Upload folder using huggingface_hub
Browse files- training_checkpoints/checkpoint-10276/config.json +99 -0
- training_checkpoints/checkpoint-10276/merges.txt +0 -0
- training_checkpoints/checkpoint-10276/model.safetensors +3 -0
- training_checkpoints/checkpoint-10276/optimizer.pt +3 -0
- training_checkpoints/checkpoint-10276/rng_state.pth +3 -0
- training_checkpoints/checkpoint-10276/scheduler.pt +3 -0
- training_checkpoints/checkpoint-10276/special_tokens_map.json +15 -0
- training_checkpoints/checkpoint-10276/tokenizer.json +0 -0
- training_checkpoints/checkpoint-10276/tokenizer_config.json +57 -0
- training_checkpoints/checkpoint-10276/trainer_state.json +227 -0
- training_checkpoints/checkpoint-10276/training_args.bin +3 -0
- training_checkpoints/checkpoint-10276/vocab.json +0 -0
training_checkpoints/checkpoint-10276/config.json
ADDED
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-large",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForSequenceClassification"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_bos_token_id": 0,
|
28 |
+
"forced_eos_token_id": 2,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "Issue",
|
32 |
+
"1": "Court Discourse",
|
33 |
+
"2": "Conclusion",
|
34 |
+
"3": "Precedent Analysis",
|
35 |
+
"4": "Section Analysis",
|
36 |
+
"5": "Argument by Petitioner",
|
37 |
+
"6": "Fact",
|
38 |
+
"7": "Argument by Respondent",
|
39 |
+
"8": "Ratio",
|
40 |
+
"9": "Appellant",
|
41 |
+
"10": "Respondent",
|
42 |
+
"11": "Argument by Appellant",
|
43 |
+
"12": "Petitioner",
|
44 |
+
"13": "Judge",
|
45 |
+
"14": "Argument by Defendant"
|
46 |
+
},
|
47 |
+
"init_std": 0.02,
|
48 |
+
"is_encoder_decoder": true,
|
49 |
+
"label2id": {
|
50 |
+
"Appellant": 9,
|
51 |
+
"Argument by Appellant": 11,
|
52 |
+
"Argument by Defendant": 14,
|
53 |
+
"Argument by Petitioner": 5,
|
54 |
+
"Argument by Respondent": 7,
|
55 |
+
"Conclusion": 2,
|
56 |
+
"Court Discourse": 1,
|
57 |
+
"Fact": 6,
|
58 |
+
"Issue": 0,
|
59 |
+
"Judge": 13,
|
60 |
+
"Petitioner": 12,
|
61 |
+
"Precedent Analysis": 3,
|
62 |
+
"Ratio": 8,
|
63 |
+
"Respondent": 10,
|
64 |
+
"Section Analysis": 4
|
65 |
+
},
|
66 |
+
"max_position_embeddings": 1024,
|
67 |
+
"model_type": "bart",
|
68 |
+
"no_repeat_ngram_size": 3,
|
69 |
+
"normalize_before": false,
|
70 |
+
"num_beams": 4,
|
71 |
+
"num_hidden_layers": 12,
|
72 |
+
"pad_token_id": 1,
|
73 |
+
"problem_type": "single_label_classification",
|
74 |
+
"scale_embedding": false,
|
75 |
+
"task_specific_params": {
|
76 |
+
"summarization": {
|
77 |
+
"length_penalty": 1.0,
|
78 |
+
"max_length": 128,
|
79 |
+
"min_length": 12,
|
80 |
+
"num_beams": 4
|
81 |
+
},
|
82 |
+
"summarization_cnn": {
|
83 |
+
"length_penalty": 2.0,
|
84 |
+
"max_length": 142,
|
85 |
+
"min_length": 56,
|
86 |
+
"num_beams": 4
|
87 |
+
},
|
88 |
+
"summarization_xsum": {
|
89 |
+
"length_penalty": 1.0,
|
90 |
+
"max_length": 62,
|
91 |
+
"min_length": 11,
|
92 |
+
"num_beams": 6
|
93 |
+
}
|
94 |
+
},
|
95 |
+
"torch_dtype": "float32",
|
96 |
+
"transformers_version": "4.35.2",
|
97 |
+
"use_cache": true,
|
98 |
+
"vocab_size": 50265
|
99 |
+
}
|
training_checkpoints/checkpoint-10276/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_checkpoints/checkpoint-10276/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd321ab9923dede0b7b5c7812006157ed15d1cb7a923820e30dc77653922e607
|
3 |
+
size 1629486164
|
training_checkpoints/checkpoint-10276/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5962d752ecb5aa0e1cc26c1945d9058e4a97c43683ed17ce9d52e9f140b6f8d
|
3 |
+
size 3259283099
|
training_checkpoints/checkpoint-10276/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edfd711e53a5772fcacde3ddbbb2f3ce3f346e8ff64688a56a80d62c7fa0aba6
|
3 |
+
size 14244
|
training_checkpoints/checkpoint-10276/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c505cb517f3974c2167fb92d456378ce17b7340b73dc39fdf556985d37976b5
|
3 |
+
size 1064
|
training_checkpoints/checkpoint-10276/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": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
