Training in progress, step 338, 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 sha256:2b8a3eece0dc302434ef64183cab96e50003409d00c5c3306d0ef88aceb611bd
|
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 sha256:92caf4c36df1978405832c53a74c976a3189649219062536fb762290a417f73e
|
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 sha256:5421d489113a06f78cffb8ba158f8a76b5b37f551fb566a3800bdcadd25c598b
|
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,
|
@@ -2366,6 +2366,13 @@
|
|
2366 |
"learning_rate": 2.0454545454545457e-05,
|
2367 |
"loss": 1.1601,
|
2368 |
"step": 337
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2369 |
}
|
2370 |
],
|
2371 |
"logging_steps": 1,
|
@@ -2385,7 +2392,7 @@
|
|
2385 |
"attributes": {}
|
2386 |
}
|
2387 |
},
|
2388 |
-
"total_flos": 4.
|
2389 |
"train_batch_size": 4,
|
2390 |
"trial_name": null,
|
2391 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9272976680384087,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 338,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2366 |
"learning_rate": 2.0454545454545457e-05,
|
2367 |
"loss": 1.1601,
|
2368 |
"step": 337
|
2369 |
+
},
|
2370 |
+
{
|
2371 |
+
"epoch": 0.9272976680384087,
|
2372 |
+
"grad_norm": 0.16423514485359192,
|
2373 |
+
"learning_rate": 1.9696969696969697e-05,
|
2374 |
+
"loss": 1.1818,
|
2375 |
+
"step": 338
|
2376 |
}
|
2377 |
],
|
2378 |
"logging_steps": 1,
|
|
|
2392 |
"attributes": {}
|
2393 |
}
|
2394 |
},
|
2395 |
+
"total_flos": 4.18827695165313e+17,
|
2396 |
"train_batch_size": 4,
|
2397 |
"trial_name": null,
|
2398 |
"trial_params": null
|