Training in progress, step 7200, 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:f358327c88330497a406e963b13ddb78a003ce402317463b9b391b3552c32c42
|
| 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 sha256:980ff32120c1c2f47389cdf3a568451df6473122f8ed381198c99b7f92bc093c
|
| 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 sha256:4c0fe42d9eb363fe64268f45e07fb0a564f8976c5c7e4c71f6081125a32d037c
|
| 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": 55.
|
| 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,
|
|
@@ -12950,6 +12950,24 @@
|
|
| 12950 |
"mean_token_accuracy": 0.6342040151357651,
|
| 12951 |
"num_tokens": 26221347.0,
|
| 12952 |
"step": 7190
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12953 |
}
|
| 12954 |
],
|
| 12955 |
"logging_steps": 5,
|
|
@@ -12969,7 +12987,7 @@
|
|
| 12969 |
"attributes": {}
|
| 12970 |
}
|
| 12971 |
},
|
| 12972 |
-
"total_flos": 1.
|
| 12973 |
"train_batch_size": 4,
|
| 12974 |
"trial_name": null,
|
| 12975 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7200,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12950 |
"mean_token_accuracy": 0.6342040151357651,
|
| 12951 |
"num_tokens": 26221347.0,
|
| 12952 |
"step": 7190
|
| 12953 |
+
},
|
| 12954 |
+
{
|
| 12955 |
+
"epoch": 55.34615384615385,
|
| 12956 |
+
"grad_norm": 0.0,
|
| 12957 |
+
"learning_rate": 1.4030000000000001e-05,
|
| 12958 |
+
"loss": 1.7202,
|
| 12959 |
+
"mean_token_accuracy": 0.6536721408367157,
|
| 12960 |
+
"num_tokens": 26239690.0,
|
| 12961 |
+
"step": 7195
|
| 12962 |
+
},
|
| 12963 |
+
{
|
| 12964 |
+
"epoch": 55.38461538461539,
|
| 12965 |
+
"grad_norm": 0.0,
|
| 12966 |
+
"learning_rate": 1.4005000000000002e-05,
|
| 12967 |
+
"loss": 1.7623,
|
| 12968 |
+
"mean_token_accuracy": 0.6440413445234299,
|
| 12969 |
+
"num_tokens": 26257855.0,
|
| 12970 |
+
"step": 7200
|
| 12971 |
}
|
| 12972 |
],
|
| 12973 |
"logging_steps": 5,
|
|
|
|
| 12987 |
"attributes": {}
|
| 12988 |
}
|
| 12989 |
},
|
| 12990 |
+
"total_flos": 1.3314145856657818e+18,
|
| 12991 |
"train_batch_size": 4,
|
| 12992 |
"trial_name": null,
|
| 12993 |
"trial_params": null
|