Hugging Face's logo

Riyagarg01
/
spacy

Model card Files
xet
Community
Riyagarg01 commited on
Commit
0f577d4
·
1 Parent(s): b64fb2f

spacy

Browse files
Files changed (37) hide show
  1. checkpoint-1000/config.json +74 -0
  2. checkpoint-1000/merges.txt +0 -0
  3. checkpoint-1000/optimizer.pt +3 -0
  4. checkpoint-1000/pytorch_model.bin +3 -0
  5. checkpoint-1000/rng_state.pth +3 -0
  6. checkpoint-1000/scheduler.pt +3 -0
  7. checkpoint-1000/special_tokens_map.json +1 -0
  8. checkpoint-1000/tokenizer.json +0 -0
  9. checkpoint-1000/tokenizer_config.json +1 -0
  10. checkpoint-1000/trainer_state.json +136 -0
  11. checkpoint-1000/training_args.bin +3 -0
  12. checkpoint-1000/vocab.json +0 -0
  13. checkpoint-1500/config.json +74 -0
  14. checkpoint-1500/merges.txt +0 -0
  15. checkpoint-1500/optimizer.pt +3 -0
  16. checkpoint-1500/pytorch_model.bin +3 -0
  17. checkpoint-1500/rng_state.pth +3 -0
  18. checkpoint-1500/scheduler.pt +3 -0
  19. checkpoint-1500/special_tokens_map.json +1 -0
  20. checkpoint-1500/tokenizer.json +0 -0
  21. checkpoint-1500/tokenizer_config.json +1 -0
  22. checkpoint-1500/trainer_state.json +196 -0
  23. checkpoint-1500/training_args.bin +3 -0
  24. checkpoint-1500/vocab.json +0 -0
  25. checkpoint-2000-1/.gitattributes +12 -0
  26. checkpoint-2000-1/config.json +3 -0
  27. checkpoint-2000-1/merges.txt +3 -0
  28. checkpoint-2000-1/optimizer.pt +3 -0
  29. checkpoint-2000-1/pytorch_model.bin +3 -0
  30. checkpoint-2000-1/rng_state.pth +3 -0
  31. checkpoint-2000-1/scheduler.pt +3 -0
  32. checkpoint-2000-1/special_tokens_map.json +3 -0
  33. checkpoint-2000-1/tokenizer.json +3 -0
  34. checkpoint-2000-1/tokenizer_config.json +3 -0
  35. checkpoint-2000-1/trainer_state.json +3 -0
  36. checkpoint-2000-1/training_args.bin +3 -0
  37. checkpoint-2000-1/vocab.json +3 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mse30/bart-base-finetuned-pubmed",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.17.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
checkpoint-1000/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36ec792e4dcdb8a794796d541ba33aa8bd543b6c6d752f4c47df547366b43d5
3
+ size 1115513717
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d1629755823caf65256e2e9311db4a38eba4338e626d326f952c07c491170ae
3
+ size 557979897
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a1ac4fb60724cf55c33d5c41b2abc8d8fa12b65f770d27c139b17390deb99d3
3
+ size 14503
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775c4aec6449f5e7d3ee3006406a3bea769a332144a73dab9f817c45c25b9f77
3
+ size 623
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,136 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 45.45454545454545,
5
+ "global_step": 1000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "learning_rate": 3e-06,
13
+ "loss": 6.8118,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 4.55,
18
+ "learning_rate": 6e-06,
19
+ "loss": 3.4879,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 6.82,
24
+ "learning_rate": 9e-06,
25
+ "loss": 2.248,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 9.09,
30
+ "learning_rate": 1.2e-05,
31
+ "loss": 1.9166,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 11.36,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.76,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 13.64,
42
+ "learning_rate": 1.8e-05,
43
+ "loss": 1.6608,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 15.91,
48
+ "learning_rate": 2.1e-05,
49
+ "loss": 1.6117,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 18.18,
54
+ "learning_rate": 2.4e-05,
55
+ "loss": 1.5719,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 20.45,
60
+ "learning_rate": 2.7000000000000002e-05,
61
+ "loss": 1.548,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 22.73,
66
+ "learning_rate": 3e-05,
67
+ "loss": 1.5326,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 25.0,
72
+ "learning_rate": 2.911764705882353e-05,
73
+ "loss": 1.523,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 27.27,
78
+ "learning_rate": 2.823529411764706e-05,
79
+ "loss": 1.51,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 29.55,
84
+ "learning_rate": 2.735294117647059e-05,
85
+ "loss": 1.4927,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 31.82,
90
+ "learning_rate": 2.647058823529412e-05,
91
