Training in progress, step 197, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2578d0630ecf659de062330437f2ab118f2bb6371e98b5d7f02cd4c84996cced
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f0afae3ebba9d0af5bee6787ab79cbf9170b2f759d14ea54267d8db2a83507f
|
3 |
size 37430836
|
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 sha256:26a269a2cea20ade02f5153afabb9927aa1d806bfa877265376ea45d5823b7de
|
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": 0.
|
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,
|
@@ -1379,6 +1379,13 @@
|
|
1379 |
"learning_rate": 0.00012727272727272728,
|
1380 |
"loss": 1.2407,
|
1381 |
"step": 196
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1382 |
}
|
1383 |
],
|
1384 |
"logging_steps": 1,
|
@@ -1398,7 +1405,7 @@
|
|
1398 |
"attributes": {}
|
1399 |
}
|
1400 |
},
|
1401 |
-
"total_flos": 2.
|
1402 |
"train_batch_size": 4,
|
1403 |
"trial_name": null,
|
1404 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.5404663923182441,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 197,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1379 |
"learning_rate": 0.00012727272727272728,
|
1380 |
"loss": 1.2407,
|
1381 |
"step": 196
|
1382 |
+
},
|
1383 |
+
{
|
1384 |
+
"epoch": 0.5404663923182441,
|
1385 |
+
"grad_norm": 0.22619858384132385,
|
1386 |
+
"learning_rate": 0.00012651515151515153,
|
1387 |
+
"loss": 1.2623,
|
1388 |
+
"step": 197
|
1389 |
}
|
1390 |
],
|
1391 |
"logging_steps": 1,
|
|
|
1405 |
"attributes": {}
|
1406 |
}
|
1407 |
},
|
1408 |
+
"total_flos": 2.4436699819317658e+17,
|
1409 |
"train_batch_size": 4,
|
1410 |
"trial_name": null,
|
1411 |
"trial_params": null
|