Training in progress, step 44, 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:fe47134b8c8bc15427b08b3910016e7efab14e4aa45ed9507cc553b51971e1d8
|
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 sha256:6c6fd91b35289f7be28aca08b7d70a297471b7f61ea33e76a019b9c6287c9e0e
|
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:cd41af6a2dac8ebfd7d5f30d74c33ac617565a086b983aef26d1bf242598ac03
|
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,
|
@@ -287,6 +287,34 @@
|
|
287 |
"learning_rate": 8.36685749586087e-06,
|
288 |
"loss": 1.9485,
|
289 |
"step": 40
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
290 |
}
|
291 |
],
|
292 |
"logging_steps": 1,
|
@@ -306,7 +334,7 @@
|
|
306 |
"attributes": {}
|
307 |
}
|
308 |
},
|
309 |
-
"total_flos":
|
310 |
"train_batch_size": 2,
|
311 |
"trial_name": null,
|
312 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.527827648114901,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 44,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
287 |
"learning_rate": 8.36685749586087e-06,
|
288 |
"loss": 1.9485,
|
289 |
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 2.355475763016158,
|
293 |
+
"grad_norm": 1.2525312900543213,
|
294 |
+
"learning_rate": 6.986960159980327e-06,
|
295 |
+
"loss": 2.0025,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.4129263913824057,
|
300 |
+
"grad_norm": 1.2137963771820068,
|
301 |
+
"learning_rate": 5.712770504451426e-06,
|
302 |
+
"loss": 1.9968,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 2.4703770197486534,
|
307 |
+
"grad_norm": 1.1027462482452393,
|
308 |
+
"learning_rate": 4.551765980832059e-06,
|
309 |
+
"loss": 2.0205,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 2.527827648114901,
|
314 |
+
"grad_norm": 1.1979150772094727,
|
315 |
+
"learning_rate": 3.5107598253199758e-06,
|
316 |
+
"loss": 1.9487,
|
317 |
+
"step": 44
|
318 |
}
|
319 |
],
|
320 |
"logging_steps": 1,
|
|
|
334 |
"attributes": {}
|
335 |
}
|
336 |
},
|
337 |
+
"total_flos": 3.0431977288052736e+16,
|
338 |
"train_batch_size": 2,
|
339 |
"trial_name": null,
|
340 |
"trial_params": null
|