chizhik
commited on
Commit
·
fd81c91
1
Parent(s):
a5f7fa8
added updated model weights
Browse files- config.json +64 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +312 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Models/bio-bert-base-spanish-wwm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "LABEL_0",
|
14 |
+
"1": "LABEL_1",
|
15 |
+
"2": "LABEL_2",
|
16 |
+
"3": "LABEL_3",
|
17 |
+
"4": "LABEL_4",
|
18 |
+
"5": "LABEL_5",
|
19 |
+
"6": "LABEL_6",
|
20 |
+
"7": "LABEL_7",
|
21 |
+
"8": "LABEL_8",
|
22 |
+
"9": "LABEL_9",
|
23 |
+
"10": "LABEL_10",
|
24 |
+
"11": "LABEL_11",
|
25 |
+
"12": "LABEL_12",
|
26 |
+
"13": "LABEL_13",
|
27 |
+
"14": "LABEL_14",
|
28 |
+
"15": "LABEL_15"
|
29 |
+
},
|
30 |
+
"initializer_range": 0.02,
|
31 |
+
"intermediate_size": 3072,
|
32 |
+
"label2id": {
|
33 |
+
"LABEL_0": 0,
|
34 |
+
"LABEL_1": 1,
|
35 |
+
"LABEL_10": 10,
|
36 |
+
"LABEL_11": 11,
|
37 |
+
"LABEL_12": 12,
|
38 |
+
"LABEL_13": 13,
|
39 |
+
"LABEL_14": 14,
|
40 |
+
"LABEL_15": 15,
|
41 |
+
"LABEL_2": 2,
|
42 |
+
"LABEL_3": 3,
|
43 |
+
"LABEL_4": 4,
|
44 |
+
"LABEL_5": 5,
|
45 |
+
"LABEL_6": 6,
|
46 |
+
"LABEL_7": 7,
|
47 |
+
"LABEL_8": 8,
|
48 |
+
"LABEL_9": 9
|
49 |
+
},
|
50 |
+
"layer_norm_eps": 1e-12,
|
51 |
+
"max_position_embeddings": 512,
|
52 |
+
"model_type": "bert",
|
53 |
+
"num_attention_heads": 12,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"output_past": true,
|
56 |
+
"pad_token_id": 1,
|
57 |
+
"position_embedding_type": "absolute",
|
58 |
+
"problem_type": "multi_label_classification",
|
59 |
+
"torch_dtype": "float32",
|
60 |
+
"transformers_version": "4.19.2",
|
61 |
+
"type_vocab_size": 2,
|
62 |
+
"use_cache": true,
|
63 |
+
"vocab_size": 38468
|
64 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0103645d5238bcb778b35c2824a75ea14df52a5d1ca8f63d459afc3d5e85b14b
|
3 |
+
size 924893085
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44f222b4ff2590dd569bf9514d0d4dd8041986c6f7f873e806c7331078d28a2d
|
3 |
+
size 462459309
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c55efde8c43192f9ebfd10429b6dd25e1fb3b68a3f3f8425f98d0b4dddee3a67
|
3 |
+
size 14567
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93585dd7fdae2ab5eced8160060697e84df90b6641ec48615080b3af11c23cb6
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "do_basic_tokenize": true, "never_split": null, "model_max_length": 512, "special_tokens_map_file": "Models/bio-bert-base-spanish-wwm-uncased/special_tokens_map.json", "name_or_path": "Models/bio-bert-base-spanish-wwm-uncased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,312 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.5278386153994516,
|
3 |
+
"best_model_checkpoint": "./CARES/checkpoints/bio-ber/checkpoint-2679",
|
4 |
+
"epoch": 19.0,
|
5 |
+
"global_step": 2679,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"eval_loss": 0.2276119738817215,
|
13 |
+
"eval_macro_f1": 0.09383679038919833,
|
14 |
+
"eval_macro_precision": 0.12681117070705897,
|
15 |
+
"eval_macro_recall": 0.07667770066244797,
|
16 |
+
"eval_micro_f1": 0.36897880539499034,
|
17 |
+
"eval_micro_precision": 0.7053406998158379,
|
18 |
+
"eval_micro_recall": 0.24983692106979777,
|
19 |
+
"eval_runtime": 2.8509,
|
20 |
+
"eval_samples_per_second": 338.842,
|
21 |
+
"eval_steps_per_second": 21.397,
|
22 |
+
"step": 141
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"eval_loss": 0.19956032931804657,
|
27 |
+
"eval_macro_f1": 0.13389070512548568,
|
28 |
+
"eval_macro_precision": 0.1949068871295339,
|
29 |
+
"eval_macro_recall": 0.11313811988335658,
|
