Training in progress, step 6230, 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:a4e39053b456b6df8110ce81bd2cb388f59e386eff388928f5268cada388626e
|
| 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 sha256:9cbb0c09fbc398d8d0fb7435bb3dc9d4c8cace4521cb5fe583739803e6fc1bfe
|
| 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:eacbb0aaa125dfae169985cf881b246f6b6f09da33c0ca6a7f00fffe4d8a4e94
|
| 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": 47.
|
| 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,
|
|
@@ -11204,6 +11204,24 @@
|
|
| 11204 |
"mean_token_accuracy": 0.6424293428659439,
|
| 11205 |
"num_tokens": 22684255.0,
|
| 11206 |
"step": 6220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11207 |
}
|
| 11208 |
],
|
| 11209 |
"logging_steps": 5,
|
|
@@ -11223,7 +11241,7 @@
|
|
| 11223 |
"attributes": {}
|
| 11224 |
}
|
| 11225 |
},
|
| 11226 |
-
"total_flos": 1.
|
| 11227 |
"train_batch_size": 4,
|
| 11228 |
"trial_name": null,
|
| 11229 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 47.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6230,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11204 |
"mean_token_accuracy": 0.6424293428659439,
|
| 11205 |
"num_tokens": 22684255.0,
|
| 11206 |
"step": 6220
|
| 11207 |
+
},
|
| 11208 |
+
{
|
| 11209 |
+
"epoch": 47.88461538461539,
|
| 11210 |
+
"grad_norm": 0.0,
|
| 11211 |
+
"learning_rate": 1.888e-05,
|
| 11212 |
+
"loss": 1.7513,
|
| 11213 |
+
"mean_token_accuracy": 0.6502956181764603,
|
| 11214 |
+
"num_tokens": 22702158.0,
|
| 11215 |
+
"step": 6225
|
| 11216 |
+
},
|
| 11217 |
+
{
|
| 11218 |
+
"epoch": 47.92307692307692,
|
| 11219 |
+
"grad_norm": 0.0,
|
| 11220 |
+
"learning_rate": 1.8855e-05,
|
| 11221 |
+
"loss": 1.6915,
|
| 11222 |
+
"mean_token_accuracy": 0.6557220876216888,
|
| 11223 |
+
"num_tokens": 22720730.0,
|
| 11224 |
+
"step": 6230
|
| 11225 |
}
|
| 11226 |
],
|
| 11227 |
"logging_steps": 5,
|
|
|
|
| 11241 |
"attributes": {}
|
| 11242 |
}
|
| 11243 |
},
|
| 11244 |
+
"total_flos": 1.1516195904086016e+18,
|
| 11245 |
"train_batch_size": 4,
|
| 11246 |
"trial_name": null,
|
| 11247 |
"trial_params": null
|