Training in progress, step 4990, 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 sha256:91d1f95fb249c80236a12ffc71af7e34c6059690fee921c561e6434111dd418e
|
| 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 sha256:3fa051f25ec9522d085dbd33974e48353929f766fba21425db485f6394ceb86c
|
| 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 sha256:48f1e3082fc88c74401e6e77b97953ab62d0e88ba98ba7e812b1c12217ae0cf1
|
| 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": 38.
|
| 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,
|
|
@@ -8972,6 +8972,24 @@
|
|
| 8972 |
"mean_token_accuracy": 0.6391725331544876,
|
| 8973 |
"num_tokens": 18162910.0,
|
| 8974 |
"step": 4980
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8975 |
}
|
| 8976 |
],
|
| 8977 |
"logging_steps": 5,
|
|
@@ -8991,7 +9009,7 @@
|
|
| 8991 |
"attributes": {}
|
| 8992 |
}
|
| 8993 |
},
|
| 8994 |
-
"total_flos": 9.
|
| 8995 |
"train_batch_size": 4,
|
| 8996 |
"trial_name": null,
|
| 8997 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4990,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8972 |
"mean_token_accuracy": 0.6391725331544876,
|
| 8973 |
"num_tokens": 18162910.0,
|
| 8974 |
"step": 4980
|
| 8975 |
+
},
|
| 8976 |
+
{
|
| 8977 |
+
"epoch": 38.34615384615385,
|
| 8978 |
+
"grad_norm": 0.0,
|
| 8979 |
+
"learning_rate": 2.5080000000000004e-05,
|
| 8980 |
+
"loss": 1.7223,
|
| 8981 |
+
"mean_token_accuracy": 0.656527328491211,
|
| 8982 |
+
"num_tokens": 18181680.0,
|
| 8983 |
+
"step": 4985
|
| 8984 |
+
},
|
| 8985 |
+
{
|
| 8986 |
+
"epoch": 38.38461538461539,
|
| 8987 |
+
"grad_norm": 0.0,
|
| 8988 |
+
"learning_rate": 2.5055e-05,
|
| 8989 |
+
"loss": 1.7574,
|
| 8990 |
+
"mean_token_accuracy": 0.6486213862895965,
|
| 8991 |
+
"num_tokens": 18199714.0,
|
| 8992 |
+
"step": 4990
|
| 8993 |
}
|
| 8994 |
],
|
| 8995 |
"logging_steps": 5,
|
|
|
|
| 9009 |
"attributes": {}
|
| 9010 |
}
|
| 9011 |
},
|
| 9012 |
+
"total_flos": 9.222815320458854e+17,
|
| 9013 |
"train_batch_size": 4,
|
| 9014 |
"trial_name": null,
|
| 9015 |
"trial_params": null
|