SjardiWillems commited on
Commit
f4f0e4d
·
verified ·
1 Parent(s): 384e934

Training in progress, epoch 1

Browse files
Files changed (36) hide show
  1. model.safetensors +1 -1
  2. run-1/checkpoint-144/config.json +31 -0
  3. run-1/checkpoint-144/model.safetensors +3 -0
  4. run-1/checkpoint-144/optimizer.pt +3 -0
  5. run-1/checkpoint-144/rng_state.pth +3 -0
  6. run-1/checkpoint-144/scheduler.pt +3 -0
  7. run-1/checkpoint-144/special_tokens_map.json +7 -0
  8. run-1/checkpoint-144/tokenizer.json +0 -0
  9. run-1/checkpoint-144/tokenizer_config.json +55 -0
  10. run-1/checkpoint-144/trainer_state.json +46 -0
  11. run-1/checkpoint-144/training_args.bin +3 -0
  12. run-1/checkpoint-144/vocab.txt +0 -0
  13. run-1/checkpoint-216/config.json +31 -0
  14. run-1/checkpoint-216/model.safetensors +3 -0
  15. run-1/checkpoint-216/optimizer.pt +3 -0
  16. run-1/checkpoint-216/rng_state.pth +3 -0
  17. run-1/checkpoint-216/scheduler.pt +3 -0
  18. run-1/checkpoint-216/special_tokens_map.json +7 -0
  19. run-1/checkpoint-216/tokenizer.json +0 -0
  20. run-1/checkpoint-216/tokenizer_config.json +55 -0
  21. run-1/checkpoint-216/trainer_state.json +56 -0
  22. run-1/checkpoint-216/training_args.bin +3 -0
  23. run-1/checkpoint-216/vocab.txt +0 -0
  24. run-2/checkpoint-36/config.json +31 -0
  25. run-2/checkpoint-36/model.safetensors +3 -0
  26. run-2/checkpoint-36/optimizer.pt +3 -0
  27. run-2/checkpoint-36/rng_state.pth +3 -0
  28. run-2/checkpoint-36/scheduler.pt +3 -0
  29. run-2/checkpoint-36/special_tokens_map.json +7 -0
  30. run-2/checkpoint-36/tokenizer.json +0 -0
  31. run-2/checkpoint-36/tokenizer_config.json +55 -0
  32. run-2/checkpoint-36/trainer_state.json +36 -0
  33. run-2/checkpoint-36/training_args.bin +3 -0
  34. run-2/checkpoint-36/vocab.txt +0 -0
  35. runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676059.fe13c9557656.828.4 +3 -0
  36. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca3ebf954bf47e16b3867b4027c95e69abd7b1d6aa47363214e7d3508b762595
3
  size 267829484
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671728f6a878097a1162c257e1aa353fdc9acdcc4c03611fb10c3b0d3c63851a
3
  size 267829484
run-1/checkpoint-144/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-1/checkpoint-144/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e573070d8a167ef5466bd3277aadce79399c2720a82a6bcb6baaa8b82c1c0ac
3
+ size 267829484
run-1/checkpoint-144/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36b873b6358e8d1f4e0c42d12ddfe8651852ebc41b194bcc7c5ee94291b14e0
3
+ size 535721146
run-1/checkpoint-144/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:979de324ed493d478b9d27827eb6a74778e519d2db38f25b2dd9a5438fef2eb2
3
+ size 14244
run-1/checkpoint-144/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9d771141c17552064fafe439559602cfdf33dc045e7fe767cd0669d0101bbda
3
+ size 1064
run-1/checkpoint-144/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-144/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-144/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-144/trainer_state.json ADDED
@@ -0,0 +1,46 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.6829116884344341,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-144",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 144,
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_loss": 2.2141971588134766,
14
+ "eval_pearson": 0.49554442333740484,
15
+ "eval_runtime": 0.9304,
16
+ "eval_samples_per_second": 1612.164,
