inflaton commited on
Commit
0432a9c
1 Parent(s): e03e8f1

Training in progress, step 1500

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05fe06169dbaa744f5d41938724b2ee4787a338b283e95233ba3da4c88c19345
3
  size 1421491284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a440a4f9cfd036bb6b0def9457b6e506188504c0d067b5fdf912cb98e0c2e006
3
  size 1421491284
run-8/checkpoint-1500/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-large",
3
+ "architectures": [
4
+ "RobertaForMultipleChoice"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.40.1",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 50265
27
+ }
run-8/checkpoint-1500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a440a4f9cfd036bb6b0def9457b6e506188504c0d067b5fdf912cb98e0c2e006
3
+ size 1421491284
run-8/checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2cbb97709e7144b3d0ab0e358ccb04aeb9cf148723bb47616bb8695ab9c1588
3
+ size 2843215085
run-8/checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f48dc2f5362fb223b487a26aed5961225e681be7dd0c9dcd202d693a285b27e
3
+ size 14244
run-8/checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bde3caf35cf8c1e0a71c93a438689c402acf594cb95fffb3af47e38206608b14
3
+ size 1064
run-8/checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
run-8/checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-8/checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1,57 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": true,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "mask_token": "<mask>",
51
+ "model_max_length": 512,
52
+ "pad_token": "<pad>",
53
+ "sep_token": "</s>",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": "<unk>"
57
+ }
run-8/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": 0.748240053653717,
14
+ "eval_loss": 0.4897768199443817,
15
+ "eval_runtime": 9.3572,
16
+ "eval_samples_per_second": 318.792,
17
+ "eval_steps_per_second": 19.985,
18
+ "step": 187
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.7867918014526367,
23
+ "eval_loss": 0.4351676404476166,
24
+ "eval_runtime": 9.48,
25
+ "eval_samples_per_second": 314.662,
26
+ "eval_steps_per_second": 19.726,
27
+ "step": 374
28
+ },
29
+ {
30
+ "epoch": 2.6737967914438503,
31
+ "grad_norm": 15.95652961730957,
32
+ "learning_rate": 4.723376230943584e-06,
33
+ "loss": 0.4992,
34
+ "step": 500
35
+ },
36
+ {
37
+ "epoch": 3.0,
38
+ "eval_accuracy": 0.8079115152359009,
39
+ "eval_loss": 0.413047730922699,
40
+ "eval_runtime": 9.447,
41
+ "eval_samples_per_second": 315.76,
42
+ "eval_steps_per_second": 19.795,
43
+ "step": 561
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.805229663848877,
48
+ "eval_loss": 0.4279593527317047,
49
+ "eval_runtime": 9.494,
50
+ "eval_samples_per_second": 314.198,
51
+ "eval_steps_per_second": 19.697,
52
+ "step": 748
53
+ },
54
+ {
55
+ "epoch": 5.0,
56
+ "eval_accuracy": 0.8109285831451416,
57
+ "eval_loss": 0.46117427945137024,
58
+ "eval_runtime": 9.4914,
59
+ "eval_samples_per_second": 314.286,
60
+ "eval_steps_per_second": 19.702,
61
+ "step": 935
62
+ },
63
+ {
64
+ "epoch": 5.347593582887701,
65
+ "grad_norm": 18.722320556640625,
66
+ "learning_rate": 2.9995162926430056e-06,
67
+ "loss": 0.258,
68
+ "step": 1000
69
+ },
70
+ {
71
+ "epoch": 6.0,
72
+ "eval_accuracy": 0.8129400014877319,
73
+ "eval_loss": 0.5127686262130737,
74
+ "eval_runtime": 9.3459,
75
+ "eval_samples_per_second": 319.179,
76
+ "eval_steps_per_second": 20.009,
77
+ "step": 1122
78
+ },
79
+ {
80
+ "epoch": 7.0,
81
+ "eval_accuracy": 0.8069058060646057,
82
+ "eval_loss": 0.5462248921394348,
83
+ "eval_runtime": 9.4811,
84
+ "eval_samples_per_second": 314.625,
85
+ "eval_steps_per_second": 19.723,
86
+ "step": 1309
87
+ },
88
+ {
89
+ "epoch": 8.0,
90
+ "eval_accuracy": 0.8112637996673584,
91
+ "eval_loss": 0.5747013688087463,
92
+ "eval_runtime": 9.4581,
93
+ "eval_samples_per_second": 315.392,
94
+ "eval_steps_per_second": 19.771,
95
+ "step": 1496
96
+ },
97
+ {
98
+ "epoch": 8.02139037433155,
99
+ "grad_norm": 17.311113357543945,
100
+ "learning_rate": 1.2756563543424279e-06,
101
+ "loss": 0.1447,
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": 2.010272908557654e+16,
111
+ "train_batch_size": 64,
112
+ "trial_name": null,
113
+ "trial_params": {
114
+ "learning_rate": 6.447236169244162e-06,
115
+ "per_device_train_batch_size": 64
116
+ }
117
+ }
run-8/checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40e8cef35b8bcc1ef26293c9bc0d35e5378a8e1a03af177be080cc43a98fabb
3
+ size 5048
run-8/checkpoint-1500/vocab.json ADDED
The diff for this file is too large to render. See raw diff