mikhail-panzo
commited on
Commit
•
33b97a2
1
Parent(s):
2309d3c
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 sha256:568beaea7b10151ac36b16502a905b74eb42e9692e9cf626d4e54483d9f62675
|
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 sha256:07e91e95945e3993b28704b8a8ff0fe58a187246a0cce963427a80f323bcbc41
|
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 sha256:5ef10d6e78066e1e0b64d0a4f7c5c873eaaaea2dfe3daf019e2a56206b658ad5
|
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 sha256:8200c7911b70674e95f6ea3c4fd4f7c5a623c58e7efa3752996c3106e6a97146
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/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": 27.707,
|
242 |
"eval_steps_per_second": 3.54,
|
243 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 50,
|
@@ -260,7 +338,7 @@
|
|
260 |
"attributes": {}
|
261 |
}
|
262 |
},
|
263 |
-
"total_flos":
|
264 |
"train_batch_size": 32,
|
265 |
"trial_name": null,
|
266 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.4016592502593994,
|
3 |
+
"best_model_checkpoint": "mikhail-panzo/ceb_b128_le5_s4000/checkpoint-2000",
|
4 |
+
"epoch": 156.86274509803923,
|
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": 27.707,
|
242 |
"eval_steps_per_second": 3.54,
|
243 |
"step": 1500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 121.56862745098039,
|
247 |
+
"grad_norm": 0.6831104755401611,
|
248 |
+
"learning_rate": 7.745e-06,
|
249 |
+
"loss": 0.4461,
|
250 |
+
"step": 1550
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 125.49019607843137,
|
254 |
+
"grad_norm": 1.195868968963623,
|
255 |
+
"learning_rate": 7.995e-06,
|
256 |
+
"loss": 0.4429,
|
257 |
+
"step": 1600
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 129.41176470588235,
|
261 |
+
"grad_norm": 1.1746853590011597,
|
262 |
+
"learning_rate": 8.245000000000002e-06,
|
263 |
+
"loss": 0.4358,
|
264 |
+
"step": 1650
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 133.33333333333334,
|
268 |
+
"grad_norm": 1.2797439098358154,
|
269 |
+
"learning_rate": 8.495e-06,
|
270 |
+
"loss": 0.4383,
|
271 |
+
"step": 1700
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 137.2549019607843,
|
275 |
+
"grad_norm": 0.6744837760925293,
|
276 |
+
"learning_rate": 8.745000000000002e-06,
|
277 |
+
"loss": 0.4416,
|
278 |
+
"step": 1750
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 141.1764705882353,
|
282 |
+
"grad_norm": 0.7655614018440247,
|
283 |
+
"learning_rate": 8.995000000000001e-06,
|
284 |
+
"loss": 0.4338,
|
285 |
+
"step": 1800
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 145.09803921568627,
|
289 |
+
"grad_norm": 0.9920282363891602,
|
290 |
+
"learning_rate": 9.245e-06,
|
291 |
+
"loss": 0.4337,
|
292 |
+
"step": 1850
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 149.01960784313727,
|
296 |
+
"grad_norm": 0.9740642309188843,
|
297 |
+
"learning_rate": 9.495000000000001e-06,
|
298 |
+
"loss": 0.4309,
|
299 |
+
"step": 1900
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 152.94117647058823,
|
303 |
+
"grad_norm": 0.9331285953521729,
|
304 |
+
"learning_rate": 9.745e-06,
|
305 |
+
"loss": 0.4337,
|
306 |
+
"step": 1950
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 156.86274509803923,
|
310 |
+
"grad_norm": 0.8512988686561584,
|
311 |
+
"learning_rate": 9.995000000000002e-06,
|
312 |
+
"loss": 0.4289,
|
313 |
+
"step": 2000
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 156.86274509803923,
|
317 |
+
"eval_loss": 0.4016592502593994,
|
318 |
+
"eval_runtime": 6.4392,
|
319 |
+
"eval_samples_per_second": 27.954,
|
320 |
+
"eval_steps_per_second": 3.572,
|
321 |
+
"step": 2000
|
322 |
}
|
323 |
],
|
324 |
"logging_steps": 50,
|
|
|
338 |
"attributes": {}
|
339 |
}
|
340 |
},
|
341 |
+
"total_flos": 4.352128118839037e+16,
|
342 |
"train_batch_size": 32,
|
343 |
"trial_name": null,
|
344 |
"trial_params": null
|