17
+ "eval_spearmanr": 0.5246897691009283,
18
+ "eval_steps_per_second": 101.029,
19
+ "step": 72
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 1.4843738079071045,
24
+ "eval_pearson": 0.6829116884344341,
25
+ "eval_runtime": 0.9345,
26
+ "eval_samples_per_second": 1605.143,
27
+ "eval_spearmanr": 0.683701728621508,
28
+ "eval_steps_per_second": 100.589,
29
+ "step": 144
30
+ }
31
+ ],
32
+ "logging_steps": 500,
33
+ "max_steps": 216,
34
+ "num_input_tokens_seen": 0,
35
+ "num_train_epochs": 3,
36
+ "save_steps": 500,
37
+ "total_flos": 0,
38
+ "train_batch_size": 8,
39
+ "trial_name": null,
40
+ "trial_params": {
41
+ "learning_rate": 1.2713760898858066e-05,
42
+ "num_train_epochs": 3,
43
+ "per_device_train_batch_size": 8,
44
+ "seed": 30
45
+ }
46
+ }
run-1/checkpoint-144/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e19ef0ddd5d554387252f8727f426e5c782e9c195b5e4538a0a61f48d78d6d
3
+ size 4920
run-1/checkpoint-144/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-216/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-1/checkpoint-216/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ecb02520b46885f6d0d94c001c5e65c57101275dc4ac389751a7017b5c4dee3
3
+ size 267829484
run-1/checkpoint-216/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f3f92025af404fa176ce4e435fb7e4248408e81dd83a48dd47bee439d7c4d45
3
+ size 535721146
run-1/checkpoint-216/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc82f36fc74ec13604a19992dfc38b2a80ca17a75c6c58aff52a3d9642586dfe
3
+ size 14244
run-1/checkpoint-216/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58bbbe0c1c6d2f5ef31cde5f9323a9c8bbdabd4fd0caccde4a4b2e9fd8bc7ded
3
+ size 1064
run-1/checkpoint-216/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-1/checkpoint-216/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-1/checkpoint-216/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-1/checkpoint-216/trainer_state.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.7717462742529176,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-1/checkpoint-216",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 216,
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_loss": 2.2141971588134766,
14
+ "eval_pearson": 0.49554442333740484,
15
+ "eval_runtime": 0.9304,
16
+ "eval_samples_per_second": 1612.164,
17
+ "eval_spearmanr": 0.5246897691009283,
18
+ "eval_steps_per_second": 101.029,
19
+ "step": 72
20
+ },
21
+ {
22
+ "epoch": 2.0,
23
+ "eval_loss": 1.4843738079071045,
24
+ "eval_pearson": 0.6829116884344341,
25
+ "eval_runtime": 0.9345,
26
+ "eval_samples_per_second": 1605.143,
27
+ "eval_spearmanr": 0.683701728621508,
28
+ "eval_steps_per_second": 100.589,
29
+ "step": 144
30
+ },
31
+ {
32
+ "epoch": 3.0,
33
+ "eval_loss": 1.107965111732483,
34
+ "eval_pearson": 0.7717462742529176,
35
+ "eval_runtime": 0.9514,
36
+ "eval_samples_per_second": 1576.576,
37
+ "eval_spearmanr": 0.7677298469590466,
38
+ "eval_steps_per_second": 98.799,
39
+ "step": 216
40
+ }
41
+ ],
42
+ "logging_steps": 500,
43
+ "max_steps": 216,
44
+ "num_input_tokens_seen": 0,
45
+ "num_train_epochs": 3,
46
+ "save_steps": 500,
47
+ "total_flos": 0,
48
+ "train_batch_size": 8,
49
+ "trial_name": null,
50
+ "trial_params": {
51
+ "learning_rate": 1.2713760898858066e-05,
52
+ "num_train_epochs": 3,
53
+ "per_device_train_batch_size": 8,
54
+ "seed": 30
55
+ }
56
+ }
run-1/checkpoint-216/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56e19ef0ddd5d554387252f8727f426e5c782e9c195b5e4538a0a61f48d78d6d
