Hugging Face's logo

aaronmena02
/
priority-model-mailclassifier

Safetensors
roberta
Model card Files
xet
 Community
aaronmena02 commited on
Commit
680b516
·
verified ·
1 Parent(s): 6d4bddd

Actualización del modelo mejorado

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-13/config.json +39 -0
  2. checkpoint-13/model.safetensors +3 -0
  3. checkpoint-13/optimizer.pt +3 -0
  4. checkpoint-13/rng_state.pth +3 -0
  5. checkpoint-13/scheduler.pt +3 -0
  6. checkpoint-13/special_tokens_map.json +51 -0
  7. checkpoint-13/tokenizer.json +0 -0
  8. checkpoint-13/tokenizer_config.json +61 -0
  9. checkpoint-13/trainer_state.json +38 -0
  10. checkpoint-13/training_args.bin +3 -0
  11. checkpoint-14/config.json +39 -0
  12. checkpoint-14/model.safetensors +3 -0
  13. checkpoint-14/optimizer.pt +3 -0
  14. checkpoint-14/rng_state.pth +3 -0
  15. checkpoint-14/scheduler.pt +3 -0
  16. checkpoint-14/special_tokens_map.json +51 -0
  17. checkpoint-14/tokenizer.json +0 -0
  18. checkpoint-14/tokenizer_config.json +61 -0
  19. checkpoint-14/trainer_state.json +38 -0
  20. checkpoint-14/training_args.bin +3 -0
  21. checkpoint-26/config.json +39 -0
  22. checkpoint-26/model.safetensors +3 -0
  23. checkpoint-26/optimizer.pt +3 -0
  24. checkpoint-26/rng_state.pth +3 -0
  25. checkpoint-26/scheduler.pt +3 -0
  26. checkpoint-26/special_tokens_map.json +51 -0
  27. checkpoint-26/tokenizer.json +0 -0
  28. checkpoint-26/tokenizer_config.json +61 -0
  29. checkpoint-26/trainer_state.json +55 -0
  30. checkpoint-26/training_args.bin +3 -0
  31. checkpoint-28/config.json +39 -0
  32. checkpoint-28/model.safetensors +3 -0
  33. checkpoint-28/optimizer.pt +3 -0
  34. checkpoint-28/rng_state.pth +3 -0
  35. checkpoint-28/scheduler.pt +3 -0
  36. checkpoint-28/special_tokens_map.json +51 -0
  37. checkpoint-28/tokenizer.json +0 -0
  38. checkpoint-28/tokenizer_config.json +61 -0
  39. checkpoint-28/trainer_state.json +55 -0
  40. checkpoint-28/training_args.bin +3 -0
  41. checkpoint-39/config.json +39 -0
  42. checkpoint-39/model.safetensors +3 -0
  43. checkpoint-39/optimizer.pt +3 -0
  44. checkpoint-39/rng_state.pth +3 -0
  45. checkpoint-39/scheduler.pt +3 -0
  46. checkpoint-39/special_tokens_map.json +51 -0
  47. checkpoint-39/tokenizer.json +0 -0
  48. checkpoint-39/tokenizer_config.json +61 -0
  49. checkpoint-39/trainer_state.json +72 -0
  50. checkpoint-39/training_args.bin +3 -0
checkpoint-13/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pysentimiento/robertuito-base-uncased",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "alta",
16
+ "1": "baja",
17
+ "2": "media"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "alta": 0,
23
+ "baja": 1,
24
+ "media": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 130,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.1",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 30000
39
+ }
checkpoint-13/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d198ace4102e0ff6926600434577d3cb56859aaa88affbfc7f1e270708e8533
3
+ size 435182156
checkpoint-13/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87f94a3f6a588307cd6b42ad336ab6238441b6f8664095041d19d53972d6178b
3
+ size 870484154
checkpoint-13/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1418ea10e4f1408220ade58b82da4e3a967a2a48f7f49cc003004158924dda5
3
+ size 14244
checkpoint-13/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f7b564f2090db5f5b1e5df77ea584dd4299c094af22f5f5c20029a79f8e0afa
3
+ size 1064
checkpoint-13/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-13/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-13/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "PreTrainedTokenizerFast",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
checkpoint-13/trainer_state.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7328296703296704,
3
+ "best_model_checkpoint": "./priority_model\\checkpoint-13",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 13,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7692307692307693,
13
+ "grad_norm": 4.372110366821289,
14
+ "learning_rate": 1.7435897435897438e-05,
15
+ "loss": 1.0904,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7307692307692307,