training_checkpoints/checkpoint-10276/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_checkpoints/checkpoint-10276/tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "<s>",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"cls_token": "<s>",
|
48 |
+
"eos_token": "</s>",
|
49 |
+
"errors": "replace",
|
50 |
+
"mask_token": "<mask>",
|
51 |
+
"model_max_length": 1024,
|
52 |
+
"pad_token": "<pad>",
|
53 |
+
"sep_token": "</s>",
|
54 |
+
"tokenizer_class": "BartTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": "<unk>"
|
57 |
+
}
|
training_checkpoints/checkpoint-10276/trainer_state.json
ADDED
@@ -0,0 +1,227 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.6233324855492023,
|
3 |
+
"best_model_checkpoint": "bart-large/checkpoint-10276",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 10276,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.19,
|
13 |
+
"learning_rate": 4.967886337096146e-05,
|
14 |
+
"loss": 2.0273,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.39,
|
19 |
+
"learning_rate": 4.9354482937589206e-05,
|
20 |
+
"loss": 1.4983,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.58,
|
25 |
+
"learning_rate": 4.903140002595043e-05,
|
26 |
+
"loss": 1.4727,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.78,
|
31 |
+
"learning_rate": 4.870701959257818e-05,
|
32 |
+
"loss": 1.3945,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.97,
|
37 |
+
"learning_rate": 4.8383287920072665e-05,
|
38 |
+
"loss": 1.1685,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.0,
|
43 |
+
"eval_accuracy": 0.6847405112316034,
|
44 |
+
"eval_f1_macro": 0.4296023125768376,
|
45 |
+
"eval_f1_micro": 0.6847405112316034,
|
46 |
+
"eval_f1_weighted": 0.6471198955620663,
|
47 |
+
"eval_loss": 1.258675456047058,
|
48 |
+
"eval_macro_fpr": 0.03310536835500512,
|
49 |
+
"eval_macro_sensitivity": 0.47197476920519743,
|
50 |
+
"eval_macro_specificity": 0.9759825618150952,
|
51 |
+
"eval_precision": 0.6359796796355663,
|
52 |
+
"eval_precision_macro": 0.4175869918662546,
|
53 |
+
"eval_recall": 0.6847405112316034,
|
54 |
+
"eval_recall_macro": 0.47197476920519743,
|
55 |
+
"eval_runtime": 166.2079,
|
56 |
+
"eval_samples_per_second": 7.767,
|
57 |
+
"eval_steps_per_second": 3.887,
|
58 |
+
"eval_weighted_fpr": 0.03183916138621607,
|
59 |
+
"eval_weighted_sensitivity": 0.6847405112316034,
|
60 |
+
"eval_weighted_specificity": 0.9549979159948256,
|
61 |
+
"step": 2569
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 1.17,
|
65 |
+
"learning_rate": 4.80589074867004e-05,
|
66 |
+
"loss": 1.2814,
|
67 |
+
"step": 3000
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 1.36,
|
71 |
+
"learning_rate": 4.7734527053328146e-05,
|
72 |
+
"loss": 1.2579,
|
73 |
+
"step": 3500
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 1.56,
|
77 |
+
"learning_rate": 4.741079538082263e-05,
|
78 |
+
"loss": 1.246,
|
79 |
+
"step": 4000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.75,
|
83 |
+
"learning_rate": 4.708641494745037e-05,
|
84 |
+
"loss": 1.0685,
|
85 |
+
"step": 4500
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 1.95,
|
89 |
+
"learning_rate": 4.676203451407811e-05,
|
90 |
+
"loss": 1.1965,
|
91 |
+
"step": 5000
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 2.0,
|
95 |
+
"eval_accuracy": 0.6638264910921766,
|
96 |
+
"eval_f1_macro": 0.3954707529203812,
|
97 |
+
"eval_f1_micro": 0.6638264910921766,
|
98 |
+
"eval_f1_weighted": 0.6467821848395333,
|
99 |
+
"eval_loss": 1.1623183488845825,
|
100 |
+
"eval_macro_fpr": 0.03422706134984445,
|
101 |
+
"eval_macro_sensitivity": 0.4261017849773373,
|
102 |
+
"eval_macro_specificity": 0.9752839802406176,
|
103 |
+
"eval_precision": 0.6943370263824146,
|
104 |
+
"eval_precision_macro": 0.45636498568634104,
|
105 |
+
"eval_recall": 0.6638264910921766,
|
106 |
+
"eval_recall_macro": 0.4261017849773373,
|
107 |
+
"eval_runtime": 320.2013,
|
108 |
+
"eval_samples_per_second": 4.032,
|
109 |
+
"eval_steps_per_second": 2.017,
|
110 |
+
"eval_weighted_fpr": 0.03490990990990991,
|
111 |
+
"eval_weighted_sensitivity": 0.6638264910921766,
|
112 |
+
"eval_weighted_specificity": 0.9654332125170877,
