Training in progress, step 3380, 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:bd3163ea4ecda2dd3295cc8084688e97c54a9b66618650e065018637b5623acb
|
| 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:bf86301750b1b5da2090cbb265bbc1fa9ec01099b683cb6f301cd75225067363
|
| 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 sha256:22c9f8513070c222196bbd9fb5737c7f860237d83ffb0525bd5ab7f8561ae027
|
| 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 sha256:82112089131b59c9c09e5311962aa5585309e7ce7360243d8a501733bc00b65c
|
| 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,
|
|
@@ -3388,6 +3388,16 @@
|
|
| 3388 |
"mean_token_accuracy": 0.7839296951889991,
|
| 3389 |
"num_tokens": 15691801.0,
|
| 3390 |
"step": 3370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3391 |
}
|
| 3392 |
],
|
| 3393 |
"logging_steps": 10,
|
|
@@ -3407,7 +3417,7 @@
|
|
| 3407 |
"attributes": {}
|
| 3408 |
}
|
| 3409 |
},
|
| 3410 |
-
"total_flos": 7.
|
| 3411 |
"train_batch_size": 4,
|
| 3412 |
"trial_name": null,
|
| 3413 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7210666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3388 |
"mean_token_accuracy": 0.7839296951889991,
|
| 3389 |
"num_tokens": 15691801.0,
|
| 3390 |
"step": 3370
|
| 3391 |
+
},
|
| 3392 |
+
{
|
| 3393 |
+
"entropy": 0.9314685501158237,
|
| 3394 |
+
"epoch": 0.7210666666666666,
|
| 3395 |
+
"grad_norm": 0.2979079782962799,
|
| 3396 |
+
"learning_rate": 7.419135403371976e-05,
|
| 3397 |
+
"loss": 1.051080322265625,
|
| 3398 |
+
"mean_token_accuracy": 0.7620216578245163,
|
| 3399 |
+
"num_tokens": 15736780.0,
|
| 3400 |
+
"step": 3380
|
| 3401 |
}
|
| 3402 |
],
|
| 3403 |
"logging_steps": 10,
|
|
|
|
| 3417 |
"attributes": {}
|
| 3418 |
}
|
| 3419 |
},
|
| 3420 |
+
"total_flos": 7.454063535555072e+16,
|
| 3421 |
"train_batch_size": 4,
|
| 3422 |
"trial_name": null,
|
| 3423 |
"trial_params": null
|