Training in progress, step 2380, 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 sha256:3cfc94df1948867d085e105e320b2b8c6a0b046ddc60086e8e828c5ef65d8091
|
| 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:d80edb3dc59cf7129b1025d5afc6331bbbf1ef729a98c0f8de3864e318e2e08b
|
| 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:bd45251763048e57f61324cd3793c9364158d2cf969dd6a4eac12b56f3101007
|
| 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 sha256:5c6eec566df00974ba222ba4aead107902646903b39998420f3f73fc62064416
|
| 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,
|
|
@@ -2388,6 +2388,16 @@
|
|
| 2388 |
"mean_token_accuracy": 0.7652165532112122,
|
| 2389 |
"num_tokens": 11022983.0,
|
| 2390 |
"step": 2370
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2391 |
}
|
| 2392 |
],
|
| 2393 |
"logging_steps": 10,
|
|
@@ -2407,7 +2417,7 @@
|
|
| 2407 |
"attributes": {}
|
| 2408 |
}
|
| 2409 |
},
|
| 2410 |
-
"total_flos": 5.
|
| 2411 |
"train_batch_size": 4,
|
| 2412 |
"trial_name": null,
|
| 2413 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.5077333333333334,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2380,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2388 |
"mean_token_accuracy": 0.7652165532112122,
|
| 2389 |
"num_tokens": 11022983.0,
|
| 2390 |
"step": 2370
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"entropy": 0.945545606315136,
|
| 2394 |
+
"epoch": 0.5077333333333334,
|
| 2395 |
+
"grad_norm": 0.24525931477546692,
|
| 2396 |
+
"learning_rate": 8.76024489245708e-05,
|
| 2397 |
+
"loss": 0.9925324440002441,
|
| 2398 |
+
"mean_token_accuracy": 0.7643568038940429,
|
| 2399 |
+
"num_tokens": 11065494.0,
|
| 2400 |
+
"step": 2380
|
| 2401 |
}
|
| 2402 |
],
|
| 2403 |
"logging_steps": 10,
|
|
|
|
| 2417 |
"attributes": {}
|
| 2418 |
}
|
| 2419 |
},
|
| 2420 |
+
"total_flos": 5.248290622603469e+16,
|
| 2421 |
"train_batch_size": 4,
|
| 2422 |
"trial_name": null,
|
| 2423 |
"trial_params": null
|