30 |
+
"eval_micro_f1": 0.4958460865763008,
|
31 |
+
"eval_micro_precision": 0.7519893899204244,
|
32 |
+
"eval_micro_recall": 0.3698630136986301,
|
33 |
+
"eval_runtime": 2.8244,
|
34 |
+
"eval_samples_per_second": 342.022,
|
35 |
+
"eval_steps_per_second": 21.598,
|
36 |
+
"step": 282
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"eval_loss": 0.18670037388801575,
|
41 |
+
"eval_macro_f1": 0.22751166658204755,
|
42 |
+
"eval_macro_precision": 0.46178526182432433,
|
43 |
+
"eval_macro_recall": 0.18375879789138674,
|
44 |
+
"eval_micro_f1": 0.5680033071517155,
|
45 |
+
"eval_micro_precision": 0.7753950338600452,
|
46 |
+
"eval_micro_recall": 0.4481409001956947,
|
47 |
+
"eval_runtime": 2.8618,
|
48 |
+
"eval_samples_per_second": 337.545,
|
49 |
+
"eval_steps_per_second": 21.315,
|
50 |
+
"step": 423
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.55,
|
54 |
+
"learning_rate": 4.822695035460993e-05,
|
55 |
+
"loss": 0.2081,
|
56 |
+
"step": 500
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_loss": 0.18518751859664917,
|
61 |
+
"eval_macro_f1": 0.34478852490640566,
|
62 |
+
"eval_macro_precision": 0.5134144581169723,
|
63 |
+
"eval_macro_recall": 0.2886504191522892,
|
64 |
+
"eval_micro_f1": 0.6130150173276858,
|
65 |
+
"eval_micro_precision": 0.7481203007518797,
|
66 |
+
"eval_micro_recall": 0.5192433137638617,
|
67 |
+
"eval_runtime": 2.8317,
|
68 |
+
"eval_samples_per_second": 341.135,
|
69 |
+
"eval_steps_per_second": 21.542,
|
70 |
+
"step": 564
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.0,
|
74 |
+
"eval_loss": 0.18300610780715942,
|
75 |
+
"eval_macro_f1": 0.4238271955718499,
|
76 |
+
"eval_macro_precision": 0.6346282008083806,
|
77 |
+
"eval_macro_recall": 0.36978265721033565,
|
78 |
+
"eval_micro_f1": 0.6232315711094564,
|
79 |
+
"eval_micro_precision": 0.7259323503902863,
|
80 |
+
"eval_micro_recall": 0.5459882583170255,
|
81 |
+
"eval_runtime": 2.8313,
|
82 |
+
"eval_samples_per_second": 341.185,
|
83 |
+
"eval_steps_per_second": 21.545,
|
84 |
+
"step": 705
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 0.18070942163467407,
|
89 |
+
"eval_macro_f1": 0.427572174915214,
|
90 |
+
"eval_macro_precision": 0.5867883838688037,
|
91 |
+
"eval_macro_recall": 0.3661335629128818,
|
92 |
+
"eval_micro_f1": 0.6416332482683194,
|
93 |
+
"eval_micro_precision": 0.7272727272727273,
|
94 |
+
"eval_micro_recall": 0.5740378343118069,
|
95 |
+
"eval_runtime": 2.822,
|
96 |
+
"eval_samples_per_second": 342.307,
|
97 |
+
"eval_steps_per_second": 21.616,
|
98 |
+
"step": 846
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 0.18207068741321564,
|
103 |
+
"eval_macro_f1": 0.47285593173212287,
|
104 |
+
"eval_macro_precision": 0.5718512640389848,
|
105 |
+
"eval_macro_recall": 0.4270343269721778,
|
106 |
+
"eval_micro_f1": 0.6605374823196605,
|
107 |
+
"eval_micro_precision": 0.7212355212355213,
|
108 |
+
"eval_micro_recall": 0.6092628832354859,
|
109 |
+
"eval_runtime": 2.8204,
|
110 |
+
"eval_samples_per_second": 342.507,
|
111 |
+
"eval_steps_per_second": 21.628,
|
112 |
+
"step": 987
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 7.09,
|
116 |
+
"learning_rate": 4.645390070921986e-05,
|
117 |
+
"loss": 0.115,
|
118 |
+
"step": 1000
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 8.0,
|
122 |
+
"eval_loss": 0.18614797294139862,
|
123 |
+
"eval_macro_f1": 0.48637001730423257,
|
124 |
+
"eval_macro_precision": 0.6057345339339811,
|
125 |
+
"eval_macro_recall": 0.4271528815196963,
|
126 |
+
"eval_micro_f1": 0.6618128867855844,
|
127 |
+
"eval_micro_precision": 0.7487644151565074,