21
+ "eval_f1": 0.7328296703296704,
22
+ "eval_loss": 0.8845496773719788,
23
+ "eval_runtime": 0.065,
24
+ "eval_samples_per_second": 799.398,
25
+ "eval_steps_per_second": 61.492,
26
+ "step": 13
27
+ }
28
+ ],
29
+ "logging_steps": 10,
30
+ "max_steps": 78,
31
+ "num_input_tokens_seen": 0,
32
+ "num_train_epochs": 6,
33
+ "save_steps": 500,
34
+ "total_flos": 9573833930220.0,
35
+ "train_batch_size": 16,
36
+ "trial_name": null,
37
+ "trial_params": null
38
+ }
checkpoint-13/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b3df75f302017e957ecfc3937821ef6f12e7d4c8200fb79b1323498df9e15a
3
+ size 4920
checkpoint-14/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pysentimiento/robertuito-base-uncased",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "alta",
16
+ "1": "baja",
17
+ "2": "media"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "alta": 0,
23
+ "baja": 1,
24
+ "media": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 130,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.1",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 30000
39
+ }
checkpoint-14/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0bc0d6a7a24f7ceccbb979e0be506dfea1197ab98d84ed9d9aa964c26921e24
3
+ size 435182156
checkpoint-14/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c6eebdf548d3369f66bff27718a9d625ab8ea613298d194459bad4449864cd9
3
+ size 870484154
checkpoint-14/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa1f86a0b2ccaf75893c4616393e9f4024c1b3e70fcc211f3f749e41096d5aeb
3
+ size 14244
checkpoint-14/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:899d3f6de42b6b2d016bb8da55d7a3499b37114b634ebb1bd13451cc02c47220
3
+ size 1064
checkpoint-14/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-14/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-14/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "PreTrainedTokenizerFast",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
checkpoint-14/trainer_state.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6908805031446541,
3
+ "best_model_checkpoint": "./priority_model\\checkpoint-14",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 14,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7142857142857143,
13
+ "grad_norm": 4.813197135925293,
14
+ "learning_rate": 1.761904761904762e-05,
15
+ "loss": 1.0447,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6981132075471698,
21
+ "eval_f1": 0.6908805031446541,
22
+ "eval_loss": 0.8730468153953552,
23
+ "eval_runtime": 0.073,
24
+ "eval_samples_per_second": 726.021,
25
+ "eval_steps_per_second": 54.794,
26
+ "step": 14
27
+ }
28
+ ],
29
+ "logging_steps": 10,
30
+ "max_steps": 84,
31
+ "num_input_tokens_seen": 0,
32
+ "num_train_epochs": 6,
33
+ "save_steps": 500,
34
+ "total_flos": 9666334741140.0,
35
+ "train_batch_size": 16,
36
+ "trial_name": null,
37
+ "trial_params": null
38
+ }
checkpoint-14/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b3df75f302017e957ecfc3937821ef6f12e7d4c8200fb79b1323498df9e15a
3
+ size 4920
checkpoint-26/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pysentimiento/robertuito-base-uncased",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "alta",
16
+ "1": "baja",
17
+ "2": "media"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "alta": 0,
23
+ "baja": 1,
24
+ "media": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 130,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.1",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 30000
39
+ }
checkpoint-26/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f85c3769630ac0771d3be86a0b71ff8bdef074eab1a95ad2eac6ceab9201f6d5
3
+ size 435182156
checkpoint-26/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e844759b2df93c87b17c66a5150681595eaa77f5b2b1a76857ce2a92a616c3
3
+ size 870484154
checkpoint-26/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ccb4c0b71300b88443210f3450b47f4ed33e17e35cc064d82b46484f80d5806
3
+ size 14244
checkpoint-26/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5317a0332397c2e24d3c96aa08fa1f16038b7d547bd3afda776b1fc63b6420
3
+ size 1064
