Training in progress, step 3500, 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 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:147545bc2b1135ad79f934cd1ffb7b878d07d17f7fa1d836dbe3b074e3d27b55
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9285b9074f231c6dd4f861de030cb2487bde39f8a15846d614f75246f479e8d5
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e35f92023c887ea287693d571ef87464e8398ebfc3f675745a6b517bdf99f81b
|
| 3 |
size 14645
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1465
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6972c2bba3bb6e2a5273e33c196638e6297934ceff4b8cafa8f16f1c6dfaa995
|
| 3 |
size 1465
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -2,9 +2,9 @@
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
-
"epoch": 0.
|
| 6 |
"eval_steps": 500,
|
| 7 |
-
"global_step":
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
@@ -3508,6 +3508,16 @@
|
|
| 3508 |
"mean_token_accuracy": 0.7716259181499481,
|
| 3509 |
"num_tokens": 16261629.0,
|
| 3510 |
"step": 3490
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3511 |
}
|
| 3512 |
],
|
| 3513 |
"logging_steps": 10,
|
|
@@ -3527,7 +3537,7 @@
|
|
| 3527 |
"attributes": {}
|
| 3528 |
}
|
| 3529 |
},
|
| 3530 |
-
"total_flos": 7.
|
| 3531 |
"train_batch_size": 4,
|
| 3532 |
"trial_name": null,
|
| 3533 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7466666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3500,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3508 |
"mean_token_accuracy": 0.7716259181499481,
|
| 3509 |
"num_tokens": 16261629.0,
|
| 3510 |
"step": 3490
|
| 3511 |
+
},
|
| 3512 |
+
{
|
| 3513 |
+
"entropy": 0.9472721114754676,
|
| 3514 |
+
"epoch": 0.7466666666666667,
|
| 3515 |
+
"grad_norm": 0.2600723206996918,
|
| 3516 |
+
"learning_rate": 7.235342070451059e-05,
|
| 3517 |
+
"loss": 1.0361743927001954,
|
| 3518 |
+
"mean_token_accuracy": 0.761479677259922,
|
| 3519 |
+
"num_tokens": 16308149.0,
|
| 3520 |
+
"step": 3500
|
| 3521 |
}
|
| 3522 |
],
|
| 3523 |
"logging_steps": 10,
|
|
|
|
| 3537 |
"attributes": {}
|
| 3538 |
}
|
| 3539 |
},
|
| 3540 |
+
"total_flos": 7.724771959780147e+16,
|
| 3541 |
"train_batch_size": 4,
|
| 3542 |
"trial_name": null,
|
| 3543 |
"trial_params": null
|