Training in progress, step 2400, 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:ca3edb767af2db5c9696c9950f7374913f7090936ec2cdbfde431ec3a86ad325
|
| 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:af1f4ddf789315e96cbf17dcdf74b128fd008ab5ca9c45b9b7439d99b8819c1f
|
| 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 sha256:5f8ed9bded014bd5f67ef92b18c77d5888fc7641dd1c54e595106bee829b861f
|
| 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 sha256:129b3f59411be48363861c37db911af3f82058403d8c8148d50126fb936d15af
|
| 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,
|
|
@@ -2408,6 +2408,16 @@
|
|
| 2408 |
"mean_token_accuracy": 0.7495349571108818,
|
| 2409 |
"num_tokens": 11117249.0,
|
| 2410 |
"step": 2390
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2411 |
}
|
| 2412 |
],
|
| 2413 |
"logging_steps": 10,
|
|
@@ -2427,7 +2437,7 @@
|
|
| 2427 |
"attributes": {}
|
| 2428 |
}
|
| 2429 |
},
|
| 2430 |
-
"total_flos": 5.
|
| 2431 |
"train_batch_size": 4,
|
| 2432 |
"trial_name": null,
|
| 2433 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.512,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2400,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2408 |
"mean_token_accuracy": 0.7495349571108818,
|
| 2409 |
"num_tokens": 11117249.0,
|
| 2410 |
"step": 2390
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"entropy": 1.0916487082839013,
|
| 2414 |
+
"epoch": 0.512,
|
| 2415 |
+
"grad_norm": 0.31891921162605286,
|
| 2416 |
+
"learning_rate": 8.737340441993575e-05,
|
| 2417 |
+
"loss": 1.1685538291931152,
|
| 2418 |
+
"mean_token_accuracy": 0.7355501770973205,
|
| 2419 |
+
"num_tokens": 11167106.0,
|
| 2420 |
+
"step": 2400
|
| 2421 |
}
|
| 2422 |
],
|
| 2423 |
"logging_steps": 10,
|
|
|
|
| 2437 |
"attributes": {}
|
| 2438 |
}
|
| 2439 |
},
|
| 2440 |
+
"total_flos": 5.297771188733952e+16,
|
| 2441 |
"train_batch_size": 4,
|
| 2442 |
"trial_name": null,
|
| 2443 |
"trial_params": null
|