Training in progress, step 9020, 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 sha256:9625885bd84a8147d4d44face9dcd5051e99f08468fb49b2007548a71fe10582
|
| 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 sha256:09a59ee47ff388b92d9f830f0698f70574bb2f06e872ba22234e141702b80dbb
|
| 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:fa6855caafaf7f5701cab0b07c9e051344d2133b6e773a0ad400aa2efcb9ab9e
|
| 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,
|
|
@@ -16226,6 +16226,24 @@
|
|
| 16226 |
"mean_token_accuracy": 0.6387849062681198,
|
| 16227 |
"num_tokens": 32859210.0,
|
| 16228 |
"step": 9010
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16229 |
}
|
| 16230 |
],
|
| 16231 |
"logging_steps": 5,
|
|
@@ -16245,7 +16263,7 @@
|
|
| 16245 |
"attributes": {}
|
| 16246 |
}
|
| 16247 |
},
|
| 16248 |
-
"total_flos": 1.
|
| 16249 |
"train_batch_size": 4,
|
| 16250 |
"trial_name": null,
|
| 16251 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 69.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9020,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 16226 |
"mean_token_accuracy": 0.6387849062681198,
|
| 16227 |
"num_tokens": 32859210.0,
|
| 16228 |
"step": 9010
|
| 16229 |
+
},
|
| 16230 |
+
{
|
| 16231 |
+
"epoch": 69.34615384615384,
|
| 16232 |
+
"grad_norm": 0.0,
|
| 16233 |
+
"learning_rate": 4.93e-06,
|
| 16234 |
+
"loss": 1.717,
|
| 16235 |
+
"mean_token_accuracy": 0.6556219637393952,
|
| 16236 |
+
"num_tokens": 32877341.0,
|
| 16237 |
+
"step": 9015
|
| 16238 |
+
},
|
| 16239 |
+
{
|
| 16240 |
+
"epoch": 69.38461538461539,
|
| 16241 |
+
"grad_norm": 0.0,
|
| 16242 |
+
"learning_rate": 4.9050000000000005e-06,
|
| 16243 |
+
"loss": 1.7134,
|
| 16244 |
+
"mean_token_accuracy": 0.6564109534025192,
|
| 16245 |
+
"num_tokens": 32895282.0,
|
| 16246 |
+
"step": 9020
|
| 16247 |
}
|
| 16248 |
],
|
| 16249 |
"logging_steps": 5,
|
|
|
|
| 16263 |
"attributes": {}
|
| 16264 |
}
|
| 16265 |
},
|
| 16266 |
+
"total_flos": 1.6680956034023424e+18,
|
| 16267 |
"train_batch_size": 4,
|
| 16268 |
"trial_name": null,
|
| 16269 |
"trial_params": null
|