initial commit
Browse files- all_results.json +23 -0
- config.json +37 -0
- eval_results.json +12 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +14 -0
- trainer_state.json +461 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8373677786818552,
|
4 |
+
"eval_loss": 0.4427230954170227,
|
5 |
+
"eval_mem_cpu_alloc_delta": 262144,
|
6 |
+
"eval_mem_cpu_peaked_delta": 81920,
|
7 |
+
"eval_mem_gpu_alloc_delta": 0,
|
8 |
+
"eval_mem_gpu_peaked_delta": 94700544,
|
9 |
+
"eval_runtime": 51.4688,
|
10 |
+
"eval_samples": 9832,
|
11 |
+
"eval_samples_per_second": 191.028,
|
12 |
+
"init_mem_cpu_alloc_delta": 2093309952,
|
13 |
+
"init_mem_cpu_peaked_delta": 265920512,
|
14 |
+
"init_mem_gpu_alloc_delta": 329781248,
|
15 |
+
"init_mem_gpu_peaked_delta": 0,
|
16 |
+
"train_mem_cpu_alloc_delta": 729513984,
|
17 |
+
"train_mem_cpu_peaked_delta": 483684352,
|
18 |
+
"train_mem_gpu_alloc_delta": 1020158976,
|
19 |
+
"train_mem_gpu_peaked_delta": 2316007936,
|
20 |
+
"train_runtime": 10484.4187,
|
21 |
+
"train_samples": 392702,
|
22 |
+
"train_samples_per_second": 3.511
|
23 |
+
}
|
config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilroberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"finetuning_task": "mnli",
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "entailment",
|
16 |
+
"1": "neutral",
|
17 |
+
"2": "contradiction"
|
18 |
+
},
|
19 |
+
"initializer_range": 0.02,
|
20 |
+
"intermediate_size": 3072,
|
21 |
+
"label2id": {
|
22 |
+
"contradiction": 2,
|
23 |
+
"entailment": 0,
|
24 |
+
"neutral": 1
|
25 |
+
},
|
26 |
+
"layer_norm_eps": 1e-05,
|
27 |
+
"max_position_embeddings": 514,
|
28 |
+
"model_type": "roberta",
|
29 |
+
"num_attention_heads": 12,
|
30 |
+
"num_hidden_layers": 6,
|
31 |
+
"pad_token_id": 1,
|
32 |
+
"position_embedding_type": "absolute",
|
33 |
+
"transformers_version": "4.6.0.dev0",
|
34 |
+
"type_vocab_size": 1,
|
35 |
+
"use_cache": true,
|
36 |
+
"vocab_size": 50265
|
37 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"eval_accuracy": 0.8373677786818552,
|
4 |
+
"eval_loss": 0.4427230954170227,
|
5 |
+
"eval_mem_cpu_alloc_delta": 262144,
|
6 |
+
"eval_mem_cpu_peaked_delta": 81920,
|
7 |
+
"eval_mem_gpu_alloc_delta": 0,
|
8 |
+
"eval_mem_gpu_peaked_delta": 94700544,
|
9 |
+
"eval_runtime": 51.4688,
|
10 |
+
"eval_samples": 9832,
|
11 |
+
"eval_samples_per_second": 191.028
|
12 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ff3f7a8e6afb8f93309e6c03de7b51f6ef558d5a4432664d04d994d62715c95
|
3 |
+
size 328532073
|
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}}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base"}
|
train_results.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 3.0,
|
3 |
+
"init_mem_cpu_alloc_delta": 2093309952,
|
4 |
+
"init_mem_cpu_peaked_delta": 265920512,
|
5 |
+
"init_mem_gpu_alloc_delta": 329781248,
|
6 |
+
"init_mem_gpu_peaked_delta": 0,
|
7 |
+
"train_mem_cpu_alloc_delta": 729513984,
|
8 |
+
"train_mem_cpu_peaked_delta": 483684352,
|
9 |
+
"train_mem_gpu_alloc_delta": 1020158976,
|
10 |
+
"train_mem_gpu_peaked_delta": 2316007936,
|
11 |
+
"train_runtime": 10484.4187,
|
12 |
+
"train_samples": 392702,
|
13 |
+
"train_samples_per_second": 3.511
|
14 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,461 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.0,
|
5 |
+
"global_step": 36816,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 9.864189482833552e-06,
|
13 |
+
"loss": 0.9064,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.08,
|
18 |
+
"learning_rate": 9.728378965667103e-06,
|
19 |
+
"loss": 0.6939,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.12,
|
24 |
+
"learning_rate": 9.592568448500653e-06,
|
25 |
+
"loss": 0.6652,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.16,
|
30 |
+
"learning_rate": 9.456757931334203e-06,
|
31 |
+
"loss": 0.6331,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.2,
|
36 |
+
"learning_rate": 9.320947414167753e-06,
|
37 |
+
"loss": 0.6061,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.24,
|
42 |
+
"learning_rate": 9.185136897001304e-06,
|
43 |
+
"loss": 0.5958,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.29,
|
48 |
+
"learning_rate": 9.049326379834855e-06,
|
49 |
+
"loss": 0.588,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.33,
|
54 |
+
"learning_rate": 8.913515862668406e-06,
|
55 |
+
"loss": 0.5726,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.37,
|
60 |
+
"learning_rate": 8.777705345501957e-06,
|
61 |
+
"loss": 0.5618,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.41,
