Upload trainer_state.json with huggingface_hub
Browse files- trainer_state.json +315 -0
trainer_state.json
ADDED
@@ -0,0 +1,315 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 391,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02557544757033248,
|
13 |
+
"grad_norm": 1.875,
|
14 |
+
"learning_rate": 2.5e-05,
|
15 |
+
"loss": 0.8604,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.05115089514066496,
|
20 |
+
"grad_norm": 1.03125,
|
21 |
+
"learning_rate": 5e-05,
|
22 |
+
"loss": 0.6219,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.07672634271099744,
|
27 |
+
"grad_norm": 0.80078125,
|
28 |
+
"learning_rate": 7.500000000000001e-05,
|
29 |
+
"loss": 0.5142,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.10230179028132992,
|
34 |
+
"grad_norm": 0.71484375,
|
35 |
+
"learning_rate": 0.0001,
|
36 |
+
"loss": 0.4471,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.1278772378516624,
|
41 |
+
"grad_norm": 0.6640625,
|
42 |
+
"learning_rate": 9.715099715099715e-05,
|
43 |
+
"loss": 0.4005,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.1534526854219949,
|
48 |
+
"grad_norm": 0.58984375,
|
49 |
+
"learning_rate": 9.430199430199431e-05,
|
50 |
+
"loss": 0.3637,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.17902813299232737,
|
55 |
+
"grad_norm": 0.57421875,
|
56 |
+
"learning_rate": 9.145299145299146e-05,
|
57 |
+
"loss": 0.35,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.20460358056265984,
|
62 |
+
"grad_norm": 0.5078125,
|
63 |
+
"learning_rate": 8.860398860398861e-05,
|
64 |
+
"loss": 0.3432,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.23017902813299232,
|
69 |
+
"grad_norm": 0.50390625,
|
70 |
+
"learning_rate": 8.575498575498576e-05,
|
71 |
+
"loss": 0.3338,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.2557544757033248,
|
76 |
+
"grad_norm": 0.58203125,
|
77 |
+
"learning_rate": 8.290598290598292e-05,
|
78 |
+
"loss": 0.3331,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.2813299232736573,
|
83 |
+
"grad_norm": 0.55859375,
|
84 |
+
"learning_rate": 8.005698005698006e-05,
|
85 |
+
"loss": 0.3215,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.3069053708439898,
|
90 |
+
"grad_norm": 0.546875,
|
91 |
+
"learning_rate": 7.720797720797721e-05,
|
92 |
+
"loss": 0.3185,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.33248081841432225,
|
97 |
+
"grad_norm": 0.51953125,
|
98 |
+
"learning_rate": 7.435897435897436e-05,
|
99 |
+
"loss": 0.3186,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.35805626598465473,
|
104 |
+
"grad_norm": 0.46484375,
|
105 |
+
"learning_rate": 7.150997150997152e-05,
|
106 |
+
"loss": 0.3156,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.3836317135549872,
|
111 |
+
"grad_norm": 0.5859375,
|
112 |
+
"learning_rate": 6.866096866096867e-05,
|
113 |
+
"loss": 0.3106,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.4092071611253197,
|
118 |
+
"grad_norm": 0.48046875,
|
119 |
+
"learning_rate": 6.581196581196581e-05,
|
120 |
+
"loss": 0.3146,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.43478260869565216,
|
125 |
+
"grad_norm": 0.53515625,
|
126 |
+
"learning_rate": 6.296296296296296e-05,
|
127 |
+
"loss": 0.3135,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.46035805626598464,
|
132 |
+
"grad_norm": 0.490234375,
|
133 |
+
"learning_rate": 6.011396011396012e-05,
|
134 |
+
"loss": 0.3059,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.4859335038363171,
|
139 |
+
"grad_norm": 0.609375,
|
140 |
+
"learning_rate": 5.726495726495726e-05,
|
141 |
+
"loss": 0.3049,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.5115089514066496,
|
146 |
+
"grad_norm": 0.53125,
|
147 |
+
"learning_rate": 5.441595441595442e-05,
|
148 |
+
"loss": 0.3032,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.5370843989769821,
|
153 |
+
"grad_norm": 0.53125,
|
154 |
+
"learning_rate": 5.156695156695157e-05,
|
155 |
+
"loss": 0.2889,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.5626598465473146,
|
160 |
+
"grad_norm": 0.50390625,
|
161 |
+
"learning_rate": 4.871794871794872e-05,
|
162 |
+
"loss": 0.2971,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.5882352941176471,
|
167 |
+
