Training in progress, step 7210, 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 sha256:1283a55b5835cff3f15cf4dd6688649a8ee2fe56e946c118b1d75bc3e897ad95
|
| 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 sha256:360331e9acd9eeaf77117aa207e77bf9509c4bca231d09c7560b00b28573a8ab
|
| 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 sha256:35d0fc8f38fa73d62e2edaabd4fe1bb1ef9944acc23856528db5ec9bf5baa9b6
|
| 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,
|
|
@@ -12968,6 +12968,24 @@
|
|
| 12968 |
"mean_token_accuracy": 0.6440413445234299,
|
| 12969 |
"num_tokens": 26257855.0,
|
| 12970 |
"step": 7200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12971 |
}
|
| 12972 |
],
|
| 12973 |
"logging_steps": 5,
|
|
@@ -12987,7 +13005,7 @@
|
|
| 12987 |
"attributes": {}
|
| 12988 |
}
|
| 12989 |
},
|
| 12990 |
-
"total_flos": 1.
|
| 12991 |
"train_batch_size": 4,
|
| 12992 |
"trial_name": null,
|
| 12993 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 55.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7210,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 12968 |
"mean_token_accuracy": 0.6440413445234299,
|
| 12969 |
"num_tokens": 26257855.0,
|
| 12970 |
"step": 7200
|
| 12971 |
+
},
|
| 12972 |
+
{
|
| 12973 |
+
"epoch": 55.42307692307692,
|
| 12974 |
+
"grad_norm": 0.0,
|
| 12975 |
+
"learning_rate": 1.3980000000000002e-05,
|
| 12976 |
+
"loss": 1.7581,
|
| 12977 |
+
"mean_token_accuracy": 0.651086950302124,
|
| 12978 |
+
"num_tokens": 26275173.0,
|
| 12979 |
+
"step": 7205
|
| 12980 |
+
},
|
| 12981 |
+
{
|
| 12982 |
+
"epoch": 55.46153846153846,
|
| 12983 |
+
"grad_norm": 0.0,
|
| 12984 |
+
"learning_rate": 1.3955000000000001e-05,
|
| 12985 |
+
"loss": 1.7523,
|
| 12986 |
+
"mean_token_accuracy": 0.6518444687128067,
|
| 12987 |
+
"num_tokens": 26293084.0,
|
| 12988 |
+
"step": 7210
|
| 12989 |
}
|
| 12990 |
],
|
| 12991 |
"logging_steps": 5,
|
|
|
|
| 13005 |
"attributes": {}
|
| 13006 |
}
|
| 13007 |
},
|
| 13008 |
+
"total_flos": 1.333179892213678e+18,
|
| 13009 |
"train_batch_size": 4,
|
| 13010 |
"trial_name": null,
|
| 13011 |
"trial_params": null
|