Training in progress, epoch 1, 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 27024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c14eadf65048b83a72a07318990b712fb81ee2d420d364dedb6d9136fb8275ac
|
3 |
size 27024
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63910
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f203216bc765834d4696952f7ded4d7087b3060c42d85bf085c66a5d1d3ddf86
|
3 |
size 63910
|
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 sha256:2d5ef96773eb758f89d6d8e0e5fe21bd00478f734b3101286128c5c2286df533
|
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:e22ca0a50bab80d00c8b8910bffb983a348f8762b7cf025e6f8e64a05a938289
|
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":
|
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,
|
@@ -1380,6 +1380,21 @@
|
|
1380 |
"eval_samples_per_second": 145.877,
|
1381 |
"eval_steps_per_second": 145.877,
|
1382 |
"step": 195
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1383 |
}
|
1384 |
],
|
1385 |
"logging_steps": 1,
|
@@ -1394,12 +1409,12 @@
|
|
1394 |
"should_evaluate": false,
|
1395 |
"should_log": false,
|
1396 |
"should_save": true,
|
1397 |
-
"should_training_stop":
|
1398 |
},
|
1399 |
"attributes": {}
|
1400 |
}
|
1401 |
},
|
1402 |
-
"total_flos":
|
1403 |
"train_batch_size": 1,
|
1404 |
"trial_name": null,
|
1405 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0012771392081736,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 196,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1380 |
"eval_samples_per_second": 145.877,
|
1381 |
"eval_steps_per_second": 145.877,
|
1382 |
"step": 195
|
1383 |
+
},
|
1384 |
+
{
|
1385 |
+
"epoch": 1.0012771392081736,
|
1386 |
+
"grad_norm": 0.08981695771217346,
|
1387 |
+
"learning_rate": 0.0,
|
1388 |
+
"loss": 12.4365,
|
1389 |
+
"step": 196
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 1.0012771392081736,
|
1393 |
+
"eval_loss": 10.354520797729492,
|
1394 |
+
"eval_runtime": 0.2791,
|
1395 |
+
"eval_samples_per_second": 150.484,
|
1396 |
+
"eval_steps_per_second": 150.484,
|
1397 |
+
"step": 196
|
1398 |
}
|
1399 |
],
|
1400 |
"logging_steps": 1,
|
|
|
1409 |
"should_evaluate": false,
|
1410 |
"should_log": false,
|
1411 |
"should_save": true,
|
1412 |
+
"should_training_stop": true
|
1413 |
},
|
1414 |
"attributes": {}
|
1415 |
}
|
1416 |
},
|
1417 |
+
"total_flos": 2534457999360.0,
|
1418 |
"train_batch_size": 1,
|
1419 |
"trial_name": null,
|
1420 |
"trial_params": null
|