Training in progress, step 345, 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 sha256:29f690d14438f6e3cdf833fa2f4ab04a5fb0513845d4e9725f23ef543afb0ec1
|
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 37431220
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb96b39f96671416517824843ba7f65a0cc13e6fd2e4a1ff0f867425e9967b36
|
3 |
size 37431220
|
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 sha256:248bdad94673d0171b6613a2054004ce1fbd7cc6609011663f62eb8bd70a3480
|
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,
|
@@ -2408,6 +2408,20 @@
|
|
2408 |
"learning_rate": 1.590909090909091e-05,
|
2409 |
"loss": 1.1236,
|
2410 |
"step": 343
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2411 |
}
|
2412 |
],
|
2413 |
"logging_steps": 1,
|
@@ -2427,7 +2441,7 @@
|
|
2427 |
"attributes": {}
|
2428 |
}
|
2429 |
},
|
2430 |
-
"total_flos": 4.
|
2431 |
"train_batch_size": 4,
|
2432 |
"trial_name": null,
|
2433 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9465020576131687,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 345,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2408 |
"learning_rate": 1.590909090909091e-05,
|
2409 |
"loss": 1.1236,
|
2410 |
"step": 343
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 0.943758573388203,
|
2414 |
+
"grad_norm": 0.17219319939613342,
|
2415 |
+
"learning_rate": 1.5151515151515153e-05,
|
2416 |
+
"loss": 1.1849,
|
2417 |
+
"step": 344
|
2418 |
+
},
|
2419 |
+
{
|
2420 |
+
"epoch": 0.9465020576131687,
|
2421 |
+
"grad_norm": 0.15850085020065308,
|
2422 |
+
"learning_rate": 1.4393939393939396e-05,
|
2423 |
+
"loss": 1.1708,
|
2424 |
+
"step": 345
|
2425 |
}
|
2426 |
],
|
2427 |
"logging_steps": 1,
|
|
|
2441 |
"attributes": {}
|
2442 |
}
|
2443 |
},
|
2444 |
+
"total_flos": 4.277394643660677e+17,
|
2445 |
"train_batch_size": 4,
|
2446 |
"trial_name": null,
|
2447 |
"trial_params": null
|