mikhail-panzo
commited on
Commit
•
5947994
1
Parent(s):
5669ea8
Training in progress, step 2000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 577789320
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77cf949a0f97184343b7d38f784b04fdb71aaee58aa4de38e1e5079b54b4ba58
|
3 |
size 577789320
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1155772233
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0048ca8ae538b9b924a62e63ceffd10e5b7e2ad8f482ef7babfb9890a931dd73
|
3 |
size 1155772233
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ab606683dee59e251ef2cbfcb1aebf2f02037a37af81cb49a67b06660659a4f
|
3 |
size 14244
|
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:b911007def71d4e0760e095fb38b9695588c94c6dfc0cb1ee70d933b50c5ece7
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -241,6 +241,84 @@
|
|
241 |
"eval_samples_per_second": 24.653,
|
242 |
"eval_steps_per_second": 3.101,
|
243 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 50,
|
@@ -260,7 +338,7 @@
|
|
260 |
"attributes": {}
|
261 |
}
|
262 |
},
|
263 |
-
"total_flos": 2.
|
264 |
"train_batch_size": 64,
|
265 |
"trial_name": null,
|
266 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.4230838716030121,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-2000",
|
4 |
+
"epoch": 86.95652173913044,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
241 |
"eval_samples_per_second": 24.653,
|
242 |
"eval_steps_per_second": 3.101,
|
243 |
"step": 1500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 67.3913043478261,
|
247 |
+
"grad_norm": 1.2938276529312134,
|
248 |
+
"learning_rate": 7.74e-06,
|
249 |
+
"loss": 0.4684,
|
250 |
+
"step": 1550
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 69.56521739130434,
|
254 |
+
"grad_norm": 1.8100048303604126,
|
255 |
+
"learning_rate": 7.990000000000001e-06,
|
256 |
+
"loss": 0.4797,
|
257 |
+
"step": 1600
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 71.73913043478261,
|
261 |
+
"grad_norm": 1.8357532024383545,
|
262 |
+
"learning_rate": 8.24e-06,
|
263 |
+
"loss": 0.4813,
|
264 |
+
"step": 1650
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 73.91304347826087,
|
268 |
+
"grad_norm": 1.4251928329467773,
|
269 |
+
"learning_rate": 8.49e-06,
|
270 |
+
"loss": 0.4622,
|
271 |
+
"step": 1700
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 76.08695652173913,
|
275 |
+
"grad_norm": 1.1764353513717651,
|
276 |
+
"learning_rate": 8.740000000000001e-06,
|
277 |
+
"loss": 0.4642,
|
278 |
+
"step": 1750
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 78.26086956521739,
|
282 |
+
"grad_norm": 1.6363924741744995,
|
283 |
+
"learning_rate": 8.99e-06,
|
284 |
+
"loss": 0.4669,
|
285 |
+
"step": 1800
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 80.43478260869566,
|
289 |
+
"grad_norm": 1.485127568244934,
|
290 |
+
"learning_rate": 9.240000000000001e-06,
|
291 |
+
"loss": 0.4595,
|
292 |
+
"step": 1850
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 82.6086956521739,
|
296 |
+
"grad_norm": 1.2844778299331665,
|
297 |
+
"learning_rate": 9.49e-06,
|
298 |
+
"loss": 0.463,
|
299 |
+
"step": 1900
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 84.78260869565217,
|
303 |
+
"grad_norm": 1.0181550979614258,
|
304 |
+
"learning_rate": 9.74e-06,
|
305 |
+
"loss": 0.4529,
|
306 |
+
"step": 1950
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 86.95652173913044,
|
310 |
+
"grad_norm": 1.3658286333084106,
|
311 |
+
"learning_rate": 9.990000000000001e-06,
|
312 |
+
"loss": 0.454,
|
313 |
+
"step": 2000
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 86.95652173913044,
|
317 |
+
"eval_loss": 0.4230838716030121,
|
318 |
+
"eval_runtime": 6.4713,
|
319 |
+
"eval_samples_per_second": 24.57,
|
320 |
+
"eval_steps_per_second": 3.091,
|
321 |
+
"step": 2000
|
322 |
}
|
323 |
],
|
324 |
"logging_steps": 50,
|
|
|
338 |
"attributes": {}
|
339 |
}
|
340 |
},
|
341 |
+
"total_flos": 2.9689323880306464e+16,
|
342 |
"train_batch_size": 64,
|
343 |
"trial_name": null,
|
344 |
"trial_params": null
|