itsanastasiaminina commited on
Commit
464f8b9
·
verified ·
1 Parent(s): faeb1fc

Training in progress, epoch 2

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa097d500ad8349a8f6f122d1710fb3a81a60f4fcaaad33d535a42b53b8db110
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b512439e4fe84c651bddbbcfc2b736adfe353cd480dd8cd09a660e3d04e406b
3
  size 498625128
run-3/checkpoint-564/config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForSequenceClassification"
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": 768,
13
+ "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5"
20
+ },
21
+ "initializer_range": 0.02,
22
+ "intermediate_size": 3072,
23
+ "label2id": {
24
+ "LABEL_0": 0,
25
+ "LABEL_1": 1,
26
+ "LABEL_2": 2,
27
+ "LABEL_3": 3,
28
+ "LABEL_4": 4,
29
+ "LABEL_5": 5
30
+ },
31
+ "layer_norm_eps": 1e-05,
32
+ "max_position_embeddings": 514,
33
+ "model_type": "roberta",
34
+ "num_attention_heads": 12,
35
+ "num_hidden_layers": 12,
36
+ "pad_token_id": 1,
37
+ "position_embedding_type": "absolute",
38
+ "problem_type": "single_label_classification",
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.47.0",
41
+ "type_vocab_size": 1,
42
+ "use_cache": true,
43
+ "vocab_size": 50265
44
+ }
run-3/checkpoint-564/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-564/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b512439e4fe84c651bddbbcfc2b736adfe353cd480dd8cd09a660e3d04e406b
3
+ size 498625128
run-3/checkpoint-564/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0bb837f3929bcd3efcd0d2afef4b209e31c852dc8f7fe2d7ffecc7d5b3dabf4
3
+ size 997370106
run-3/checkpoint-564/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b99d4651e5b9b77475812868d3a6b49436d527964ed98dfb1718b7fe878ae78
3
+ size 14244
run-3/checkpoint-564/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f3c32079fa9a5b4789046eeb207646cfea3de29b14bfa44d661f4fc9fe1adf
3
+ size 1064
run-3/checkpoint-564/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-3/checkpoint-564/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-3/checkpoint-564/tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
run-3/checkpoint-564/trainer_state.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5824584566376877,
3
+ "best_model_checkpoint": "students_scores_model/run-3/checkpoint-564",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 564,
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_f1": 0.527378071005394,
14
+ "eval_loss": 1.0453823804855347,
15
+ "eval_runtime": 37.8811,
16
+ "eval_samples_per_second": 59.396,
17
+ "eval_steps_per_second": 7.444,
18
+ "step": 282
19
+ },
20
+ {
21
+ "epoch": 1.773049645390071,
22
+ "grad_norm": 10.149354934692383,
23
+ "learning_rate": 1.4371191049893149e-05,
24
+ "loss": 1.0168,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_f1": 0.5824584566376877,
30
+ "eval_loss": 0.9663960337638855,
31
+ "eval_runtime": 37.8357,
32
+ "eval_samples_per_second": 59.468,
33
+ "eval_steps_per_second": 7.453,
34
+ "step": 564
35
+ }
36
+ ],
37
+ "logging_steps": 500,
38
+ "max_steps": 1410,
39
+ "num_input_tokens_seen": 0,
40
+ "num_train_epochs": 5,
41
+ "save_steps": 500,
42
+ "stateful_callbacks": {
43
+ "TrainerControl": {
44
+ "args": {
45
+ "should_epoch_stop": false,
46
+ "should_evaluate": false,
47
+ "should_log": false,
48
+ "should_save": true,
49
+ "should_training_stop": false
50
+ },
51
+ "attributes": {}
52
+ }
53
+ },
54
+ "total_flos": 4203350064691200.0,
55
+ "train_batch_size": 32,
56
+ "trial_name": null,
57
+ "trial_params": {
58
+ "learning_rate": 2.2267449868515756e-05,
59
+ "num_train_epochs": 5,
60
+ "per_device_train_batch_size": 32,
61
+ "weight_decay": 0.0007528832894945841
62
+ }
63
+ }
run-3/checkpoint-564/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6439588b06d32843c28d9e83f3ff417aeba35fd26576c7c184a7760ef6f0bc
3
+ size 5368
run-3/checkpoint-564/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec09_12-41-02_ea67bac3fd95/events.out.tfevents.1733754551.ea67bac3fd95.23.3 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:967f20897ed7b77daec2d6f145e1de039fe49e4cf681108faca685192bb31f2e
3
- size 5672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ce7963f66d2be3a630c73749414b30a5d80eefa8b9e79f45f68a2c670aba1b
3
+ size 6200