Training in progress, step 37, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebcdc06844f452ee7c310f654f69e21ae664d5ebb01d68559119fb5e2cb9a19e
|
3 |
size 640009682
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43f2a6525da838f326067b6c1a069a3ec574f77d262ceb75df0eeef3b5ae6ae7
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d38bae5f81c99ece5b795024d5ad5a854e0d6cc507c9d6f2ac6decfbbf1a473e
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d41e60937074a461777d2cab28e8611d5f17f01a72994e98959303819744935d
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6075abe3a7ca7cb0106cd47632619bea5486e06afd509d3ee787b3ef8a14b11d
|
3 |
size 15024
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1df0c22090f509867cb1f8fd81877850d90a52f2fa21e66515d4ed39ac5f588
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
-
"epoch":
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -198,6 +198,90 @@
|
|
198 |
"eval_samples_per_second": 11.875,
|
199 |
"eval_steps_per_second": 3.088,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +305,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos":
|
230 |
"train_batch_size": 1,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": NaN,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 3.051546391752577,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 37,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 11.875,
|
199 |
"eval_steps_per_second": 3.088,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.1443298969072164,
|
204 |
+
"grad_norm": NaN,
|
205 |
+
"learning_rate": 3.0209635834655392e-05,
|
206 |
+
"loss": 0.0,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.2268041237113403,
|
211 |
+
"grad_norm": NaN,
|
212 |
+
"learning_rate": 2.6942958916356998e-05,
|
213 |
+
"loss": 0.0,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 2.3092783505154637,
|
218 |
+
"grad_norm": NaN,
|
219 |
+
"learning_rate": 2.3902180795591093e-05,
|
220 |
+
"loss": 0.0,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 2.3917525773195876,
|
225 |
+
"grad_norm": NaN,
|
226 |
+
"learning_rate": 2.111178402983751e-05,
|
227 |
+
"loss": 0.0,
|
228 |
+
"step": 29
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.4742268041237114,
|
232 |
+
"grad_norm": NaN,
|
233 |
+
"learning_rate": 1.8594235253127375e-05,
|
234 |
+
"loss": 0.0,
|
235 |
+
"step": 30
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 2.556701030927835,
|
239 |
+
"grad_norm": NaN,
|
240 |
+
"learning_rate": 1.6369804287916028e-05,
|
241 |
+
"loss": 0.0,
|
242 |
+
"step": 31
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.6391752577319587,
|
246 |
+
"grad_norm": NaN,
|
247 |
+
"learning_rate": 1.4456400944391146e-05,
|
248 |
+
"loss": 0.0,
|
249 |
+
"step": 32
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 2.7216494845360826,
|
253 |
+
"grad_norm": NaN,
|
254 |
+
"learning_rate": 1.2869430821211828e-05,
|
255 |
+
"loss": 0.0,
|
256 |
+
"step": 33
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 2.804123711340206,
|
260 |
+
"grad_norm": NaN,
|
261 |
+
"learning_rate": 1.1621671268686606e-05,
|
262 |
+
"loss": 0.0,
|
263 |
+
"step": 34
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 2.88659793814433,
|
267 |
+
"grad_norm": NaN,
|
268 |
+
"learning_rate": 1.0723168513061666e-05,
|
269 |
+
"loss": 0.0,
|
270 |
+
"step": 35
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 2.9690721649484537,
|
274 |
+
"grad_norm": NaN,
|
275 |
+
"learning_rate": 1.0181156770214243e-05,
|
276 |
+
"loss": 0.0,
|
277 |
+
"step": 36
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 3.051546391752577,
|
281 |
+
"grad_norm": NaN,
|
282 |
+
"learning_rate": 1e-05,
|
283 |
+
"loss": 0.0,
|
284 |
+
"step": 37
|
285 |
}
|
286 |
],
|
287 |
"logging_steps": 1,
|
|
|
305 |
"should_evaluate": false,
|
306 |
"should_log": false,
|
307 |
"should_save": true,
|
308 |
+
"should_training_stop": true
|
309 |
},
|
310 |
"attributes": {}
|
311 |
}
|
312 |
},
|
313 |
+
"total_flos": 5.784250223102525e+17,
|
314 |
"train_batch_size": 1,
|
315 |
"trial_name": null,
|
316 |
"trial_params": null
|