checkpoint-26/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-26/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-26/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "PreTrainedTokenizerFast",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
checkpoint-26/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7328296703296704,
3
+ "best_model_checkpoint": "./priority_model\\checkpoint-13",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 26,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7692307692307693,
13
+ "grad_norm": 4.372110366821289,
14
+ "learning_rate": 1.7435897435897438e-05,
15
+ "loss": 1.0904,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7307692307692307,
21
+ "eval_f1": 0.7328296703296704,
22
+ "eval_loss": 0.8845496773719788,
23
+ "eval_runtime": 0.065,
24
+ "eval_samples_per_second": 799.398,
25
+ "eval_steps_per_second": 61.492,
26
+ "step": 13
27
+ },
28
+ {
29
+ "epoch": 1.5384615384615383,
30
+ "grad_norm": 4.574769973754883,
31
+ "learning_rate": 1.4871794871794874e-05,
32
+ "loss": 0.8551,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.6730769230769231,
38
+ "eval_f1": 0.6639957264957265,
39
+ "eval_loss": 0.777785062789917,
40
+ "eval_runtime": 0.062,
41
+ "eval_samples_per_second": 838.712,
42
+ "eval_steps_per_second": 64.516,
43
+ "step": 26
44
+ }
45
+ ],
46
+ "logging_steps": 10,
47
+ "max_steps": 78,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 6,
50
+ "save_steps": 500,
51
+ "total_flos": 19147667860440.0,
52
+ "train_batch_size": 16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-26/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b3df75f302017e957ecfc3937821ef6f12e7d4c8200fb79b1323498df9e15a
3
+ size 4920
checkpoint-28/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pysentimiento/robertuito-base-uncased",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "alta",
16
+ "1": "baja",
17
+ "2": "media"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "alta": 0,
23
+ "baja": 1,
24
+ "media": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 130,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.1",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 30000
39
+ }
checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b2bd02a335f5a3a8c4bdd5d3a74a97ff80001534010039d717df39b7d74439
3
+ size 435182156
checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1759d67710dfd16da0debaea95a223dbcb542cafee01a413b5e3764c94ab0099
3
+ size 870484154
checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0046987cdbe643f67d2d8b570ecbc8787b7e4a6967a282eee47a2b2c34ea5258
3
+ size 14244
checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24dc3b9b1a672e4aa6927b0896df357968a007aa7c1ba1caf9da4006ec0cad26
3
+ size 1064
checkpoint-28/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-28/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-28/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "PreTrainedTokenizerFast",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
checkpoint-28/trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7699889219082452,
3
+ "best_model_checkpoint": "./priority_model\\checkpoint-28",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 28,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7142857142857143,
13
+ "grad_norm": 4.813197135925293,
14
+ "learning_rate": 1.761904761904762e-05,
15
+ "loss": 1.0447,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.6981132075471698,
21
+ "eval_f1": 0.6908805031446541,
22
+ "eval_loss": 0.8730468153953552,
23
+ "eval_runtime": 0.073,
24
+ "eval_samples_per_second": 726.021,
25
+ "eval_steps_per_second": 54.794,
26
+ "step": 14
27
+ },
28
+ {
29
+ "epoch": 1.4285714285714286,
30
+ "grad_norm": 5.208207130432129,
31
+ "learning_rate": 1.5476190476190476e-05,
32
+ "loss": 0.9076,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.7735849056603774,
38
+ "eval_f1": 0.7699889219082452,
39
+ "eval_loss": 0.6862769722938538,
40
+ "eval_runtime": 0.063,
41
+ "eval_samples_per_second": 841.277,
42
+ "eval_steps_per_second": 63.493,
43
+ "step": 28
44
+ }
45
+ ],
46
+ "logging_steps": 10,
47
+ "max_steps": 84,
48
+ "num_input_tokens_seen": 0,
49
+ "num_train_epochs": 6,
50
+ "save_steps": 500,
51
+ "total_flos": 19332669482280.0,
52
