Training in progress, step 6650, 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 sha256:7b060e9a6efd0cf2b801fbcd192f41b66eb14fd4a277ed05ecd9ea30b31ad44c
|
| 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 sha256:1dbfe5d350081af00b535d88a2802a89c4ed8aeddefcf849ceee3508c197a0ce
|
| 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 sha256:177a20d3760da4ad06d1291a788f72d5283e41868182482ec1ba93c6fe4e5b75
|
| 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": 51.
|
| 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,
|
|
@@ -11960,6 +11960,24 @@
|
|
| 11960 |
"mean_token_accuracy": 0.6608267247676849,
|
| 11961 |
"num_tokens": 24216830.0,
|
| 11962 |
"step": 6640
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11963 |
}
|
| 11964 |
],
|
| 11965 |
"logging_steps": 5,
|
|
@@ -11979,7 +11997,7 @@
|
|
| 11979 |
"attributes": {}
|
| 11980 |
}
|
| 11981 |
},
|
| 11982 |
-
"total_flos": 1.
|
| 11983 |
"train_batch_size": 4,
|
| 11984 |
"trial_name": null,
|
| 11985 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 51.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6650,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11960 |
"mean_token_accuracy": 0.6608267247676849,
|
| 11961 |
"num_tokens": 24216830.0,
|
| 11962 |
"step": 6640
|
| 11963 |
+
},
|
| 11964 |
+
{
|
| 11965 |
+
"epoch": 51.11538461538461,
|
| 11966 |
+
"grad_norm": 0.0,
|
| 11967 |
+
"learning_rate": 1.6780000000000002e-05,
|
| 11968 |
+
"loss": 1.7234,
|
| 11969 |
+
"mean_token_accuracy": 0.6543210685253144,
|
| 11970 |
+
"num_tokens": 24235082.0,
|
| 11971 |
+
"step": 6645
|
| 11972 |
+
},
|
| 11973 |
+
{
|
| 11974 |
+
"epoch": 51.15384615384615,
|
| 11975 |
+
"grad_norm": 0.0,
|
| 11976 |
+
"learning_rate": 1.6755e-05,
|
| 11977 |
+
"loss": 1.7839,
|
| 11978 |
+
"mean_token_accuracy": 0.64230475127697,
|
| 11979 |
+
"num_tokens": 24252383.0,
|
| 11980 |
+
"step": 6650
|
| 11981 |
}
|
| 11982 |
],
|
| 11983 |
"logging_steps": 5,
|
|
|
|
| 11997 |
"attributes": {}
|
| 11998 |
}
|
| 11999 |
},
|
| 12000 |
+
"total_flos": 1.2295456961377075e+18,
|
| 12001 |
"train_batch_size": 4,
|
| 12002 |
"trial_name": null,
|
| 12003 |
"trial_params": null
|