tmnam20 commited on
Commit
afb24eb
1 Parent(s): 28ac851

Training in progress, step 7000, checkpoint

Browse files
checkpoint-7000/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<bos>": 40478,
3
+ "<eos>": 40479,
4
+ "<pad>": 40480
5
+ }
checkpoint-7000/config.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-gpt",
3
+ "afn": "gelu",
4
+ "architectures": [
5
+ "OpenAIGPTForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "embd_pdrop": 0.1,
9
+ "id2label": {
10
+ "0": "entailment",
11
+ "1": "neutral",
12
+ "2": "contradiction"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "contradiction": 2,
17
+ "entailment": 0,
18
+ "neutral": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "openai-gpt",
22
+ "n_ctx": 512,
23
+ "n_embd": 768,
24
+ "n_head": 24,
25
+ "n_layer": 12,
26
+ "n_positions": 512,
27
+ "n_special": 0,
28
+ "pad_token_id": 40480,
29
+ "predict_special_tokens": true,
30
+ "problem_type": "single_label_classification",
31
+ "resid_pdrop": 0.1,
32
+ "summary_activation": null,
33
+ "summary_first_dropout": 0.1,
34
+ "summary_proj_to_labels": true,
35
+ "summary_type": "cls_index",
36
+ "summary_use_proj": true,
37
+ "task_specific_params": {
38
+ "text-generation": {
39
+ "do_sample": true,
40
+ "max_length": 50
41
+ }
42
+ },
43
+ "torch_dtype": "float32",
44
+ "transformers_version": "4.33.0.dev0",
45
+ "vocab_size": 40481
46
+ }
checkpoint-7000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-7000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfdbaf5ce78ad95e1f62951cbd8ee387842ae916715e15de5a94fb3c1d541656
3
+ size 932401285
checkpoint-7000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea431ab704594cf3981265829b426635f2e963dbaf68de71008d7a736db2a3b
3
+ size 466205145
checkpoint-7000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b8f0452bf9ad22b104d4f6fd2cb7cbfa9bed047dd6a1d7373f9dffd4effc40b
3
+ size 14575
checkpoint-7000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8fb1e1accde8db968a2cd379266750e2de1bdcec8bf240a7c8b93339f41a04
3
+ size 627
checkpoint-7000/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-7000/tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "model_max_length": 512,
4
+ "padding_side": "left",
5
+ "tokenizer_class": "OpenAIGPTTokenizer",
6
+ "unk_token": "<unk>"
7
+ }
checkpoint-7000/trainer_state.json ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 1.0955135822296143,
3
+ "best_model_checkpoint": "/kaggle/output/checkpoint-7000",
4
+ "epoch": 0.28520208604954367,
5
+ "eval_steps": 1000,
6
+ "global_step": 7000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "learning_rate": 2.7777777777777777e-11,
14
+ "loss": 1.1506,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.04,
19
+ "learning_rate": 2.7750000000000004e-08,
20
+ "loss": 1.1326,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.04,
25
+ "eval_accuracy": 0.3331337325349301,
26
+ "eval_loss": 1.1057127714157104,
27
+ "eval_runtime": 61.3538,
28
+ "eval_samples_per_second": 81.657,
29
+ "eval_steps_per_second": 10.219,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "learning_rate": 5.5527777777777784e-08,
35
+ "loss": 1.1238,
36
+ "step": 2000
37
+ },
38
+ {
39
+ "epoch": 0.08,
40
+ "eval_accuracy": 0.33812375249501,
41
+ "eval_loss": 1.1044437885284424,
42
+ "eval_runtime": 61.256,
43
+ "eval_samples_per_second": 81.788,
44
+ "eval_steps_per_second": 10.236,
45
+ "step": 2000
46
+ },
47
+ {
48
+ "epoch": 0.12,
49
+ "learning_rate": 8.327777777777778e-08,
50
+ "loss": 1.1251,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.12,
55
+ "eval_accuracy": 0.3407185628742515,
56
+ "eval_loss": 1.1043975353240967,
57
+ "eval_runtime": 61.2433,
58
+ "eval_samples_per_second": 81.805,
59
+ "eval_steps_per_second": 10.238,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 0.16,
64
+ "learning_rate": 1.1105555555555557e-07,
65
+ "loss": 1.1205,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.16,
70
+ "eval_accuracy": 0.3387225548902196,
71
+ "eval_loss": 1.100860357284546,
72
+ "eval_runtime": 61.4457,
73
+ "eval_samples_per_second": 81.535,
74
+ "eval_steps_per_second": 10.204,
75
+ "step": 4000
76
+ },
77
+ {
78
+ "epoch": 0.2,
79
+ "learning_rate": 1.3880555555555558e-07,
80
+ "loss": 1.1192,
81
+ "step": 5000
82
+ },
83
+ {
84
+ "epoch": 0.2,
85
+ "eval_accuracy": 0.34151696606786425,
86
+ "eval_loss": 1.1005476713180542,
87
+ "eval_runtime": 61.2568,
88
+ "eval_samples_per_second": 81.787,
89
+ "eval_steps_per_second": 10.236,
90
+ "step": 5000
91
+ },
92
+ {
93
+ "epoch": 0.24,
94
+ "learning_rate": 1.6658333333333335e-07,
95
+ "loss": 1.1145,
96
+ "step": 6000
97
+ },
98
+ {
99
+ "epoch": 0.24,
100
+ "eval_accuracy": 0.3508982035928144,
101
+ "eval_loss": 1.0979759693145752,
102
+ "eval_runtime": 61.2221,
103
+ "eval_samples_per_second": 81.833,
104
+ "eval_steps_per_second": 10.241,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 0.29,
109
+ "learning_rate": 1.9433333333333334e-07,
110
+ "loss": 1.1164,
111
+ "step": 7000
112
+ },
113
+ {
114
+ "epoch": 0.29,
115
+ "eval_accuracy": 0.35508982035928144,
116
+ "eval_loss": 1.0955135822296143,
117
+ "eval_runtime": 61.255,
118
+ "eval_samples_per_second": 81.789,
119
+ "eval_steps_per_second": 10.236,
120
+ "step": 7000
121
+ }
122
+ ],
123
+ "logging_steps": 1000,
124
+ "max_steps": 10000000,
125
+ "num_train_epochs": 408,
126
+ "save_steps": 1000,
127
+ "total_flos": 1.4632485912576e+16,
128
+ "trial_name": null,
129
+ "trial_params": null
130
+ }
checkpoint-7000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e31537d78ddfb65ec62a3bb3689996ba9eab16c9072c351cad313c78d3b7a608
3
+ size 4091
checkpoint-7000/vocab.json ADDED
The diff for this file is too large to render. See raw diff