Training in progress, step 48, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2964338224
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:92a5195cc750844b0bbc895066277d57c0718916d29688804e359cf73cc5ce6f
|
3 |
size 2964338224
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1485440604
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b70c7fb24e252910d76b9e2aec21c3fc8339de03d6b82df521ec794192bf984b
|
3 |
size 1485440604
|
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 sha256:535489482a0b34fccaa30a29409920995d6879a3a5e9c37a34bb64e915525f48
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
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,
|
@@ -315,6 +315,34 @@
|
|
315 |
"learning_rate": 3.5107598253199758e-06,
|
316 |
"loss": 1.9487,
|
317 |
"step": 44
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 1,
|
@@ -334,7 +362,7 @@
|
|
334 |
"attributes": {}
|
335 |
}
|
336 |
},
|
337 |
-
"total_flos": 3.
|
338 |
"train_batch_size": 2,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.7576301615798924,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 48,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
315 |
"learning_rate": 3.5107598253199758e-06,
|
316 |
"loss": 1.9487,
|
317 |
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 2.585278276481149,
|
321 |
+
"grad_norm": 1.2198636531829834,
|
322 |
+
"learning_rate": 2.595861075973613e-06,
|
323 |
+
"loss": 2.0071,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 2.642728904847397,
|
328 |
+
"grad_norm": 1.2485204935073853,
|
329 |
+
"learning_rate": 1.8124387224476347e-06,
|
330 |
+
"loss": 1.8711,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.7001795332136447,
|
335 |
+
"grad_norm": 1.2243603467941284,
|
336 |
+
"learning_rate": 1.1650901986267365e-06,
|
337 |
+
"loss": 1.9128,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 2.7576301615798924,
|
342 |
+
"grad_norm": 1.1391812562942505,
|
343 |
+
"learning_rate": 6.576144030555259e-07,
|
344 |
+
"loss": 1.9854,
|
345 |
+
"step": 48
|
346 |
}
|
347 |
],
|
348 |
"logging_steps": 1,
|
|
|
362 |
"attributes": {}
|
363 |
}
|
364 |
},
|
365 |
+
"total_flos": 3.3055149893382144e+16,
|
366 |
"train_batch_size": 2,
|
367 |
"trial_name": null,
|
368 |
"trial_params": null
|