
119 |
+
"step": 4476
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 6.032171581769437,
|
123 |
+
"grad_norm": 1.6792231798171997,
|
124 |
+
"learning_rate": 1.8715018429951985e-05,
|
125 |
+
"loss": 0.7005,
|
126 |
+
"step": 4500
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 6.702412868632708,
|
130 |
+
"grad_norm": 1.7535431385040283,
|
131 |
+
"learning_rate": 1.5553697749216852e-05,
|
132 |
+
"loss": 0.701,
|
133 |
+
"step": 5000
|
134 |
+
},
|
135 |
+
{
|
136 |
+
"epoch": 7.0,
|
137 |
+
"eval_accuracy": 0.4941334128379822,
|
138 |
+
"eval_loss": 0.6931472420692444,
|
139 |
+
"eval_runtime": 9.0431,
|
140 |
+
"eval_samples_per_second": 329.865,
|
141 |
+
"eval_steps_per_second": 20.679,
|
142 |
+
"step": 5222
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 7.372654155495979,
|
146 |
+
"grad_norm": 1.7443852424621582,
|
147 |
+
"learning_rate": 1.239237706848172e-05,
|
148 |
+
"loss": 0.7015,
|
149 |
+
"step": 5500
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 8.0,
|
153 |
+
"eval_accuracy": 0.5122359991073608,
|
154 |
+
"eval_loss": 0.6931472420692444,
|
155 |
+
"eval_runtime": 9.0713,
|
156 |
+
"eval_samples_per_second": 328.839,
|
157 |
+
"eval_steps_per_second": 20.614,
|
158 |
+
"step": 5968
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 8.04289544235925,
|
162 |
+
"grad_norm": 1.6793931722640991,
|
163 |
+
"learning_rate": 9.231056387746587e-06,
|
164 |
+
"loss": 0.7003,
|
165 |
+
"step": 6000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 8.71313672922252,
|
169 |
+
"grad_norm": 1.6744327545166016,
|
170 |
+
"learning_rate": 6.069735707011455e-06,
|
171 |
+
"loss": 0.7013,
|
172 |
+
"step": 6500
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 9.0,
|
176 |
+
"eval_accuracy": 0.48776400089263916,
|
177 |
+
"eval_loss": 0.6931472420692444,
|
178 |
+
"eval_runtime": 9.1943,
|
179 |
+
"eval_samples_per_second": 324.441,
|
180 |
+
"eval_steps_per_second": 20.339,
|
181 |
+
"step": 6714
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 9.383378016085791,
|
185 |
+
"grad_norm": 1.55774986743927,
|
186 |
+
"learning_rate": 2.908415026276322e-06,
|
187 |
+
"loss": 0.6984,
|
188 |
+
"step": 7000
|
189 |
+
}
|
190 |
+
],
|
191 |
+
"logging_steps": 500,
|
192 |
+
"max_steps": 7460,
|
193 |
+
"num_input_tokens_seen": 0,
|
194 |
+
"num_train_epochs": 10,
|
195 |
+
"save_steps": 500,
|
196 |
+
"total_flos": 1.8226917764893548e+16,
|
197 |
+
"train_batch_size": 16,
|
198 |
+
"trial_name": null,
|
199 |
+
"trial_params": {
|
200 |
+
"learning_rate": 4.716690455656818e-05,
|
201 |
+
"per_device_train_batch_size": 16
|
202 |
+
}
|
203 |
+
}
|
run-3/checkpoint-7000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0537522960a235b809ea329ec1396888a29088f8f8ec27bb9dbf5e7701ff29d
|
3 |
+
size 5048
|
run-3/checkpoint-7000/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-500/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "bert-large-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForMultipleChoice"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 4096,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 512,
|
16 |
+
"model_type": "bert",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.40.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
run-4/checkpoint-500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc6d5d7b39b3893580c52210ee5a58e9a8c2eccf9e6ffe2680b58d66f2c31759
|
3 |
+
size 1340618660
|
run-4/checkpoint-500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7a106e591a105b493cc0f76ce53bb2818157961ec5683210f59d905818b7c3e
|
3 |
+
size 2681472237
|
run-4/checkpoint-500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0c317b20a8b0f126de354e22abe6285be95b0457be6843da518d21b802633c6
|
3 |
+
size 14244
|
run-4/checkpoint-500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:027293190e8851694adbf6dea83c94303fe6f15ac4609b83940b639d53ccd08e
|
3 |
+
size 1064
|
run-4/checkpoint-500/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-4/checkpoint-500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-4/checkpoint-500/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-4/checkpoint-500/trainer_state.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.6702412868632708,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.6702412868632708,
|
13 |
+
"grad_norm": 13.804513931274414,
|
14 |
+
"learning_rate": 1.2284160000241888e-05,
|
15 |
+
"loss": 0.5698,
|
16 |
+
"step": 500
|
17 |
+
}
|
18 |
+
],
|
19 |
+
"logging_steps": 500,
|
20 |
+
"max_steps": 7460,
|
21 |
+
"num_input_tokens_seen": 0,
|
22 |
+
"num_train_epochs": 10,
|
23 |
+
"save_steps": 500,
|
24 |
+
"total_flos": 1313261590810176.0,
|
25 |
+
"train_batch_size": 16,
|
26 |
+
"trial_name": null,
|
27 |
+
"trial_params": {
|
28 |
+
"learning_rate": 1.3166642758879955e-05,
|
29 |
+
"per_device_train_batch_size": 16
|
30 |
+
}
|
31 |
+
}
|
run-4/checkpoint-500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
|
3 |
+
size 5048
|
run-4/checkpoint-500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5048
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27b6f814d1d31383705935d6e962b569d93dc7baa4de5cb209ef031fca6730c2
|
3 |
size 5048
|