Training in progress, step 9000, 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 sha256:81165dbe1b919bdbeece3315287a13a8b18835ce415bfb90a3e8bbd36d0ea657
|
| 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 sha256:5e6ecf6311a4ddbdc418cc7536de1a2ea31699bc218679e3f3dd946fc9c070dd
|
| 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 sha256:4d79052f03c4d6c1df3c12a532a0bd16984a5dac27be71daa0b047577059e155
|
| 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": 69.
|
| 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,
|
|
@@ -16190,6 +16190,24 @@
|
|
| 16190 |
"mean_token_accuracy": 0.6585129857063293,
|
| 16191 |
"num_tokens": 32786796.0,
|
| 16192 |
"step": 8990
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16193 |
}
|
| 16194 |
],
|
| 16195 |
"logging_steps": 5,
|
|
@@ -16209,7 +16227,7 @@
|
|
| 16209 |
"attributes": {}
|
| 16210 |
}
|
| 16211 |
},
|
| 16212 |
-
"total_flos": 1.
|
| 16213 |
"train_batch_size": 4,
|
| 16214 |
"trial_name": null,
|
| 16215 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9000,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16190 |
"mean_token_accuracy": 0.6585129857063293,
|
| 16191 |
"num_tokens": 32786796.0,
|
| 16192 |
"step": 8990
|
| 16193 |
+
},
|
| 16194 |
+
{
|
| 16195 |
+
"epoch": 69.1923076923077,
|
| 16196 |
+
"grad_norm": 0.0,
|
| 16197 |
+
"learning_rate": 5.03e-06,
|
| 16198 |
+
"loss": 1.8112,
|
| 16199 |
+
"mean_token_accuracy": 0.6334796369075775,
|
| 16200 |
+
"num_tokens": 32804348.0,
|
| 16201 |
+
"step": 8995
|
| 16202 |
+
},
|
| 16203 |
+
{
|
| 16204 |
+
"epoch": 69.23076923076923,
|
| 16205 |
+
"grad_norm": 0.0,
|
| 16206 |
+
"learning_rate": 5.005e-06,
|
| 16207 |
+
"loss": 1.7595,
|
| 16208 |
+
"mean_token_accuracy": 0.6397767275571823,
|
| 16209 |
+
"num_tokens": 32822708.0,
|
| 16210 |
+
"step": 9000
|
| 16211 |
}
|
| 16212 |
],
|
| 16213 |
"logging_steps": 5,
|
|
|
|
| 16227 |
"attributes": {}
|
| 16228 |
}
|
| 16229 |
},
|
| 16230 |
+
"total_flos": 1.664386522546176e+18,
|
| 16231 |
"train_batch_size": 4,
|
| 16232 |
"trial_name": null,
|
| 16233 |
"trial_params": null
|