|
113 |
+
"step": 5138
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 2.14,
|
117 |
+
"learning_rate": 4.643765408070585e-05,
|
118 |
+
"loss": 1.0697,
|
119 |
+
"step": 5500
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 2.34,
|
123 |
+
"learning_rate": 4.611327364733359e-05,
|
124 |
+
"loss": 1.1042,
|
125 |
+
"step": 6000
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 2.53,
|
129 |
+
"learning_rate": 4.578954197482808e-05,
|
130 |
+
"loss": 1.124,
|
131 |
+
"step": 6500
|
132 |
+
},
|
133 |
+
{
|
134 |
+
"epoch": 2.72,
|
135 |
+
"learning_rate": 4.546516154145582e-05,
|
136 |
+
"loss": 1.1449,
|
137 |
+
"step": 7000
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 2.92,
|
141 |
+
"learning_rate": 4.514078110808356e-05,
|
142 |
+
"loss": 1.189,
|
143 |
+
"step": 7500
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 3.0,
|
147 |
+
"eval_accuracy": 0.7234701781564679,
|
148 |
+
"eval_f1_macro": 0.5196282925085354,
|
149 |
+
"eval_f1_micro": 0.7234701781564679,
|
150 |
+
"eval_f1_weighted": 0.7031290239201134,
|
151 |
+
"eval_loss": 1.357356309890747,
|
152 |
+
"eval_macro_fpr": 0.027073020005110214,
|
153 |
+
"eval_macro_sensitivity": 0.5527845991176076,
|
154 |
+
"eval_macro_specificity": 0.9790845865453512,
|
155 |
+
"eval_precision": 0.7219921821470505,
|
156 |
+
"eval_precision_macro": 0.5413306235947684,
|
157 |
+
"eval_recall": 0.7234701781564679,
|
158 |
+
"eval_recall_macro": 0.5527845991176076,
|
159 |
+
"eval_runtime": 290.3268,
|
160 |
+
"eval_samples_per_second": 4.447,
|
161 |
+
"eval_steps_per_second": 2.225,
|
162 |
+
"eval_weighted_fpr": 0.026576341844710787,
|
163 |
+
"eval_weighted_sensitivity": 0.7234701781564679,
|
164 |
+
"eval_weighted_specificity": 0.9627986200238022,
|
165 |
+
"step": 7707
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 3.11,
|
169 |
+
"learning_rate": 4.481704943557805e-05,
|
170 |
+
"loss": 0.9829,
|
171 |
+
"step": 8000
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 3.31,
|
175 |
+
"learning_rate": 4.4492669002205786e-05,
|
176 |
+
"loss": 0.9172,
|
177 |
+
"step": 8500
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 3.5,
|
181 |
+
"learning_rate": 4.416828856883353e-05,
|
182 |
+
"loss": 0.9911,
|
183 |
+
"step": 9000
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 3.7,
|
187 |
+
"learning_rate": 4.384390813546127e-05,
|
188 |
+
"loss": 0.9934,
|
189 |
+
"step": 9500
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 3.89,
|
193 |
+
"learning_rate": 4.351952770208901e-05,
|
194 |
+
"loss": 1.0127,
|
195 |
+
"step": 10000
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 4.0,
|
199 |
+
"eval_accuracy": 0.7668474051123161,
|
200 |
+
"eval_f1_macro": 0.6233324855492023,
|
201 |
+
"eval_f1_micro": 0.7668474051123161,
|
202 |
+
"eval_f1_weighted": 0.7569127961671379,
|
203 |
+
"eval_loss": 1.4684507846832275,
|
204 |
+
"eval_macro_fpr": 0.022371017412255348,
|
205 |
+
"eval_macro_sensitivity": 0.6201844239757082,
|
206 |
+
"eval_macro_specificity": 0.9821444214871504,
|
207 |
+
"eval_precision": 0.7584494799967734,
|
208 |
+
"eval_precision_macro": 0.6670503035550461,
|
209 |
+
"eval_recall": 0.7668474051123161,
|
210 |
+
"eval_recall_macro": 0.6201844239757082,
|
211 |
+
"eval_runtime": 296.0277,
|
212 |
+
"eval_samples_per_second": 4.361,
|
213 |
+
"eval_steps_per_second": 2.182,
|
214 |
+
"eval_weighted_fpr": 0.021255561047948592,
|
215 |
+
"eval_weighted_sensitivity": 0.7668474051123161,
|
216 |
+
"eval_weighted_specificity": 0.9653189171949409,
|
217 |
+
"step": 10276
|
218 |
+
}
|
219 |
+
],
|
220 |
+
"logging_steps": 500,
|
221 |
+
"max_steps": 77070,
|
222 |
+
"num_train_epochs": 30,
|
223 |
+
"save_steps": 500,
|
224 |
+
"total_flos": 2.233640488026931e+16,
|
225 |
+
"trial_name": null,
|
226 |
+
"trial_params": null
|
227 |
+
}
|
training_checkpoints/checkpoint-10276/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6e37f60a60daa651d8e7f2ff3947107bcf8c19f622a0416af7b872e6562bd538
|
3 |
+
size 4600
|
training_checkpoints/checkpoint-10276/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|