Training in progress, step 357, 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:cc2624a8ffcf1841a9421ca1f17277f4c8d9b072e238a8603e30cdfdae2cb8ca
|
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 sha256:210d9ceabe7e26d81c6de62edaa8bf5373afa8e36c75a23d9b951a596eda2c05
|
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 sha256:56085f5a51542351a94b27a3e2abb809af51b595632f72dc4fabbe92e8070a60
|
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,
|
@@ -2485,6 +2485,27 @@
|
|
2485 |
"learning_rate": 7.5757575757575764e-06,
|
2486 |
"loss": 1.175,
|
2487 |
"step": 354
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2488 |
}
|
2489 |
],
|
2490 |
"logging_steps": 1,
|
@@ -2504,7 +2525,7 @@
|
|
2504 |
"attributes": {}
|
2505 |
}
|
2506 |
},
|
2507 |
-
"total_flos": 4.
|
2508 |
"train_batch_size": 4,
|
2509 |
"trial_name": null,
|
2510 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9794238683127572,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 357,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2485 |
"learning_rate": 7.5757575757575764e-06,
|
2486 |
"loss": 1.175,
|
2487 |
"step": 354
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.9739368998628258,
|
2491 |
+
"grad_norm": 0.16342799365520477,
|
2492 |
+
"learning_rate": 6.818181818181818e-06,
|
2493 |
+
"loss": 1.2179,
|
2494 |
+
"step": 355
|
2495 |
+
},
|
2496 |
+
{
|
2497 |
+
"epoch": 0.9766803840877915,
|
2498 |
+
"grad_norm": 0.1597851812839508,
|
2499 |
+
"learning_rate": 6.060606060606061e-06,
|
2500 |
+
"loss": 1.1208,
|
2501 |
+
"step": 356
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 0.9794238683127572,
|
2505 |
+
"grad_norm": 0.16428720951080322,
|
2506 |
+
"learning_rate": 5.303030303030304e-06,
|
2507 |
+
"loss": 1.1197,
|
2508 |
+
"step": 357
|
2509 |
}
|
2510 |
],
|
2511 |
"logging_steps": 1,
|
|
|
2525 |
"attributes": {}
|
2526 |
}
|
2527 |
},
|
2528 |
+
"total_flos": 4.4192512511902925e+17,
|
2529 |
"train_batch_size": 4,
|
2530 |
"trial_name": null,
|
2531 |
"trial_params": null
|