com1
Browse files- config.json +52 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.txt +3 -0
- trainer_state.json +424 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hyunwoongko/kobart",
|
3 |
+
"activation_dropout": 0.0,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.1,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"do_blenderbot_90_layernorm": false,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 1,
|
27 |
+
"extra_pos_embeddings": 2,
|
28 |
+
"force_bos_token_to_be_generated": false,
|
29 |
+
"gradient_checkpointing": false,
|
30 |
+
"id2label": {
|
31 |
+
"0": "NEGATIVE",
|
32 |
+
"1": "POSITIVE"
|
33 |
+
},
|
34 |
+
"init_std": 0.02,
|
35 |
+
"is_encoder_decoder": true,
|
36 |
+
"label2id": {
|
37 |
+
"NEGATIVE": 0,
|
38 |
+
"POSITIVE": 1
|
39 |
+
},
|
40 |
+
"max_position_embeddings": 1026,
|
41 |
+
"model_type": "bart",
|
42 |
+
"normalize_before": false,
|
43 |
+
"normalize_embedding": true,
|
44 |
+
"num_hidden_layers": 6,
|
45 |
+
"pad_token_id": 3,
|
46 |
+
"scale_embedding": false,
|
47 |
+
"static_position_embeddings": false,
|
48 |
+
"transformers_version": "4.2.2",
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 30000,
|
51 |
+
"xla_device": true
|
52 |
+
}
|
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 sha256:10e01c0aca1c49490b0f8b3aa256ba914376ca000487da2c32ece25b1c3e46ff
|
3 |
+
size 772129774
|
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_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>", "do_lower_case": false, "special_tokens_map_file": "/root/.cache/huggingface/transformers/97eaf441c74b8b3313c1b25fc39c6a816a85d47459270d02e75ccd36623de189.9d6cd81ef646692fb1c169a880161ea1cb95f49694f220aced9b704b457e51dd", "name_or_path": "hyunwoongko/kobart"}
|
train_results.txt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
epoch = 5.0
|
2 |
+
train_runtime = 9443.8872
|
3 |
+
train_samples_per_second = 0.357
|
trainer_state.json
ADDED
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 3375,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.07,
|
12 |
+
"learning_rate": 4.925925925925926e-05,
|
13 |
+
"loss": 6.5471,
|
14 |
+
"step": 50
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.15,
|
18 |
+
"learning_rate": 4.851851851851852e-05,
|
19 |
+
"loss": 5.3494,
|
20 |
+
"step": 100
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.22,
|
24 |
+
"learning_rate": 4.7777777777777784e-05,
|
25 |
+
"loss": 4.6856,
|
26 |
+
"step": 150
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.3,
|
30 |
+
"learning_rate": 4.703703703703704e-05,
|
31 |
+
"loss": 4.2817,
|
32 |
+
"step": 200
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.37,
|
36 |
+
"learning_rate": 4.62962962962963e-05,
|
37 |
+
"loss": 4.002,
|
38 |
+
"step": 250
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.44,
|
42 |
+
"learning_rate": 4.555555555555556e-05,
|
43 |
+
"loss": 3.7676,
|
44 |
+
"step": 300
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.52,
|
48 |
+
"learning_rate": 4.481481481481482e-05,
|
49 |
+
"loss": 3.6137,
|
50 |
+
"step": 350
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.59,
|
54 |
+
"learning_rate": 4.4074074074074076e-05,
|
55 |
+
"loss": 3.5144,
|
56 |
+
"step": 400
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.67,
|
60 |
+
"learning_rate": 4.3333333333333334e-05,
|
61 |
+
"loss": 3.4205,
|
62 |
+
"step": 450
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.74,
|
66 |
+
"learning_rate": 4.259259259259259e-05,
|
67 |
+
"loss": 3.3922,
|
68 |
+
"step": 500
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.81,
|
72 |
+
"learning_rate": 4.185185185185185e-05,
|
73 |
+
"loss": 3.2814,
|
74 |
+
"step": 550
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.89,
|
78 |
+
"learning_rate": 4.111111111111111e-05,
|
79 |
+
"loss": 3.154,
|
80 |
+
"step": 600
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.96,
|
84 |
+
"learning_rate": 4.0370370370370374e-05,
|
85 |
+
"loss": 3.1475,
|
86 |
+
"step": 650
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.04,
|
90 |
+
"learning_rate": 3.962962962962963e-05,
|
91 |
+
"loss": 3.0733,
|
92 |
+
"step": 700
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.11,
|
96 |
+
"learning_rate": 3.888888888888889e-05,
|
97 |
+
"loss": 3.0052,
|
98 |
+
"step": 750
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.19,