3
+ size 4920
run-1/checkpoint-216/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-36/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "id2label": {
12
+ "0": "LABEL_0"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "label2id": {
16
+ "LABEL_0": 0
17
+ },
18
+ "max_position_embeddings": 512,
19
+ "model_type": "distilbert",
20
+ "n_heads": 12,
21
+ "n_layers": 6,
22
+ "pad_token_id": 0,
23
+ "problem_type": "regression",
24
+ "qa_dropout": 0.1,
25
+ "seq_classif_dropout": 0.2,
26
+ "sinusoidal_pos_embds": false,
27
+ "tie_weights_": true,
28
+ "torch_dtype": "float32",
29
+ "transformers_version": "4.38.2",
30
+ "vocab_size": 30522
31
+ }
run-2/checkpoint-36/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:671728f6a878097a1162c257e1aa353fdc9acdcc4c03611fb10c3b0d3c63851a
3
+ size 267829484
run-2/checkpoint-36/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:795d9d93b9cac620c1df794dd66411fdd87ac340b63b38d24d4017d323c0e3f9
3
+ size 535721146
run-2/checkpoint-36/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc36f5ba400419a91973422c57902c4174f8dd55889259959ee4a9d9cca1d43c
3
+ size 14308
run-2/checkpoint-36/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7e4d128f09cda8b7cac2cd33fa0e5bd01a27bcc9ee3ff3a5478fc58e9e0adb9
3
+ size 1064
run-2/checkpoint-36/special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
run-2/checkpoint-36/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
run-2/checkpoint-36/tokenizer_config.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_lower_case": true,
47
+ "mask_token": "[MASK]",
48
+ "model_max_length": 512,
49
+ "pad_token": "[PAD]",
50
+ "sep_token": "[SEP]",
51
+ "strip_accents": null,
52
+ "tokenize_chinese_chars": true,
53
+ "tokenizer_class": "DistilBertTokenizer",
54
+ "unk_token": "[UNK]"
55
+ }
run-2/checkpoint-36/trainer_state.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.32223422122729983,
3
+ "best_model_checkpoint": "distilbert-base-uncased-finetuned-stsb/run-2/checkpoint-36",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 36,
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_loss": 2.4969136714935303,
14
+ "eval_pearson": 0.32223422122729983,
15
+ "eval_runtime": 0.9052,
16
+ "eval_samples_per_second": 1657.071,
17
+ "eval_spearmanr": 0.32647520010278785,
18
+ "eval_steps_per_second": 103.843,
19
+ "step": 36
20
+ }
21
+ ],
22
+ "logging_steps": 500,
23
+ "max_steps": 180,
24
+ "num_input_tokens_seen": 0,
25
+ "num_train_epochs": 5,
26
+ "save_steps": 500,
27
+ "total_flos": 0,
28
+ "train_batch_size": 16,
29
+ "trial_name": null,
30
+ "trial_params": {
31
+ "learning_rate": 2.5099285971844188e-05,
32
+ "num_train_epochs": 5,
33
+ "per_device_train_batch_size": 16,
34
+ "seed": 8
35
+ }
36
+ }
run-2/checkpoint-36/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
3
+ size 4920
run-2/checkpoint-36/vocab.txt ADDED
The diff for this file is too large to render. See raw diff
 
runs/Mar05_21-56-47_fe13c9557656/events.out.tfevents.1709676059.fe13c9557656.828.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab88a6061645b0ff13f99c63c89e6e8e1a8bbf6cf48cc7c51af9e8cdfd38a162
3
+ size 6815
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56e19ef0ddd5d554387252f8727f426e5c782e9c195b5e4538a0a61f48d78d6d
3
  size 4920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12643df0525ba3f2bf5dee245df6a74c3697e1dda56998a9dd617f86119470b4
3
  size 4920