|
128 |
+
"eval_micro_recall": 0.5929549902152642,
|
129 |
+
"eval_runtime": 2.8241,
|
130 |
+
"eval_samples_per_second": 342.057,
|
131 |
+
"eval_steps_per_second": 21.6,
|
132 |
+
"step": 1128
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 9.0,
|
136 |
+
"eval_loss": 0.18139992654323578,
|
137 |
+
"eval_macro_f1": 0.4968758987364566,
|
138 |
+
"eval_macro_precision": 0.6188063911104451,
|
139 |
+
"eval_macro_recall": 0.4425857583556203,
|
140 |
+
"eval_micro_f1": 0.6716259298618491,
|
141 |
+
"eval_micro_precision": 0.7348837209302326,
|
142 |
+
"eval_micro_recall": 0.6183953033268101,
|
143 |
+
"eval_runtime": 2.8195,
|
144 |
+
"eval_samples_per_second": 342.612,
|
145 |
+
"eval_steps_per_second": 21.635,
|
146 |
+
"step": 1269
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 10.0,
|
150 |
+
"eval_loss": 0.19238035380840302,
|
151 |
+
"eval_macro_f1": 0.4762674411195111,
|
152 |
+
"eval_macro_precision": 0.5687316855202853,
|
153 |
+
"eval_macro_recall": 0.42920385227971614,
|
154 |
+
"eval_micro_f1": 0.6690066690066689,
|
155 |
+
"eval_micro_precision": 0.7241641337386018,
|
156 |
+
"eval_micro_recall": 0.6216568819308546,
|
157 |
+
"eval_runtime": 2.8152,
|
158 |
+
"eval_samples_per_second": 343.137,
|
159 |
+
"eval_steps_per_second": 21.668,
|
160 |
+
"step": 1410
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 10.64,
|
164 |
+
"learning_rate": 4.468085106382979e-05,
|
165 |
+
"loss": 0.0668,
|
166 |
+
"step": 1500
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 11.0,
|
170 |
+
"eval_loss": 0.20003741979599,
|
171 |
+
"eval_macro_f1": 0.5041732295700452,
|
172 |
+
"eval_macro_precision": 0.5819236883447072,
|
173 |
+
"eval_macro_recall": 0.458955350441925,
|
174 |
+
"eval_micro_f1": 0.6811645036829183,
|
175 |
+
"eval_micro_precision": 0.7367223065250379,
|
176 |
+
"eval_micro_recall": 0.6333985649054142,
|
177 |
+
"eval_runtime": 2.8186,
|
178 |
+
"eval_samples_per_second": 342.72,
|
179 |
+
"eval_steps_per_second": 21.642,
|
180 |
+
"step": 1551
|
181 |
+
},
|
182 |
+
{
|
183 |
+
"epoch": 12.0,
|
184 |
+
"eval_loss": 0.21071653068065643,
|
185 |
+
"eval_macro_f1": 0.5060970351192071,
|
186 |
+
"eval_macro_precision": 0.6216233664621571,
|
187 |
+
"eval_macro_recall": 0.46859394229849854,
|
188 |
+
"eval_micro_f1": 0.6627946703108984,
|
189 |
+
"eval_micro_precision": 0.6958393113342898,
|
190 |
+
"eval_micro_recall": 0.6327462491846053,
|
191 |
+
"eval_runtime": 2.817,
|
192 |
+
"eval_samples_per_second": 342.914,
|
193 |
+
"eval_steps_per_second": 21.654,
|
194 |
+
"step": 1692
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 13.0,
|
198 |
+
"eval_loss": 0.20960789918899536,
|
199 |
+
"eval_macro_f1": 0.5055202034151333,
|
200 |
+
"eval_macro_precision": 0.6090230781362929,
|
201 |
+
"eval_macro_recall": 0.450320346412875,
|
202 |
+
"eval_micro_f1": 0.6799041424169804,
|
203 |
+
"eval_micro_precision": 0.7154178674351584,
|
204 |
+
"eval_micro_recall": 0.6477495107632094,
|
205 |
+
"eval_runtime": 4.7452,
|
206 |
+
"eval_samples_per_second": 203.576,
|
207 |
+
"eval_steps_per_second": 12.855,
|
208 |
+
"step": 1833
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 14.0,
|
212 |
+
"eval_loss": 0.21599768102169037,
|
213 |
+
"eval_macro_f1": 0.5190622646217878,
|
214 |
+
"eval_macro_precision": 0.6551140465404754,
|
215 |
+
"eval_macro_recall": 0.47196058443148803,
|
216 |
+
"eval_micro_f1": 0.6803764377831997,
|
217 |
+
"eval_micro_precision": 0.7305389221556886,
|
218 |
+
"eval_micro_recall": 0.6366601435094585,
|
219 |
+
"eval_runtime": 2.819,
|
220 |
