itsanastasiaminina commited on
Commit
c19446f
·
verified ·
1 Parent(s): d48e545

Training in progress, epoch 1

Browse files
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17de67ad92dabf88985a54e46778d6c5d57f8027da6db3b5f37de0c6b94ff74b
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea2043a7287a89e0eb3267b922ec1c03f64e493e3d0efba0cd35347958e3671
3
  size 498625128
run-0/checkpoint-1689/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68f1d83a24dea24b3ee8fe08ca2d8c2be0524aab6848d54221b60f93a60135a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:071c5e9be8c89f7e7601ef6e67c044701f3e899071b5431a452dcbeb2c3af0a4
3
  size 14244
run-1/checkpoint-282/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-1/checkpoint-282/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-282/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea2043a7287a89e0eb3267b922ec1c03f64e493e3d0efba0cd35347958e3671
3
+ size 498625128
run-1/checkpoint-282/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999e75bc5aaad74b86317e29c1e81dd077f4b6a78f001803307ebae716b6eefc
3
+ size 997370106
run-1/checkpoint-282/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d12757df72b49b0663b87aec71a85f9fa69ea3a56502af0f73cd584877bbf5be
3
+ size 14244
run-1/checkpoint-282/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:639dc49e9521201cddb6d5d8803bac4684da6fa8e3e14aa19b68ec52605bb111
3
+ size 1064
run-1/checkpoint-282/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-1/checkpoint-282/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-282/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-1/checkpoint-282/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5135559583730447,
3
+ "best_model_checkpoint": "students_scores_model/run-1/checkpoint-282",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 282,
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": 0.5135559583730447,
14
+ "eval_loss": 1.0615456104278564,
15
+ "eval_runtime": 37.678,
16
+ "eval_samples_per_second": 59.716,
17
+ "eval_steps_per_second": 7.484,
18
+ "step": 282
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 1410,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "stateful_callbacks": {
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": false
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 0,
39
+ "train_batch_size": 32,
40
+ "trial_name": null,
41
+ "trial_params": {
42
+ "learning_rate": 1.3228889953650998e-05,
43
+ "num_train_epochs": 5,
44
+ "per_device_train_batch_size": 32,
45
+ "weight_decay": 0.0004860339799795757
46
+ }
47
+ }
run-1/checkpoint-282/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6c0e80228b83305d52c2ecaa5e9378ae485930e09ca765409ad7f4e4465fdb
3
+ size 5368
run-1/checkpoint-282/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733664606.3b937233628b.23.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e96c87fba5c9f879263c9f22eb08bf65b18a48b87749d9c5bc0be73fec0f7477
3
- size 6641
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67c6c68d617e9b1c9f1ebe90c7bda69b8a8f00392c9ec7940d8fa332d67205a3
3
+ size 7312
runs/Dec08_13-30-03_3b937233628b/events.out.tfevents.1733666403.3b937233628b.23.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3350e90f0c8779d6f71021b1a776b743d534129f9c073b4fb05ba9325cd986c4
3
+ size 5672
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86e506878344e67934428f3176c568da4bb4fdfd8b8918c71494a2c9eb08433b
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6c0e80228b83305d52c2ecaa5e9378ae485930e09ca765409ad7f4e4465fdb
3
  size 5368