mikhail-panzo
commited on
Commit
•
991181b
1
Parent(s):
31162ce
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 sha256:17756aebf81d95bb9838128283e6da6710d776c7d9df7c685f664101b5b99452
|
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 sha256:9b487bee88037fce1eca80b45882678fd5954a83a75d4060d95c1e16fccf145d
|
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 sha256:2f01983801a45234478c13db780514a852cdeaff2aa79f279442e47dc68cb11d
|
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 sha256:15b560a9dc43b2ed5d8c7b0910cf19c12068f6e2db4cd26fd270e940d4d1787b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_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": 31.058,
|
242 |
"eval_steps_per_second": 3.885,
|
243 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
244 |
}
|
245 |
],
|
246 |
"logging_steps": 50,
|
@@ -260,7 +338,7 @@
|
|
260 |
"attributes": {}
|
261 |
}
|
262 |
},
|
263 |
-
"total_flos":
|
264 |
"train_batch_size": 16,
|
265 |
"trial_name": null,
|
266 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3677983582019806,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-2000",
|
4 |
+
"epoch": 3.350785340314136,
|
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": 31.058,
|
242 |
"eval_steps_per_second": 3.885,
|
243 |
"step": 1500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 2.5968586387434556,
|
247 |
+
"grad_norm": 1.6483193635940552,
|
248 |
+
"learning_rate": 7.745e-05,
|
249 |
+
"loss": 0.414,
|
250 |
+
"step": 1550
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 2.680628272251309,
|
254 |
+
"grad_norm": 1.7688554525375366,
|
255 |
+
"learning_rate": 7.995e-05,
|
256 |
+
"loss": 0.4153,
|
257 |
+
"step": 1600
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 2.7643979057591626,
|
261 |
+
"grad_norm": 1.2314317226409912,
|
262 |
+
"learning_rate": 8.245e-05,
|
263 |
+
"loss": 0.4089,
|
264 |
+
"step": 1650
|
265 |
+
},
|
266 |
+
{
|
267 |
+
"epoch": 2.8481675392670156,
|
268 |
+
"grad_norm": 1.6623793840408325,
|
269 |
+
"learning_rate": 8.495e-05,
|
270 |
+
"loss": 0.4124,
|
271 |
+
"step": 1700
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 2.931937172774869,
|
275 |
+
"grad_norm": 3.812507390975952,
|
276 |
+
"learning_rate": 8.745000000000001e-05,
|
277 |
+
"loss": 0.4112,
|
278 |
+
"step": 1750
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.0157068062827226,
|
282 |
+
"grad_norm": 2.141019821166992,
|
283 |
+
"learning_rate": 8.995e-05,
|
284 |
+
"loss": 0.4081,
|
285 |
+
"step": 1800
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 3.099476439790576,
|
289 |
+
"grad_norm": 1.8928133249282837,
|
290 |
+
"learning_rate": 9.245e-05,
|
291 |
+
"loss": 0.4067,
|
292 |
+
"step": 1850
|
293 |
+
},
|
294 |
+
{
|
295 |
+
"epoch": 3.183246073298429,
|
296 |
+
"grad_norm": 2.322817087173462,
|
297 |
+
"learning_rate": 9.495e-05,
|
298 |
+
"loss": 0.4088,
|
299 |
+
"step": 1900
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 3.2670157068062826,
|
303 |
+
"grad_norm": 2.1984918117523193,
|
304 |
+
"learning_rate": 9.745000000000001e-05,
|
305 |
+
"loss": 0.3976,
|
306 |
+
"step": 1950
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 3.350785340314136,
|
310 |
+
"grad_norm": 2.0455121994018555,
|
311 |
+
"learning_rate": 9.995e-05,
|
312 |
+
"loss": 0.4022,
|
313 |
+
"step": 2000
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 3.350785340314136,
|
317 |
+
"eval_loss": 0.3677983582019806,
|
318 |
+
"eval_runtime": 274.4574,
|
319 |
+
"eval_samples_per_second": 30.93,
|
320 |
+
"eval_steps_per_second": 3.869,
|
321 |
+
"step": 2000
|
322 |
}
|
323 |
],
|
324 |
"logging_steps": 50,
|
|
|
338 |
"attributes": {}
|
339 |
}
|
340 |
},
|
341 |
+
"total_flos": 3.5804068604023104e+16,
|
342 |
"train_batch_size": 16,
|
343 |
"trial_name": null,
|
344 |
"trial_params": null
|