Training in progress, step 3300, 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 sha256:279a914ee367624a13ecda02b36d93c216504742ae91a74ddc185f0e4fa7acdd
|
| 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:ec5d2cccb2877266a5193654a1f615a7810f37a292922ce137d68cd5de9c547c
|
| 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:f7d7d491557359c384eb19b68a6049f35ea03b02bfecea570a74cb7561a24b92
|
| 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:d2afd0e2043c7166de33bc9bf7754be031080ee6f459516412c5b4c89ff03e42
|
| 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,
|
|
@@ -3308,6 +3308,16 @@
|
|
| 3308 |
"mean_token_accuracy": 0.7824687540531159,
|
| 3309 |
"num_tokens": 15302428.0,
|
| 3310 |
"step": 3290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3311 |
}
|
| 3312 |
],
|
| 3313 |
"logging_steps": 10,
|
|
@@ -3327,7 +3337,7 @@
|
|
| 3327 |
"attributes": {}
|
| 3328 |
}
|
| 3329 |
},
|
| 3330 |
-
"total_flos": 7.
|
| 3331 |
"train_batch_size": 4,
|
| 3332 |
"trial_name": null,
|
| 3333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.704,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3308 |
"mean_token_accuracy": 0.7824687540531159,
|
| 3309 |
"num_tokens": 15302428.0,
|
| 3310 |
"step": 3290
|
| 3311 |
+
},
|
| 3312 |
+
{
|
| 3313 |
+
"entropy": 0.9096255600452423,
|
| 3314 |
+
"epoch": 0.704,
|
| 3315 |
+
"grad_norm": 0.2182462513446808,
|
| 3316 |
+
"learning_rate": 7.539365119163204e-05,
|
| 3317 |
+
"loss": 0.9878718376159668,
|
| 3318 |
+
"mean_token_accuracy": 0.7683326050639152,
|
| 3319 |
+
"num_tokens": 15350117.0,
|
| 3320 |
+
"step": 3300
|
| 3321 |
}
|
| 3322 |
],
|
| 3323 |
"logging_steps": 10,
|
|
|
|
| 3337 |
"attributes": {}
|
| 3338 |
}
|
| 3339 |
},
|
| 3340 |
+
"total_flos": 7.272356326334669e+16,
|
| 3341 |
"train_batch_size": 4,
|
| 3342 |
"trial_name": null,
|
| 3343 |
"trial_params": null
|