Training in progress, step 6250, 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:a32367e3316481fa8129fab79c1942050844d8fbb8bceadd7202c2c2dc96a95a
|
| 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:be83475a02cd1daa491885a10734be028c930494081efa2e740d933f75caeedd
|
| 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 sha256:24b3a8c694429ae5718d5d4d433078f476cd4f70d6d42b194ef2a8099d776ab5
|
| 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": 48.
|
| 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,
|
|
@@ -11240,6 +11240,24 @@
|
|
| 11240 |
"mean_token_accuracy": 0.6477993667125702,
|
| 11241 |
"num_tokens": 22757040.0,
|
| 11242 |
"step": 6240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11243 |
}
|
| 11244 |
],
|
| 11245 |
"logging_steps": 5,
|
|
@@ -11259,7 +11277,7 @@
|
|
| 11259 |
"attributes": {}
|
| 11260 |
}
|
| 11261 |
},
|
| 11262 |
-
"total_flos": 1.
|
| 11263 |
"train_batch_size": 4,
|
| 11264 |
"trial_name": null,
|
| 11265 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11240 |
"mean_token_accuracy": 0.6477993667125702,
|
| 11241 |
"num_tokens": 22757040.0,
|
| 11242 |
"step": 6240
|
| 11243 |
+
},
|
| 11244 |
+
{
|
| 11245 |
+
"epoch": 48.03846153846154,
|
| 11246 |
+
"grad_norm": 0.0,
|
| 11247 |
+
"learning_rate": 1.878e-05,
|
| 11248 |
+
"loss": 1.7979,
|
| 11249 |
+
"mean_token_accuracy": 0.6381140261888504,
|
| 11250 |
+
"num_tokens": 22775082.0,
|
| 11251 |
+
"step": 6245
|
| 11252 |
+
},
|
| 11253 |
+
{
|
| 11254 |
+
"epoch": 48.07692307692308,
|
| 11255 |
+
"grad_norm": 0.0,
|
| 11256 |
+
"learning_rate": 1.8755e-05,
|
| 11257 |
+
"loss": 1.7172,
|
| 11258 |
+
"mean_token_accuracy": 0.6539857119321824,
|
| 11259 |
+
"num_tokens": 22793573.0,
|
| 11260 |
+
"step": 6250
|
| 11261 |
}
|
| 11262 |
],
|
| 11263 |
"logging_steps": 5,
|
|
|
|
| 11277 |
"attributes": {}
|
| 11278 |
}
|
| 11279 |
},
|
| 11280 |
+
"total_flos": 1.1553547110447514e+18,
|
| 11281 |
"train_batch_size": 4,
|
| 11282 |
"trial_name": null,
|
| 11283 |
"trial_params": null
|