|
66 |
+
"learning_rate": 8.641894828335508e-06,
|
67 |
+
"loss": 0.5599,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.45,
|
72 |
+
"learning_rate": 8.506084311169057e-06,
|
73 |
+
"loss": 0.5557,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.49,
|
78 |
+
"learning_rate": 8.370273794002608e-06,
|
79 |
+
"loss": 0.5444,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.53,
|
84 |
+
"learning_rate": 8.234463276836159e-06,
|
85 |
+
"loss": 0.5423,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.57,
|
90 |
+
"learning_rate": 8.09865275966971e-06,
|
91 |
+
"loss": 0.5322,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.61,
|
96 |
+
"learning_rate": 7.96284224250326e-06,
|
97 |
+
"loss": 0.541,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.65,
|
102 |
+
"learning_rate": 7.827031725336811e-06,
|
103 |
+
"loss": 0.5284,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.69,
|
108 |
+
"learning_rate": 7.691221208170362e-06,
|
109 |
+
"loss": 0.524,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.73,
|
114 |
+
"learning_rate": 7.555410691003911e-06,
|
115 |
+
"loss": 0.5213,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.77,
|
120 |
+
"learning_rate": 7.419600173837462e-06,
|
121 |
+
"loss": 0.5153,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.81,
|
126 |
+
"learning_rate": 7.283789656671013e-06,
|
127 |
+
"loss": 0.5256,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.86,
|
132 |
+
"learning_rate": 7.147979139504564e-06,
|
133 |
+
"loss": 0.509,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.9,
|
138 |
+
"learning_rate": 7.012168622338115e-06,
|
139 |
+
"loss": 0.5088,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.94,
|
144 |
+
"learning_rate": 6.8763581051716655e-06,
|
145 |
+
"loss": 0.5053,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.98,
|
150 |
+
"learning_rate": 6.7405475880052155e-06,
|
151 |
+
"loss": 0.4892,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.02,
|
156 |
+
"learning_rate": 6.6047370708387655e-06,
|
157 |
+
"loss": 0.484,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.06,
|
162 |
+
"learning_rate": 6.468926553672316e-06,
|
163 |
+
"loss": 0.4504,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.1,
|
168 |
+
"learning_rate": 6.333116036505867e-06,
|
169 |
+
"loss": 0.4658,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.14,
|
174 |
+
"learning_rate": 6.197305519339418e-06,
|
175 |
+
"loss": 0.4468,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.18,
|
180 |
+
"learning_rate": 6.061495002172969e-06,
|
181 |
+
"loss": 0.4542,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.22,
|
186 |
+
"learning_rate": 5.92568448500652e-06,
|
187 |
+
"loss": 0.4555,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.26,
|
192 |
+
"learning_rate": 5.78987396784007e-06,
|
193 |
+
"loss": 0.4602,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.3,
|
198 |
+
"learning_rate": 5.65406345067362e-06,
|
199 |
+
"loss": 0.4465,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.34,
|
204 |
+
"learning_rate": 5.518252933507171e-06,
|
205 |
+
"loss": 0.4601,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.39,
|
210 |
+
"learning_rate": 5.382442416340722e-06,
|
211 |
+
"loss": 0.4595,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.43,
|
216 |
+
"learning_rate": 5.2466318991742724e-06,
|
217 |
+
"loss": 0.4534,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 1.47,
|
222 |
+
"learning_rate": 5.110821382007823e-06,
|
223 |
+
"loss": 0.4464,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 1.51,
|
228 |
+
"learning_rate": 4.975010864841373e-06,
|
229 |
+
"loss": 0.4398,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.55,
|
234 |
+
"learning_rate": 4.839200347674924e-06,
|
235 |
+
"loss": 0.4433,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 1.59,
|
240 |
+
"learning_rate": 4.703389830508475e-06,
|
241 |
+
"loss": 0.441,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 1.63,
|
246 |
+
"learning_rate": 4.567579313342025e-06,
|
247 |
+
"loss": 0.4479,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 1.67,
|
252 |
+
"learning_rate": 4.431768796175576e-06,
|
253 |
+
"loss": 0.4471,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 1.71,
|
258 |
+
"learning_rate": 4.295958279009127e-06,
|
259 |
+
"loss": 0.4431,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.75,
|
264 |
+
"learning_rate": 4.160147761842678e-06,
|
265 |
+
"loss": 0.4389,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.79,
|
270 |
+
"learning_rate": 4.024337244676228e-06,
