Training in progress, step 5080, 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:fd1708825001eb19bc3351324b1353473b4e6d4697f80cba4ae65372c05352c0
|
| 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 sha256:66c3d1dd65af3bdd625f448cb2f9a99ccbc54ee4e67bdc853bd6a67e82e4220b
|
| 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 sha256:66062fe0592c15d9ef731d1fad928d60dfae8581458b02915ec3883d9c0aa637
|
| 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": 39.
|
| 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,
|
|
@@ -9134,6 +9134,24 @@
|
|
| 9134 |
"mean_token_accuracy": 0.6582199364900589,
|
| 9135 |
"num_tokens": 18490095.0,
|
| 9136 |
"step": 5070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9137 |
}
|
| 9138 |
],
|
| 9139 |
"logging_steps": 5,
|
|
@@ -9153,7 +9171,7 @@
|
|
| 9153 |
"attributes": {}
|
| 9154 |
}
|
| 9155 |
},
|
| 9156 |
-
"total_flos": 9.
|
| 9157 |
"train_batch_size": 4,
|
| 9158 |
"trial_name": null,
|
| 9159 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 39.07692307692308,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9134 |
"mean_token_accuracy": 0.6582199364900589,
|
| 9135 |
"num_tokens": 18490095.0,
|
| 9136 |
"step": 5070
|
| 9137 |
+
},
|
| 9138 |
+
{
|
| 9139 |
+
"epoch": 39.03846153846154,
|
| 9140 |
+
"grad_norm": 0.0,
|
| 9141 |
+
"learning_rate": 2.463e-05,
|
| 9142 |
+
"loss": 1.7668,
|
| 9143 |
+
"mean_token_accuracy": 0.6507688373327255,
|
| 9144 |
+
"num_tokens": 18507912.0,
|
| 9145 |
+
"step": 5075
|
| 9146 |
+
},
|
| 9147 |
+
{
|
| 9148 |
+
"epoch": 39.07692307692308,
|
| 9149 |
+
"grad_norm": 0.0,
|
| 9150 |
+
"learning_rate": 2.4605e-05,
|
| 9151 |
+
"loss": 1.7214,
|
| 9152 |
+
"mean_token_accuracy": 0.650596770644188,
|
| 9153 |
+
"num_tokens": 18526534.0,
|
| 9154 |
+
"step": 5080
|
| 9155 |
}
|
| 9156 |
],
|
| 9157 |
"logging_steps": 5,
|
|
|
|
| 9171 |
"attributes": {}
|
| 9172 |
}
|
| 9173 |
},
|
| 9174 |
+
"total_flos": 9.387455004986573e+17,
|
| 9175 |
"train_batch_size": 4,
|
| 9176 |
"trial_name": null,
|
| 9177 |
"trial_params": null
|