Commit
•
61f067a
1
Parent(s):
e7439cd
Training in progress, step 2500, 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 sha256:3a6f08fab5c9cd3e3824141f661d04fab419e16f0f27aa8be427a55a045a5024
|
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 sha256:59d2fcaa714da200edbccb39a9f2728d1eac302590a189b7a1ad33e51ddded74
|
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:e0a3df38c17b475ea7e47b6c462cb3838a91cdec2a3f47a69fc35d66481cfa21
|
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:b382f91d6a62c99969921e0d8014a3b1f89a198a6a81ab888e1194bc144c13d5
|
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,
|
@@ -319,6 +319,84 @@
|
|
319 |
"eval_samples_per_second": 31.924,
|
320 |
"eval_steps_per_second": 3.994,
|
321 |
"step": 2000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
322 |
}
|
323 |
],
|
324 |
"logging_steps": 50,
|
@@ -338,7 +416,7 @@
|
|
338 |
"attributes": {}
|
339 |
}
|
340 |
},
|
341 |
-
"total_flos":
|
342 |
"train_batch_size": 16,
|
343 |
"trial_name": null,
|
344 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.3528364896774292,
|
3 |
+
"best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-2500",
|
4 |
+
"epoch": 4.18848167539267,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
319 |
"eval_samples_per_second": 31.924,
|
320 |
"eval_steps_per_second": 3.994,
|
321 |
"step": 2000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 3.4345549738219896,
|
325 |
+
"grad_norm": 2.121384859085083,
|
326 |
+
"learning_rate": 9.918333333333334e-05,
|
327 |
+
"loss": 0.4058,
|
328 |
+
"step": 2050
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 3.518324607329843,
|
332 |
+
"grad_norm": 1.645984411239624,
|
333 |
+
"learning_rate": 9.835e-05,
|
334 |
+
"loss": 0.4021,
|
335 |
+
"step": 2100
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 3.6020942408376966,
|
339 |
+
"grad_norm": 1.246239185333252,
|
340 |
+
"learning_rate": 9.751666666666666e-05,
|
341 |
+
"loss": 0.3991,
|
342 |
+
"step": 2150
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 3.6858638743455496,
|
346 |
+
"grad_norm": 1.9096795320510864,
|
347 |
+
"learning_rate": 9.668333333333334e-05,
|
348 |
+
"loss": 0.3961,
|
349 |
+
"step": 2200
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 3.769633507853403,
|
353 |
+
"grad_norm": 1.8867601156234741,
|
354 |
+
"learning_rate": 9.585000000000001e-05,
|
355 |
+
"loss": 0.3904,
|
356 |
+
"step": 2250
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 3.8534031413612566,
|
360 |
+
"grad_norm": 1.7438101768493652,
|
361 |
+
"learning_rate": 9.501666666666668e-05,
|
362 |
+
"loss": 0.3895,
|
363 |
+
"step": 2300
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 3.93717277486911,
|
367 |
+
"grad_norm": 1.1799490451812744,
|
368 |
+
"learning_rate": 9.418333333333334e-05,
|
369 |
+
"loss": 0.4027,
|
370 |
+
"step": 2350
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 4.020942408376963,
|
374 |
+
"grad_norm": 1.1952763795852661,
|
375 |
+
"learning_rate": 9.335e-05,
|
376 |
+
"loss": 0.3893,
|
377 |
+
"step": 2400
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 4.104712041884817,
|
381 |
+
"grad_norm": 2.008756160736084,
|
382 |
+
"learning_rate": 9.251666666666667e-05,
|
383 |
+
"loss": 0.3878,
|
384 |
+
"step": 2450
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 4.18848167539267,
|
388 |
+
"grad_norm": 2.2693591117858887,
|
389 |
+
"learning_rate": 9.168333333333333e-05,
|
390 |
+
"loss": 0.3863,
|
391 |
+
"step": 2500
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 4.18848167539267,
|
395 |
+
"eval_loss": 0.3528364896774292,
|
396 |
+
"eval_runtime": 272.7627,
|
397 |
+
"eval_samples_per_second": 31.122,
|
398 |
+
"eval_steps_per_second": 3.893,
|
399 |
+
"step": 2500
|
400 |
}
|
401 |
],
|
402 |
"logging_steps": 50,
|
|
|
416 |
"attributes": {}
|
417 |
}
|
418 |
},
|
419 |
+
"total_flos": 4.477753664307475e+16,
|
420 |
"train_batch_size": 16,
|
421 |
"trial_name": null,
|
422 |
"trial_params": null
|