|
102 |
+
"learning_rate": 3.814814814814815e-05,
|
103 |
+
"loss": 2.9697,
|
104 |
+
"step": 800
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.26,
|
108 |
+
"learning_rate": 3.740740740740741e-05,
|
109 |
+
"loss": 2.8816,
|
110 |
+
"step": 850
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.33,
|
114 |
+
"learning_rate": 3.6666666666666666e-05,
|
115 |
+
"loss": 2.8471,
|
116 |
+
"step": 900
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.41,
|
120 |
+
"learning_rate": 3.592592592592593e-05,
|
121 |
+
"loss": 2.7135,
|
122 |
+
"step": 950
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.48,
|
126 |
+
"learning_rate": 3.518518518518519e-05,
|
127 |
+
"loss": 2.6549,
|
128 |
+
"step": 1000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.56,
|
132 |
+
"learning_rate": 3.444444444444445e-05,
|
133 |
+
"loss": 2.6859,
|
134 |
+
"step": 1050
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.63,
|
138 |
+
"learning_rate": 3.3703703703703706e-05,
|
139 |
+
"loss": 2.5475,
|
140 |
+
"step": 1100
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.7,
|
144 |
+
"learning_rate": 3.2962962962962964e-05,
|
145 |
+
"loss": 2.5651,
|
146 |
+
"step": 1150
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.78,
|
150 |
+
"learning_rate": 3.222222222222223e-05,
|
151 |
+
"loss": 2.5293,
|
152 |
+
"step": 1200
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.85,
|
156 |
+
"learning_rate": 3.148148148148148e-05,
|
157 |
+
"loss": 2.4666,
|
158 |
+
"step": 1250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.93,
|
162 |
+
"learning_rate": 3.074074074074074e-05,
|
163 |
+
"loss": 2.5076,
|
164 |
+
"step": 1300
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.0,
|
168 |
+
"learning_rate": 3e-05,
|
169 |
+
"loss": 2.4786,
|
170 |
+
"step": 1350
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.07,
|
174 |
+
"learning_rate": 2.925925925925926e-05,
|
175 |
+
"loss": 2.4179,
|
176 |
+
"step": 1400
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.15,
|
180 |
+
"learning_rate": 2.851851851851852e-05,
|
181 |
+
"loss": 2.4282,
|
182 |
+
"step": 1450
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.22,
|
186 |
+
"learning_rate": 2.777777777777778e-05,
|
187 |
+
"loss": 2.3712,
|
188 |
+
"step": 1500
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.3,
|
192 |
+
"learning_rate": 2.7037037037037037e-05,
|
193 |
+
"loss": 2.4311,
|
194 |
+
"step": 1550
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.37,
|
198 |
+
"learning_rate": 2.6296296296296296e-05,
|
199 |
+
"loss": 2.3564,
|
200 |
+
"step": 1600
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.44,
|
204 |
+
"learning_rate": 2.5555555555555554e-05,
|
205 |
+
"loss": 2.3612,
|
206 |
+
"step": 1650
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.52,
|
210 |
+
"learning_rate": 2.4814814814814816e-05,
|
211 |
+
"loss": 2.3105,
|
212 |
+
"step": 1700
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.59,
|
216 |
+
"learning_rate": 2.4074074074074074e-05,
|
217 |
+
"loss": 2.3608,
|
218 |
+
"step": 1750
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.67,
|
222 |
+
"learning_rate": 2.3333333333333336e-05,
|
223 |
+
"loss": 2.3177,
|
224 |
+
"step": 1800
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.74,
|
228 |
+
"learning_rate": 2.2592592592592594e-05,
|
229 |
+
"loss": 2.2787,
|
230 |
+
"step": 1850
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.81,
|
234 |
+
"learning_rate": 2.1851851851851852e-05,
|
235 |
+
"loss": 2.2704,
|
236 |
+
"step": 1900
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.89,
|
240 |
+
"learning_rate": 2.111111111111111e-05,
|
241 |
+
"loss": 2.3038,
|
242 |
+
"step": 1950
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.96,
|
246 |
+
"learning_rate": 2.037037037037037e-05,
|
247 |
+
"loss": 2.2936,
|
248 |
+
"step": 2000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.04,
|
252 |
+
"learning_rate": 1.962962962962963e-05,
|
253 |
+
"loss": 2.2346,
|
254 |
+
"step": 2050
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.11,
|
258 |
+
"learning_rate": 1.888888888888889e-05,
|
259 |
+
"loss": 2.1724,
|
260 |
+
"step": 2100
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.19,
|
264 |
+
"learning_rate": 1.814814814814815e-05,
|
265 |
+
"loss": 2.2722,
|
266 |
+
"step": 2150