+ "loss": 1.4879,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 34.09,
96
+ "learning_rate": 2.5588235294117648e-05,
97
+ "loss": 1.48,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 36.36,
102
+ "learning_rate": 2.4705882352941174e-05,
103
+ "loss": 1.4764,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 38.64,
108
+ "learning_rate": 2.3823529411764704e-05,
109
+ "loss": 1.4716,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 40.91,
114
+ "learning_rate": 2.2941176470588233e-05,
115
+ "loss": 1.4668,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 43.18,
120
+ "learning_rate": 2.2058823529411766e-05,
121
+ "loss": 1.4688,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 45.45,
126
+ "learning_rate": 2.1176470588235296e-05,
127
+ "loss": 1.4633,
128
+ "step": 1000
129
+ }
130
+ ],
131
+ "max_steps": 2200,
132
+ "num_train_epochs": 100,
133
+ "total_flos": 2356631411097600.0,
134
+ "trial_name": null,
135
+ "trial_params": null
136
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f010161376860d44956735d3b51461f0f46c300ad48ada8df56e8a5a95dcd05e
3
+ size 3055
checkpoint-1000/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mse30/bart-base-finetuned-pubmed",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.17.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
checkpoint-1500/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2658f09806e71771479d24e528c281e385260ac981c9b3c7d8c2b978b76e8048
3
+ size 1115513717
checkpoint-1500/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7b13358eed1205a3248b1f48c2b61dbf050db12ec7d67f16fd4629470351cdf
3
+ size 557979897
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711f03dcc59b9f8dc08326df8cd11830f0cd9b6df1d2099fa4d515f414009d6f
3
+ size 14503
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948709ab58459baf217b15d02ea1a3614eb8668501108aef40a6eb529f12b000
3
+ size 623
checkpoint-1500/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-1500/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1500/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 68.18181818181819,
5
+ "global_step": 1500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "learning_rate": 3e-06,
13
+ "loss": 6.8118,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 4.55,
18
+ "learning_rate": 6e-06,
19
+ "loss": 3.4879,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 6.82,
24
+ "learning_rate": 9e-06,
25
+ "loss": 2.248,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 9.09,
30
+ "learning_rate": 1.2e-05,
31
+ "loss": 1.9166,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 11.36,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.76,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 13.64,
42
+ "learning_rate": 1.8e-05,
43
+ "loss": 1.6608,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 15.91,
48
+ "learning_rate": 2.1e-05,
49
+ "loss": 1.6117,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 18.18,
54
+ "learning_rate": 2.4e-05,
55
+ "loss": 1.5719,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 20.45,
60
+ "learning_rate": 2.7000000000000002e-05,
61
+ "loss": 1.548,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 22.73,
66
+ "learning_rate": 3e-05,
67
+ "loss": 1.5326,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 25.0,
72
+ "learning_rate": 2.911764705882353e-05,
73
+ "loss": 1.523,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 27.27,
78
+ "learning_rate": 2.823529411764706e-05,
79
+ "loss": 1.51,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 29.55,
84
+ "learning_rate": 2.735294117647059e-05,
85
+ "loss": 1.4927,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 31.82,
90
+ "learning_rate": 2.647058823529412e-05,
91
+ "loss": 1.4879,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 34.09,
96
+ "learning_rate": 2.5588235294117648e-05,
97
+ "loss": 1.48,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 36.36,
102
+ "learning_rate": 2.4705882352941174e-05,
103
+ "loss": 1.4764,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 38.64,
108
+ "learning_rate": 2.3823529411764704e-05,
109
+ "loss": 1.4716,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 40.91,
114
+ "learning_rate": 2.2941176470588233e-05,
115
+ "loss": 1.4668,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 43.18,
120
+ "learning_rate": 2.2058823529411766e-05,
121
