Training in progress, step 4360, 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 sha256:5dd22ad50eca0c97d3087dee9f828155637132c8493f95e5b45a650228e8fe4f
|
| 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 sha256:92c434b9032fd844ba9bea78485389833c3d56d0ecd7af4353bec3e35e2ec2ff
|
| 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:bceae117c299b3530d1c8082e7de8ba11c4a7a3879e946f34d1babb497a05267
|
| 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 sha256:0065d77907671e06967cc54d2afe420aaa55e85dbdfc2f6b3450358ac68ce592
|
| 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,
|
|
@@ -4368,6 +4368,16 @@
|
|
| 4368 |
"mean_token_accuracy": 0.7774942420423031,
|
| 4369 |
"num_tokens": 20248134.0,
|
| 4370 |
"step": 4350
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4371 |
}
|
| 4372 |
],
|
| 4373 |
"logging_steps": 10,
|
|
@@ -4387,7 +4397,7 @@
|
|
| 4387 |
"attributes": {}
|
| 4388 |
}
|
| 4389 |
},
|
| 4390 |
-
"total_flos": 9.
|
| 4391 |
"train_batch_size": 4,
|
| 4392 |
"trial_name": null,
|
| 4393 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.9301333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4360,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4368 |
"mean_token_accuracy": 0.7774942420423031,
|
| 4369 |
"num_tokens": 20248134.0,
|
| 4370 |
"step": 4350
|
| 4371 |
+
},
|
| 4372 |
+
{
|
| 4373 |
+
"entropy": 0.8857482261955738,
|
| 4374 |
+
"epoch": 0.9301333333333334,
|
| 4375 |
+
"grad_norm": 0.2634090483188629,
|
| 4376 |
+
"learning_rate": 5.825219062868118e-05,
|
| 4377 |
+
"loss": 0.9745967864990235,
|
| 4378 |
+
"mean_token_accuracy": 0.7782815754413605,
|
| 4379 |
+
"num_tokens": 20288504.0,
|
| 4380 |
+
"step": 4360
|
| 4381 |
}
|
| 4382 |
],
|
| 4383 |
"logging_steps": 10,
|
|
|
|
| 4397 |
"attributes": {}
|
| 4398 |
}
|
| 4399 |
},
|
| 4400 |
+
"total_flos": 9.6052452516523e+16,
|
| 4401 |
"train_batch_size": 4,
|
| 4402 |
"trial_name": null,
|
| 4403 |
"trial_params": null
|