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.26,
|
270 |
+
"learning_rate": 1.740740740740741e-05,
|
271 |
+
"loss": 2.2064,
|
272 |
+
"step": 2200
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.33,
|
276 |
+
"learning_rate": 1.6666666666666667e-05,
|
277 |
+
"loss": 2.2001,
|
278 |
+
"step": 2250
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.41,
|
282 |
+
"learning_rate": 1.5925925925925926e-05,
|
283 |
+
"loss": 2.2209,
|
284 |
+
"step": 2300
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.48,
|
288 |
+
"learning_rate": 1.5185185185185186e-05,
|
289 |
+
"loss": 2.2761,
|
290 |
+
"step": 2350
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.56,
|
294 |
+
"learning_rate": 1.4444444444444444e-05,
|
295 |
+
"loss": 2.2162,
|
296 |
+
"step": 2400
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.63,
|
300 |
+
"learning_rate": 1.3703703703703704e-05,
|
301 |
+
"loss": 2.1901,
|
302 |
+
"step": 2450
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.7,
|
306 |
+
"learning_rate": 1.2962962962962962e-05,
|
307 |
+
"loss": 2.1575,
|
308 |
+
"step": 2500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.78,
|
312 |
+
"learning_rate": 1.2222222222222222e-05,
|
313 |
+
"loss": 2.131,
|
314 |
+
"step": 2550
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.85,
|
318 |
+
"learning_rate": 1.1481481481481482e-05,
|
319 |
+
"loss": 2.1589,
|
320 |
+
"step": 2600
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.93,
|
324 |
+
"learning_rate": 1.074074074074074e-05,
|
325 |
+
"loss": 2.1777,
|
326 |
+
"step": 2650
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 4.0,
|
330 |
+
"learning_rate": 1e-05,
|
331 |
+
"loss": 2.1124,
|
332 |
+
"step": 2700
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 4.07,
|
336 |
+
"learning_rate": 9.259259259259259e-06,
|
337 |
+
"loss": 2.1113,
|
338 |
+
"step": 2750
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 4.15,
|
342 |
+
"learning_rate": 8.518518518518519e-06,
|
343 |
+
"loss": 2.087,
|
344 |
+
"step": 2800
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 4.22,
|
348 |
+
"learning_rate": 7.777777777777777e-06,
|
349 |
+
"loss": 2.1169,
|
350 |
+
"step": 2850
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 4.3,
|
354 |
+
"learning_rate": 7.0370370370370375e-06,
|
355 |
+
"loss": 2.143,
|
356 |
+
"step": 2900
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 4.37,
|
360 |
+
"learning_rate": 6.296296296296296e-06,
|
361 |
+
"loss": 2.0682,
|
362 |
+
"step": 2950
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 4.44,
|
366 |
+
"learning_rate": 5.555555555555556e-06,
|
367 |
+
"loss": 2.133,
|
368 |
+
"step": 3000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 4.52,
|
372 |
+
"learning_rate": 4.814814814814815e-06,
|
373 |
+
"loss": 2.0986,
|
374 |
+
"step": 3050
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 4.59,
|
378 |
+
"learning_rate": 4.074074074074075e-06,
|
379 |
+
"loss": 2.1205,
|
380 |
+
"step": 3100
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.67,
|
384 |
+
"learning_rate": 3.3333333333333333e-06,
|
385 |
+
"loss": 2.0935,
|
386 |
+
"step": 3150
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 4.74,
|
390 |
+
"learning_rate": 2.5925925925925925e-06,
|
391 |
+
"loss": 2.0082,
|
392 |
+
"step": 3200
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.81,
|
396 |
+
"learning_rate": 1.8518518518518519e-06,
|
397 |
+
"loss": 2.0897,
|
398 |
+
"step": 3250
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 4.89,
|
402 |
+
"learning_rate": 1.1111111111111112e-06,
|
403 |
+
"loss": 2.1662,
|
404 |
+
"step": 3300
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 4.96,
|
408 |
+
"learning_rate": 3.703703703703704e-07,
|
409 |
+
"loss": 2.1098,
|
410 |
+
"step": 3350
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 5.0,
|
414 |
+
"step": 3375,
|
415 |
+
"train_runtime": 9443.8872,
|
416 |
+
"train_samples_per_second": 0.357
|
417 |
+
}
|
418 |
+
],
|
419 |
+
"max_steps": 3375,
|
420 |
+
"num_train_epochs": 5,
|
421 |
+
"total_flos": 6087722705879040,
|
422 |
+
"trial_name": null,
|
423 |
+
"trial_params": null
|
424 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a5c60e6d37cb1869b94092b5f46106efd7c47320243c156f7b4576bde7e2c6c
|
3 |
+
size 1967
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|