Training in progress, step 7880, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1657
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2198585ee8158cb55a9a58c87d1242e6a56e7e29c3e24dabe101173daae90c79
|
| 3 |
size 1657
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14709
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ecb4acd6879770af76b28915e3d5a7247300e027f2f2c1256e8351c84c9b1692
|
| 3 |
size 14709
|
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 sha256:2412c0d3c37ad11eb94d097f4579dd00b2d16b32f0dba3af416c3682f83d80a2
|
| 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": 60.
|
| 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,
|
|
@@ -14174,6 +14174,24 @@
|
|
| 14174 |
"mean_token_accuracy": 0.6583037704229355,
|
| 14175 |
"num_tokens": 28701898.0,
|
| 14176 |
"step": 7870
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14177 |
}
|
| 14178 |
],
|
| 14179 |
"logging_steps": 5,
|
|
@@ -14193,7 +14211,7 @@
|
|
| 14193 |
"attributes": {}
|
| 14194 |
}
|
| 14195 |
},
|
| 14196 |
-
"total_flos": 1.
|
| 14197 |
"train_batch_size": 4,
|
| 14198 |
"trial_name": null,
|
| 14199 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 60.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7880,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 14174 |
"mean_token_accuracy": 0.6583037704229355,
|
| 14175 |
"num_tokens": 28701898.0,
|
| 14176 |
"step": 7870
|
| 14177 |
+
},
|
| 14178 |
+
{
|
| 14179 |
+
"epoch": 60.57692307692308,
|
| 14180 |
+
"grad_norm": 0.0,
|
| 14181 |
+
"learning_rate": 1.0630000000000002e-05,
|
| 14182 |
+
"loss": 1.7366,
|
| 14183 |
+
"mean_token_accuracy": 0.6519467145204544,
|
| 14184 |
+
"num_tokens": 28720551.0,
|
| 14185 |
+
"step": 7875
|
| 14186 |
+
},
|
| 14187 |
+
{
|
| 14188 |
+
"epoch": 60.61538461538461,
|
| 14189 |
+
"grad_norm": 0.0,
|
| 14190 |
+
"learning_rate": 1.0605000000000001e-05,
|
| 14191 |
+
"loss": 1.7621,
|
| 14192 |
+
"mean_token_accuracy": 0.6454852074384689,
|
| 14193 |
+
"num_tokens": 28738693.0,
|
| 14194 |
+
"step": 7880
|
| 14195 |
}
|
| 14196 |
],
|
| 14197 |
"logging_steps": 5,
|
|
|
|
| 14211 |
"attributes": {}
|
| 14212 |
}
|
| 14213 |
},
|
| 14214 |
+
"total_flos": 1.457198313863086e+18,
|
| 14215 |
"train_batch_size": 4,
|
| 14216 |
"trial_name": null,
|
| 14217 |
"trial_params": null
|