Training in progress, step 3400, 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:f41f735dce6a8003468a6c5ce44f6c71b561894070d69313845b23d659d1bbe4
|
| 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 sha256:2c70bae3e0662b4f2b201d28815b5c6972cb61c75c7af8d599ae3ea571ca1e48
|
| 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:ffce0421169d0fa6689e5f4ddd7334b9181626336e190a84268a0d247c817a81
|
| 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 sha256:3aa10ccd5ad4dd3055471e16b2cf20f1af79ee5b90aea106c8b4b82baf4d79b9
|
| 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,
|
|
@@ -3408,6 +3408,16 @@
|
|
| 3408 |
"mean_token_accuracy": 0.7475218966603279,
|
| 3409 |
"num_tokens": 15789887.0,
|
| 3410 |
"step": 3390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3411 |
}
|
| 3412 |
],
|
| 3413 |
"logging_steps": 10,
|
|
@@ -3427,7 +3437,7 @@
|
|
| 3427 |
"attributes": {}
|
| 3428 |
}
|
| 3429 |
},
|
| 3430 |
-
"total_flos": 7.
|
| 3431 |
"train_batch_size": 4,
|
| 3432 |
"trial_name": null,
|
| 3433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7253333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3408 |
"mean_token_accuracy": 0.7475218966603279,
|
| 3409 |
"num_tokens": 15789887.0,
|
| 3410 |
"step": 3390
|
| 3411 |
+
},
|
| 3412 |
+
{
|
| 3413 |
+
"entropy": 1.0159111820161342,
|
| 3414 |
+
"epoch": 0.7253333333333334,
|
| 3415 |
+
"grad_norm": 0.2403489053249359,
|
| 3416 |
+
"learning_rate": 7.38878451162126e-05,
|
| 3417 |
+
"loss": 1.1378083229064941,
|
| 3418 |
+
"mean_token_accuracy": 0.7544682174921036,
|
| 3419 |
+
"num_tokens": 15837848.0,
|
| 3420 |
+
"step": 3400
|
| 3421 |
}
|
| 3422 |
],
|
| 3423 |
"logging_steps": 10,
|
|
|
|
| 3437 |
"attributes": {}
|
| 3438 |
}
|
| 3439 |
},
|
| 3440 |
+
"total_flos": 7.502343720778445e+16,
|
| 3441 |
"train_batch_size": 4,
|
| 3442 |
"trial_name": null,
|
| 3443 |
"trial_params": null
|