+
"eval_samples_per_second": 342.677,
|
221 |
+
"eval_steps_per_second": 21.639,
|
222 |
+
"step": 1974
|
223 |
+
},
|
224 |
+
{
|
225 |
+
"epoch": 14.18,
|
226 |
+
"learning_rate": 4.2907801418439716e-05,
|
227 |
+
"loss": 0.0365,
|
228 |
+
"step": 2000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 15.0,
|
232 |
+
"eval_loss": 0.21732226014137268,
|
233 |
+
"eval_macro_f1": 0.4982722788861393,
|
234 |
+
"eval_macro_precision": 0.5812880908852627,
|
235 |
+
"eval_macro_recall": 0.46102462821831114,
|
236 |
+
"eval_micro_f1": 0.6856754921928038,
|
237 |
+
"eval_micro_precision": 0.7147912243453645,
|
238 |
+
"eval_micro_recall": 0.6588388780169602,
|
239 |
+
"eval_runtime": 2.837,
|
240 |
+
"eval_samples_per_second": 340.498,
|
241 |
+
"eval_steps_per_second": 21.501,
|
242 |
+
"step": 2115
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 16.0,
|
246 |
+
"eval_loss": 0.23044872283935547,
|
247 |
+
"eval_macro_f1": 0.5067733640623313,
|
248 |
+
"eval_macro_precision": 0.6404358198207177,
|
249 |
+
"eval_macro_recall": 0.46429191921900426,
|
250 |
+
"eval_micro_f1": 0.6748382703438883,
|
251 |
+
"eval_micro_precision": 0.7058404558404558,
|
252 |
+
"eval_micro_recall": 0.6464448793215917,
|
253 |
+
"eval_runtime": 2.8419,
|
254 |
+
"eval_samples_per_second": 339.909,
|
255 |
+
"eval_steps_per_second": 21.464,
|
256 |
+
"step": 2256
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 17.0,
|
260 |
+
"eval_loss": 0.23040802776813507,
|
261 |
+
"eval_macro_f1": 0.5182045437347171,
|
262 |
+
"eval_macro_precision": 0.6102649650627312,
|
263 |
+
"eval_macro_recall": 0.474946805831835,
|
264 |
+
"eval_micro_f1": 0.6864349011588274,
|
265 |
+
"eval_micro_precision": 0.7187723054960742,
|
266 |
+
"eval_micro_recall": 0.6568819308545336,
|
267 |
+
"eval_runtime": 2.8516,
|
268 |
+
"eval_samples_per_second": 338.756,
|
269 |
+
"eval_steps_per_second": 21.391,
|
270 |
+
"step": 2397
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 17.73,
|
274 |
+
"learning_rate": 4.1134751773049644e-05,
|
275 |
+
"loss": 0.021,
|
276 |
+
"step": 2500
|
277 |
+
},
|
278 |
+
{
|
279 |
+
"epoch": 18.0,
|
280 |
+
"eval_loss": 0.23820702731609344,
|
281 |
+
"eval_macro_f1": 0.5109008179961498,
|
282 |
+
"eval_macro_precision": 0.6241805280991644,
|
283 |
+
"eval_macro_recall": 0.4711108204223084,
|
284 |
+
"eval_micro_f1": 0.6758481692979509,
|
285 |
+
"eval_micro_precision": 0.6966759002770083,
|
286 |
+
"eval_micro_recall": 0.6562296151337247,
|
287 |
+
"eval_runtime": 2.8209,
|
288 |
+
"eval_samples_per_second": 342.448,
|
289 |
+
"eval_steps_per_second": 21.625,
|
290 |
+
"step": 2538
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 19.0,
|
294 |
+
"eval_loss": 0.23519271612167358,
|
295 |
+
"eval_macro_f1": 0.5278386153994516,
|
296 |
+
"eval_macro_precision": 0.6066088954753265,
|
297 |
+
"eval_macro_recall": 0.48873540160049156,
|
298 |
+
"eval_micro_f1": 0.6875645883568722,
|
299 |
+
"eval_micro_precision": 0.7284671532846715,
|
300 |
+
"eval_micro_recall": 0.6510110893672537,
|
301 |
+
"eval_runtime": 2.8218,
|
302 |
+
"eval_samples_per_second": 342.33,
|
303 |
+
"eval_steps_per_second": 21.617,
|
304 |
+
"step": 2679
|
305 |
+
}
|
306 |
+
],
|
307 |
+
"max_steps": 14100,
|
308 |
+
"num_train_epochs": 100,
|
309 |
+
"total_flos": 1.0688023305003456e+16,
|
310 |
+
"trial_name": null,
|
311 |
+
"trial_params": null
|
312 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2a1147ed9cfb8d56c0709711a5e7f2cc6001c6110bc1058d46761f68db1f8cd
|
3 |
+
size 3183
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|