"grad_norm": 0.546875,
|
168 |
+
"learning_rate": 4.586894586894587e-05,
|
169 |
+
"loss": 0.3088,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.6138107416879796,
|
174 |
+
"grad_norm": 0.57421875,
|
175 |
+
"learning_rate": 4.301994301994302e-05,
|
176 |
+
"loss": 0.2977,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.639386189258312,
|
181 |
+
"grad_norm": 0.578125,
|
182 |
+
"learning_rate": 4.0170940170940174e-05,
|
183 |
+
"loss": 0.2956,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.6649616368286445,
|
188 |
+
"grad_norm": 0.546875,
|
189 |
+
"learning_rate": 3.732193732193732e-05,
|
190 |
+
"loss": 0.2953,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.690537084398977,
|
195 |
+
"grad_norm": 0.49609375,
|
196 |
+
"learning_rate": 3.4472934472934476e-05,
|
197 |
+
"loss": 0.2955,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.7161125319693095,
|
202 |
+
"grad_norm": 0.49609375,
|
203 |
+
"learning_rate": 3.162393162393162e-05,
|
204 |
+
"loss": 0.2892,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.7416879795396419,
|
209 |
+
"grad_norm": 0.486328125,
|
210 |
+
"learning_rate": 2.8774928774928778e-05,
|
211 |
+
"loss": 0.281,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.7672634271099744,
|
216 |
+
"grad_norm": 0.4921875,
|
217 |
+
"learning_rate": 2.5925925925925925e-05,
|
218 |
+
"loss": 0.2911,
|
219 |
+
"step": 300
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.7928388746803069,
|
223 |
+
"grad_norm": 0.61328125,
|
224 |
+
"learning_rate": 2.307692307692308e-05,
|
225 |
+
"loss": 0.2943,
|
226 |
+
"step": 310
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.8184143222506394,
|
230 |
+
"grad_norm": 0.53125,
|
231 |
+
"learning_rate": 2.022792022792023e-05,
|
232 |
+
"loss": 0.293,
|
233 |
+
"step": 320
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.8439897698209718,
|
237 |
+
"grad_norm": 0.4609375,
|
238 |
+
"learning_rate": 1.737891737891738e-05,
|
239 |
+
"loss": 0.2815,
|
240 |
+
"step": 330
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.8695652173913043,
|
244 |
+
"grad_norm": 0.4609375,
|
245 |
+
"learning_rate": 1.4529914529914531e-05,
|
246 |
+
"loss": 0.2871,
|
247 |
+
"step": 340
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.8951406649616368,
|
251 |
+
"grad_norm": 0.55078125,
|
252 |
+
"learning_rate": 1.168091168091168e-05,
|
253 |
+
"loss": 0.2832,
|
254 |
+
"step": 350
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.9207161125319693,
|
258 |
+
"grad_norm": 0.55859375,
|
259 |
+
"learning_rate": 8.831908831908831e-06,
|
260 |
+
"loss": 0.289,
|
261 |
+
"step": 360
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.9462915601023018,
|
265 |
+
"grad_norm": 0.53125,
|
266 |
+
"learning_rate": 5.982905982905984e-06,
|
267 |
+
"loss": 0.2936,
|
268 |
+
"step": 370
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.9718670076726342,
|
272 |
+
"grad_norm": 0.484375,
|
273 |
+
"learning_rate": 3.133903133903134e-06,
|
274 |
+
"loss": 0.2828,
|
275 |
+
"step": 380
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.9974424552429667,
|
279 |
+
"grad_norm": 0.53515625,
|
280 |
+
"learning_rate": 2.8490028490028494e-07,
|
281 |
+
"loss": 0.2916,
|
282 |
+
"step": 390
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 1.0,
|
286 |
+
"step": 391,
|
287 |
+
"total_flos": 1.382893920190464e+16,
|
288 |
+
"train_loss": 0.3390924896273162,
|
289 |
+
"train_runtime": 504.4341,
|
290 |
+
"train_samples_per_second": 49.56,
|
291 |
+
"train_steps_per_second": 0.775
|
292 |
+
}
|
293 |
+
],
|
294 |
+
"logging_steps": 10,
|
295 |
+
"max_steps": 391,
|
296 |
+
"num_input_tokens_seen": 0,
|
297 |
+
"num_train_epochs": 1,
|
298 |
+
"save_steps": 1000,
|
299 |
+
"stateful_callbacks": {
|
300 |
+
"TrainerControl": {
|
301 |
+
"args": {
|
302 |
+
"should_epoch_stop": false,
|
303 |
+
"should_evaluate": false,
|
304 |
+
"should_log": false,
|
305 |
+
"should_save": true,
|
306 |
+
"should_training_stop": true
|
307 |
+
},
|
308 |
+
"attributes": {}
|
309 |
+
}
|
310 |
+
},
|
311 |
+
"total_flos": 1.382893920190464e+16,
|
312 |
+
"train_batch_size": 4,
|
313 |
+
"trial_name": null,
|
314 |
+
"trial_params": null
|
315 |
+
}
|