|
271 |
+
"loss": 0.4404,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.83,
|
276 |
+
"learning_rate": 3.8885267275097785e-06,
|
277 |
+
"loss": 0.4431,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.87,
|
282 |
+
"learning_rate": 3.7527162103433294e-06,
|
283 |
+
"loss": 0.4343,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.91,
|
288 |
+
"learning_rate": 3.61690569317688e-06,
|
289 |
+
"loss": 0.4335,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.96,
|
294 |
+
"learning_rate": 3.4810951760104307e-06,
|
295 |
+
"loss": 0.4354,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.0,
|
300 |
+
"learning_rate": 3.3452846588439815e-06,
|
301 |
+
"loss": 0.4493,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 2.04,
|
306 |
+
"learning_rate": 3.2094741416775315e-06,
|
307 |
+
"loss": 0.3965,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 2.08,
|
312 |
+
"learning_rate": 3.0736636245110824e-06,
|
313 |
+
"loss": 0.4061,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 2.12,
|
318 |
+
"learning_rate": 2.9378531073446333e-06,
|
319 |
+
"loss": 0.4041,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 2.16,
|
324 |
+
"learning_rate": 2.8020425901781833e-06,
|
325 |
+
"loss": 0.3955,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 2.2,
|
330 |
+
"learning_rate": 2.666232073011734e-06,
|
331 |
+
"loss": 0.4015,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 2.24,
|
336 |
+
"learning_rate": 2.530421555845285e-06,
|
337 |
+
"loss": 0.3917,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.28,
|
342 |
+
"learning_rate": 2.3946110386788354e-06,
|
343 |
+
"loss": 0.397,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 2.32,
|
348 |
+
"learning_rate": 2.2588005215123863e-06,
|
349 |
+
"loss": 0.3925,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 2.36,
|
354 |
+
"learning_rate": 2.1229900043459367e-06,
|
355 |
+
"loss": 0.3933,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 2.4,
|
360 |
+
"learning_rate": 1.987179487179487e-06,
|
361 |
+
"loss": 0.404,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 2.44,
|
366 |
+
"learning_rate": 1.851368970013038e-06,
|
367 |
+
"loss": 0.4005,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 2.49,
|
372 |
+
"learning_rate": 1.7155584528465885e-06,
|
373 |
+
"loss": 0.405,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.53,
|
378 |
+
"learning_rate": 1.5797479356801393e-06,
|
379 |
+
"loss": 0.3949,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 2.57,
|
384 |
+
"learning_rate": 1.4439374185136898e-06,
|
385 |
+
"loss": 0.393,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 2.61,
|
390 |
+
"learning_rate": 1.3081269013472406e-06,
|
391 |
+
"loss": 0.3974,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 2.65,
|
396 |
+
"learning_rate": 1.172316384180791e-06,
|
397 |
+
"loss": 0.4052,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 2.69,
|
402 |
+
"learning_rate": 1.0365058670143417e-06,
|
403 |
+
"loss": 0.3938,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 2.73,
|
408 |
+
"learning_rate": 9.006953498478922e-07,
|
409 |
+
"loss": 0.3958,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 2.77,
|
414 |
+
"learning_rate": 7.648848326814429e-07,
|
415 |
+
"loss": 0.3917,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.81,
|
420 |
+
"learning_rate": 6.290743155149935e-07,
|
421 |
+
"loss": 0.4079,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 2.85,
|
426 |
+
"learning_rate": 4.932637983485442e-07,
|
427 |
+
"loss": 0.3902,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 2.89,
|
432 |
+
"learning_rate": 3.574532811820948e-07,
|
433 |
+
"loss": 0.3802,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 2.93,
|
438 |
+
"learning_rate": 2.216427640156454e-07,
|
439 |
+
"loss": 0.3934,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 2.97,
|
444 |
+
"learning_rate": 8.583224684919601e-08,
|
445 |
+
"loss": 0.4002,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 3.0,
|
450 |
+
"step": 36816,
|
451 |
+
"total_flos": 1275249174174720.0,
|
452 |
+
"train_runtime": 10484.4187,
|
453 |
+
"train_samples_per_second": 3.511
|
454 |
+
}
|
455 |
+
],
|
456 |
+
"max_steps": 36816,
|
457 |
+
"num_train_epochs": 3,
|
458 |
+
"total_flos": 1275249174174720.0,
|
459 |
+
"trial_name": null,
|
460 |
+
"trial_params": null
|
461 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f8b60e6ce70e153cdbf05528fde76a9aa14b755fa73b09157453724b5055c68
|
3 |
+
size 2415
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|