+ "loss": 1.4688,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 45.45,
126
+ "learning_rate": 2.1176470588235296e-05,
127
+ "loss": 1.4633,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 47.73,
132
+ "learning_rate": 2.0294117647058825e-05,
133
+ "loss": 1.4587,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 50.0,
138
+ "learning_rate": 1.9411764705882355e-05,
139
+ "loss": 1.4592,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 52.27,
144
+ "learning_rate": 1.8529411764705884e-05,
145
+ "loss": 1.4636,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 54.55,
150
+ "learning_rate": 1.7647058823529414e-05,
151
+ "loss": 1.4552,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 56.82,
156
+ "learning_rate": 1.6764705882352943e-05,
157
+ "loss": 1.4535,
158
+ "step": 1250
159
+ },
160
+ {
161
+ "epoch": 59.09,
162
+ "learning_rate": 1.5882352941176473e-05,
163
+ "loss": 1.4515,
164
+ "step": 1300
165
+ },
166
+ {
167
+ "epoch": 61.36,
168
+ "learning_rate": 1.5e-05,
169
+ "loss": 1.4513,
170
+ "step": 1350
171
+ },
172
+ {
173
+ "epoch": 63.64,
174
+ "learning_rate": 1.411764705882353e-05,
175
+ "loss": 1.4495,
176
+ "step": 1400
177
+ },
178
+ {
179
+ "epoch": 65.91,
180
+ "learning_rate": 1.323529411764706e-05,
181
+ "loss": 1.4492,
182
+ "step": 1450
183
+ },
184
+ {
185
+ "epoch": 68.18,
186
+ "learning_rate": 1.2352941176470587e-05,
187
+ "loss": 1.4488,
188
+ "step": 1500
189
+ }
190
+ ],
191
+ "max_steps": 2200,
192
+ "num_train_epochs": 100,
193
+ "total_flos": 3534032511959040.0,
194
+ "trial_name": null,
195
+ "trial_params": null
196
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f010161376860d44956735d3b51461f0f46c300ad48ada8df56e8a5a95dcd05e
3
+ size 3055
checkpoint-1500/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000-1/.gitattributes ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
2
+ rng_state.pth filter=lfs diff=lfs merge=lfs -text
3
+ scheduler.pt filter=lfs diff=lfs merge=lfs -text
4
+ tokenizer_config.json filter=lfs diff=lfs merge=lfs -text
5
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
6
+ trainer_state.json filter=lfs diff=lfs merge=lfs -text
7
+ config.json filter=lfs diff=lfs merge=lfs -text
8
+ merges.txt filter=lfs diff=lfs merge=lfs -text
9
+ vocab.json filter=lfs diff=lfs merge=lfs -text
10
+ training_args.bin filter=lfs diff=lfs merge=lfs -text
11
+ optimizer.pt filter=lfs diff=lfs merge=lfs -text
12
+ special_tokens_map.json filter=lfs diff=lfs merge=lfs -text
checkpoint-2000-1/config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6fd11a5ca4aeaf55daffa2cbb033649547ebd1e0b4f069d877d0d8570cc61ec
3
+ size 1725
checkpoint-2000-1/merges.txt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe36cab26d4f4421ed725e10a2e9ddb7f799449c603a96e7f29b5a3c82a95862
3
+ size 456356
checkpoint-2000-1/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1737d39cc966b0e97a85cd3305f9a20d9f9229deb161129735316a8f54532a54
3
+ size 1115513717
checkpoint-2000-1/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f905f3c689b3f516a60655ddf78b9fcdc71de01558efda46f37879d1716ea856
3
+ size 557979897
checkpoint-2000-1/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd06c17946498bd195533f43686eea0b8f81a1cfcdeb9438b6f754f80e3dcb6
3
+ size 14503
checkpoint-2000-1/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b3c04811897c85d0bb1701f0f07ac9b7b37a57bd95a011e5a6e2f70a196485
3
+ size 623
checkpoint-2000-1/special_tokens_map.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:378eb3bf733eb16e65792d7e3fda5b8a4631387ca04d2015199c4d4f22ae554d
3
+ size 239
checkpoint-2000-1/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c10114c3062d3e9ab84a448abfb5166a8427946d8a3e5b99ecfac7313fe3091
3
+ size 2108810
checkpoint-2000-1/tokenizer_config.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7df4d29598704785c3b88424709232cf230dc77860344149055e3817fc0f94fc
3
+ size 367
checkpoint-2000-1/trainer_state.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75fccafa22ae5a356b8b607ea5db57b8e40601f88b54b46dc27f7cf0eca564e8
3
+ size 5076
checkpoint-2000-1/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f010161376860d44956735d3b51461f0f46c300ad48ada8df56e8a5a95dcd05e
3
+ size 3055
checkpoint-2000-1/vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed19656ea1707df69134c4af35c8ceda2cc9860bf2c3495026153a133670ab5e
3
+ size 798293