itsanastasiaminina commited on
Commit
3a06821
·
verified ·
1 Parent(s): 95a4136

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 sha256:57a14f7748a6a04a7c02c53485e1877118fea7f53eaad0eacef0915801fc34ae
3
  size 498625128
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728857b3c80e63abbfacca10d1f25711a2e4fe2c73c47eb51aafe5d590b57ccc
3
  size 498625128
run-1/checkpoint-1126/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eed3091eb761444c21e8ad4810c28637b0a0c9c3103bbcc5f996e34a658356bc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:279aab4142ba2bc15a26a5c73e18f555c0949931f163d68de9a3f73e4f0c4c00
3
  size 14244
run-2/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-2/checkpoint-282/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-282/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:728857b3c80e63abbfacca10d1f25711a2e4fe2c73c47eb51aafe5d590b57ccc
3
+ size 498625128
run-2/checkpoint-282/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cdb81877303a98f937bc1392bb920d59d40c07b88cc7fae9ba86d29458231a2
3
+ size 997370106
run-2/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-2/checkpoint-282/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af89341496c26ffc385b6d2ae617d411de3d4467e6aa357a7b47b6ff6486a57b
3
+ size 1064
run-2/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-2/checkpoint-282/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/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-2/checkpoint-282/trainer_state.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.5280922046056804,
3
+ "best_model_checkpoint": "students_scores_model/run-2/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": 0.5280922046056804,
14
+ "eval_loss": 1.0346653461456299,
15
+ "eval_runtime": 37.6542,
16
+ "eval_samples_per_second": 59.754,
17
+ "eval_steps_per_second": 7.489,
18
+ "step": 282
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 846,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 3,
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": 1.1002898202280765e-05,
43
+ "num_train_epochs": 3,
44
+ "per_device_train_batch_size": 32,
45
+ "weight_decay": 0.008293142825111385
46
+ }
47
+ }
run-2/checkpoint-282/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92eed261d071d88405c0cc7cdc0b8eceb2628d134f07932409e8529a92610828
3
+ size 5368
run-2/checkpoint-282/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733696071.6ff5f1d99a72.23.1 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0165ba875ed7e21956c12132105f40b098af07a9beb59848292d6b9ce6fa0157
3
- size 6093
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:050d52b2978937320826fc72b8f18c57c3acb5314cd046fbf0bdc0f4f4c8227f
3
+ size 6764
runs/Dec08_21-54-18_6ff5f1d99a72/events.out.tfevents.1733697267.6ff5f1d99a72.23.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b4da3604c035e0fcb7a604e4fe47408defad95dc293db84af1e5f4fa9d32fcb
3
+ size 5671
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b94ce251b73f8aadbf2d3b914945301b52341856da7ddaf4675709c9b25289a5
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92eed261d071d88405c0cc7cdc0b8eceb2628d134f07932409e8529a92610828
3
  size 5368