Training in progress, step 1500
Browse files- model.safetensors +1 -1
- run-0/checkpoint-1500/config.json +26 -0
- run-0/checkpoint-1500/model.safetensors +3 -0
- run-0/checkpoint-1500/optimizer.pt +3 -0
- run-0/checkpoint-1500/rng_state.pth +3 -0
- run-0/checkpoint-1500/scheduler.pt +3 -0
- run-0/checkpoint-1500/special_tokens_map.json +7 -0
- run-0/checkpoint-1500/tokenizer.json +0 -0
- run-0/checkpoint-1500/tokenizer_config.json +55 -0
- run-0/checkpoint-1500/trainer_state.json +117 -0
- run-0/checkpoint-1500/training_args.bin +3 -0
- run-0/checkpoint-1500/vocab.txt +0 -0
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:a4e8216b4bd112f4ed16a59512dca9cd037abdd6604ad814b94db4b98d881fdf
|
3 |
size 1340618660
|
run-0/checkpoint-1500/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-0/checkpoint-1500/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4e8216b4bd112f4ed16a59512dca9cd037abdd6604ad814b94db4b98d881fdf
|
3 |
+
size 1340618660
|
run-0/checkpoint-1500/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d52e0a0e2f9de699b2edbbbfc6fdf2cec0e9e886a5275bbe603e13a03ea2a5da
|
3 |
+
size 2681472237
|
run-0/checkpoint-1500/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02726484d0368608126b4b623e8a9dca0feeef64e1c28760438804747f801dfd
|
3 |
+
size 14244
|
run-0/checkpoint-1500/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ffe8c3042419912798e897252d0e20cac6cbffbbdf307bf8ee4796ded1cbb71
|
3 |
+
size 1064
|
run-0/checkpoint-1500/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-0/checkpoint-1500/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-0/checkpoint-1500/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-0/checkpoint-1500/trainer_state.json
ADDED
@@ -0,0 +1,117 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 8.02139037433155,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 1500,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"eval_accuracy": 0.7532685399055481,
|
14 |
+
"eval_loss": 0.4793490469455719,
|
15 |
+
"eval_runtime": 9.3602,
|
16 |
+
"eval_samples_per_second": 318.688,
|
17 |
+
"eval_steps_per_second": 19.978,
|
18 |
+
"step": 187
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 2.0,
|
22 |
+
"eval_accuracy": 0.7790814638137817,
|
23 |
+
"eval_loss": 0.4668562114238739,
|
24 |
+
"eval_runtime": 9.4916,
|
25 |
+
"eval_samples_per_second": 314.277,
|
26 |
+
"eval_steps_per_second": 19.702,
|
27 |
+
"step": 374
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.6737967914438503,
|
31 |
+
"grad_norm": 9.970394134521484,
|
32 |
+
"learning_rate": 1.0116255710136231e-05,
|
33 |
+
"loss": 0.4413,
|
34 |
+
"step": 500
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 3.0,
|
38 |
+
"eval_accuracy": 0.7790814638137817,
|
39 |
+
"eval_loss": 0.5445067882537842,
|
40 |
+
"eval_runtime": 9.4939,
|
41 |
+
"eval_samples_per_second": 314.202,
|
42 |
+
"eval_steps_per_second": 19.697,
|
43 |
+
"step": 561
|
44 |
+
},
|
45 |
+
{
|
46 |
+
"epoch": 4.0,
|
47 |
+
"eval_accuracy": 0.7700302004814148,
|
48 |
+
"eval_loss": 0.6839850544929504,
|
49 |
+
"eval_runtime": 9.4969,
|
50 |
+
"eval_samples_per_second": 314.101,
|
51 |
+
"eval_steps_per_second": 19.691,
|
52 |
+
"step": 748
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 5.0,
|
56 |
+
"eval_accuracy": 0.7680187821388245,
|
57 |
+
"eval_loss": 0.7934393286705017,
|
58 |
+
"eval_runtime": 9.5009,
|
59 |
+
"eval_samples_per_second": 313.97,
|
60 |
+
"eval_steps_per_second": 19.682,
|
61 |
+
"step": 935
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 5.347593582887701,
|
65 |
+
"grad_norm": 6.287047863006592,
|
66 |
+
"learning_rate": 6.424191582349286e-06,
|
67 |
+
"loss": 0.1515,
|
68 |
+
"step": 1000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 6.0,
|
72 |
+
"eval_accuracy": 0.7730472683906555,
|
73 |
+
"eval_loss": 0.7747542262077332,
|
74 |
+
"eval_runtime": 9.4572,
|
75 |
+
"eval_samples_per_second": 315.421,
|
76 |
+
"eval_steps_per_second": 19.773,
|
77 |
+
"step": 1122
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 7.0,
|
81 |
+
"eval_accuracy": 0.7700302004814148,
|
82 |
+
"eval_loss": 0.8394743800163269,
|
83 |
+
"eval_runtime": 9.6279,
|
84 |
+
"eval_samples_per_second": 309.83,
|
85 |
+
"eval_steps_per_second": 19.423,
|
86 |
+
"step": 1309
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 8.0,
|
90 |
+
"eval_accuracy": 0.7717063426971436,
|
91 |
+
"eval_loss": 0.8363062143325806,
|
92 |
+
"eval_runtime": 9.6181,
|
93 |
+
"eval_samples_per_second": 310.145,
|
94 |
+
"eval_steps_per_second": 19.443,
|
95 |
+
"step": 1496
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 8.02139037433155,
|
99 |
+
"grad_norm": 7.763587474822998,
|
100 |
+
"learning_rate": 2.73212745456234e-06,
|
101 |
+
"loss": 0.0648,
|
102 |
+
"step": 1500
|
103 |
+
}
|
104 |
+
],
|
105 |
+
"logging_steps": 500,
|
106 |
+
"max_steps": 1870,
|
107 |
+
"num_input_tokens_seen": 0,
|
108 |
+
"num_train_epochs": 10,
|
109 |
+
"save_steps": 500,
|
110 |
+
"total_flos": 1.7577443886948468e+16,
|
111 |
+
"train_batch_size": 64,
|
112 |
+
"trial_name": null,
|
113 |
+
"trial_params": {
|
114 |
+
"learning_rate": 1.3808319837923177e-05,
|
115 |
+
"per_device_train_batch_size": 64
|
116 |
+
}
|
117 |
+
}
|
run-0/checkpoint-1500/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feac2daf058c7e56243ee3aa074f41715308b943716dfb58c6ab30c00c466ccf
|
3 |
+
size 5048
|
run-0/checkpoint-1500/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|