+ "train_batch_size": 16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b3df75f302017e957ecfc3937821ef6f12e7d4c8200fb79b1323498df9e15a
3
+ size 4920
checkpoint-39/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pysentimiento/robertuito-base-uncased",
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
+ "gradient_checkpointing": false,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 768,
14
+ "id2label": {
15
+ "0": "alta",
16
+ "1": "baja",
17
+ "2": "media"
18
+ },
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 3072,
21
+ "label2id": {
22
+ "alta": 0,
23
+ "baja": 1,
24
+ "media": 2
25
+ },
26
+ "layer_norm_eps": 1e-12,
27
+ "max_position_embeddings": 130,
28
+ "model_type": "roberta",
29
+ "num_attention_heads": 12,
30
+ "num_hidden_layers": 12,
31
+ "pad_token_id": 1,
32
+ "position_embedding_type": "absolute",
33
+ "problem_type": "single_label_classification",
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.40.1",
36
+ "type_vocab_size": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 30000
39
+ }
checkpoint-39/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62235655d7a62fb49ac0de71f88018dd31f7d21ac9bcae2fe0a8c18800194e4
3
+ size 435182156
checkpoint-39/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee8ad63338b3fa9aa1ea7d2f212c1fd03a1e8343bd05f41c7b8b8b1994dbf70
3
+ size 870484154
checkpoint-39/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb9177fbb90f4a88e6aa0b1c202499a1428672d1bfc84c9dbce0e46bd1733e2
3
+ size 14244
checkpoint-39/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b2e202c170896819fe5c8705d592f734857e399294fb0b675ea3405da128d09
3
+ size 1064
checkpoint-39/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-39/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-39/tokenizer_config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "mask_token": "<mask>",
49
+ "max_length": 128,
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_to_multiple_of": null,
52
+ "pad_token": "<pad>",
53
+ "pad_token_type_id": 0,
54
+ "padding_side": "right",
55
+ "sep_token": "</s>",
56
+ "stride": 0,
57
+ "tokenizer_class": "PreTrainedTokenizerFast",
58
+ "truncation_side": "right",
59
+ "truncation_strategy": "longest_first",
60
+ "unk_token": "<unk>"
61
+ }
checkpoint-39/trainer_state.json ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7328296703296704,
3
+ "best_model_checkpoint": "./priority_model\\checkpoint-13",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 39,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7692307692307693,
13
+ "grad_norm": 4.372110366821289,
14
+ "learning_rate": 1.7435897435897438e-05,
15
+ "loss": 1.0904,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.7307692307692307,
21
+ "eval_f1": 0.7328296703296704,
22
+ "eval_loss": 0.8845496773719788,
23
+ "eval_runtime": 0.065,
24
+ "eval_samples_per_second": 799.398,
25
+ "eval_steps_per_second": 61.492,
26
+ "step": 13
27
+ },
28
+ {
29
+ "epoch": 1.5384615384615383,
30
+ "grad_norm": 4.574769973754883,
31
+ "learning_rate": 1.4871794871794874e-05,
32
+ "loss": 0.8551,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 2.0,
37
+ "eval_accuracy": 0.6730769230769231,
38
+ "eval_f1": 0.6639957264957265,
39
+ "eval_loss": 0.777785062789917,
40
+ "eval_runtime": 0.062,
41
+ "eval_samples_per_second": 838.712,
42
+ "eval_steps_per_second": 64.516,
43
+ "step": 26
44
+ },
45
+ {
46
+ "epoch": 2.3076923076923075,
47
+ "grad_norm": 4.142388820648193,
48
+ "learning_rate": 1.230769230769231e-05,
49
+ "loss": 0.6724,
50
+ "step": 30
51
+ },
52
+ {
53
+ "epoch": 3.0,
54
+ "eval_accuracy": 0.7307692307692307,
55
+ "eval_f1": 0.7262200165425973,
56
+ "eval_loss": 0.6311762928962708,
57
+ "eval_runtime": 0.062,
58
+ "eval_samples_per_second": 838.709,
59
+ "eval_steps_per_second": 64.516,
60
+ "step": 39
61
+ }
62
+ ],
63
+ "logging_steps": 10,
64
+ "max_steps": 78,
65
+ "num_input_tokens_seen": 0,
66
+ "num_train_epochs": 6,
67
+ "save_steps": 500,
68
+ "total_flos": 28721501790660.0,
69
+ "train_batch_size": 16,
70
+ "trial_name": null,
71
+ "trial_params": null
72
+ }
checkpoint-39/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3b3df75f302017e957ecfc3937821ef6f12e7d4c8200fb79b1323498df9e15a
3
+ size 4920