inflaton commited on
Commit
e6f775c
1 Parent(s): ec31dc4

Training in progress, step 500

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f7d25481e681f44ba27d8739c8e323e06580f610b8d3af37a2d8c34237721c9
3
  size 1421491284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651378cf7bea75dc86ec68f9f71993a0daa3779a8226fe90612689a15ddca1bc
3
  size 1421491284
run-5/checkpoint-500/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-5/checkpoint-500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:651378cf7bea75dc86ec68f9f71993a0daa3779a8226fe90612689a15ddca1bc
3
+ size 1421491284
run-5/checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c2c862290deba6e9f1f4bb49b404b623f6d523485bbbc05424267a394e23ff2
3
+ size 2843215085
run-5/checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0639a7eaef72e817a0290e4a7570d62c240430949de277ab7ac247d229f91114
3
+ size 14244
run-5/checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e107fd8bf0826c032c25e10699711e36b17055e3dff2f749887b1518aa5b6b01
3
+ size 1064
run-5/checkpoint-500/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-5/checkpoint-500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-5/checkpoint-500/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-5/checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.6737967914438503,
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": 1.0,
13
+ "eval_accuracy": 0.7019778490066528,
14
+ "eval_loss": 0.5544637441635132,
15
+ "eval_runtime": 9.2773,
16
+ "eval_samples_per_second": 321.539,
17
+ "eval_steps_per_second": 20.157,
18
+ "step": 187
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.744552493095398,
23
+ "eval_loss": 0.49814581871032715,
24
+ "eval_runtime": 9.3471,
25
+ "eval_samples_per_second": 319.136,
26
+ "eval_steps_per_second": 20.006,
27
+ "step": 374
28
+ },
29
+ {
30
+ "epoch": 2.6737967914438503,
31
+ "grad_norm": 11.23240852355957,
32
+ "learning_rate": 1.7634576095057786e-06,
33
+ "loss": 0.5749,
34
+ "step": 500
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1870,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 10,
41
+ "save_steps": 500,
42
+ "total_flos": 5969895738820488.0,
43
+ "train_batch_size": 64,
44
+ "trial_name": null,
45
+ "trial_params": {
46
+ "learning_rate": 2.4070552772086175e-06,
47
+ "per_device_train_batch_size": 64
48
+ }
49
+ }
run-5/checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6433f0c0ad099ec3bf4145fcc86507c8490c2f642ce9a6a75665bc6009566568
3
+ size 5048
run-5/checkpoint-500/vocab.json 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 sha256:7db8a7a0dfed6f985d34492a77fc54ac5788fe514ba2cde45d3b63947da0c296
3
  size 5048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6433f0c0ad099ec3bf4145fcc86507c8490c2f642ce9a6a75665bc6009566568
3
  size 5048