Training in progress, step 3320, 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 sha256:5ca8aab3f42a92334fb88ee852e2737fe2ea149be267dcc1df7f1a11e7829711
|
| 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:edef98eaf58bf533bbf5af59bf44664e3ebcf03881534047f47026c682711523
|
| 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 sha256:98340413f80c7c012823362a7f779f257e6c720b0e2a5082f5ec15455eba69a7
|
| 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 sha256:15a6aa2e1178b0f38673123bff7ddda8c78ab40287a4c3cdac28b47fff4147bf
|
| 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,
|
|
@@ -3328,6 +3328,16 @@
|
|
| 3328 |
"mean_token_accuracy": 0.7397180199623108,
|
| 3329 |
"num_tokens": 15404947.0,
|
| 3330 |
"step": 3310
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3331 |
}
|
| 3332 |
],
|
| 3333 |
"logging_steps": 10,
|
|
@@ -3347,7 +3357,7 @@
|
|
| 3347 |
"attributes": {}
|
| 3348 |
}
|
| 3349 |
},
|
| 3350 |
-
"total_flos": 7.
|
| 3351 |
"train_batch_size": 4,
|
| 3352 |
"trial_name": null,
|
| 3353 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7082666666666667,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3320,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3328 |
"mean_token_accuracy": 0.7397180199623108,
|
| 3329 |
"num_tokens": 15404947.0,
|
| 3330 |
"step": 3310
|
| 3331 |
+
},
|
| 3332 |
+
{
|
| 3333 |
+
"entropy": 1.0128936409950255,
|
| 3334 |
+
"epoch": 0.7082666666666667,
|
| 3335 |
+
"grad_norm": 0.2553557753562927,
|
| 3336 |
+
"learning_rate": 7.509486654670137e-05,
|
| 3337 |
+
"loss": 1.0848438262939453,
|
| 3338 |
+
"mean_token_accuracy": 0.752461838722229,
|
| 3339 |
+
"num_tokens": 15454949.0,
|
| 3340 |
+
"step": 3320
|
| 3341 |
}
|
| 3342 |
],
|
| 3343 |
"logging_steps": 10,
|
|
|
|
| 3357 |
"attributes": {}
|
| 3358 |
}
|
| 3359 |
},
|
| 3360 |
+
"total_flos": 7.321964861000294e+16,
|
| 3361 |
"train_batch_size": 4,
|
| 3362 |
"trial_name": null,
|
| 3363 |
"trial_params": null
|