Training in progress, step 2190, 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:e52f504cc027830dec2506fbc1b44ea062937b3c1ec245d172fa5b828c2721ca
|
| 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 sha256:5b44b261549e6cd5c612883e1326798f1404cd16b84340e8a7b2d2fed4d8a9db
|
| 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:ebccaa63a4aa42ec882d015df5959febc02388ab669fb7b04cb994353ba0138d
|
| 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": 16.
|
| 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,
|
|
@@ -3932,6 +3932,24 @@
|
|
| 3932 |
"mean_token_accuracy": 0.638142678141594,
|
| 3933 |
"num_tokens": 7950816.0,
|
| 3934 |
"step": 2180
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3935 |
}
|
| 3936 |
],
|
| 3937 |
"logging_steps": 5,
|
|
@@ -3951,7 +3969,7 @@
|
|
| 3951 |
"attributes": {}
|
| 3952 |
}
|
| 3953 |
},
|
| 3954 |
-
"total_flos": 4.
|
| 3955 |
"train_batch_size": 4,
|
| 3956 |
"trial_name": null,
|
| 3957 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 16.846153846153847,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2190,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3932 |
"mean_token_accuracy": 0.638142678141594,
|
| 3933 |
"num_tokens": 7950816.0,
|
| 3934 |
"step": 2180
|
| 3935 |
+
},
|
| 3936 |
+
{
|
| 3937 |
+
"epoch": 16.807692307692307,
|
| 3938 |
+
"grad_norm": 0.0,
|
| 3939 |
+
"learning_rate": 3.908e-05,
|
| 3940 |
+
"loss": 1.7457,
|
| 3941 |
+
"mean_token_accuracy": 0.6490698546171189,
|
| 3942 |
+
"num_tokens": 7969482.0,
|
| 3943 |
+
"step": 2185
|
| 3944 |
+
},
|
| 3945 |
+
{
|
| 3946 |
+
"epoch": 16.846153846153847,
|
| 3947 |
+
"grad_norm": 0.0,
|
| 3948 |
+
"learning_rate": 3.9055000000000005e-05,
|
| 3949 |
+
"loss": 1.7675,
|
| 3950 |
+
"mean_token_accuracy": 0.6475545018911362,
|
| 3951 |
+
"num_tokens": 7987748.0,
|
| 3952 |
+
"step": 2190
|
| 3953 |
}
|
| 3954 |
],
|
| 3955 |
"logging_steps": 5,
|
|
|
|
| 3969 |
"attributes": {}
|
| 3970 |
}
|
| 3971 |
},
|
| 3972 |
+
"total_flos": 4.046989871819981e+17,
|
| 3973 |
"train_batch_size": 4,
|
| 3974 |
"trial_name": null,
|
| 3975 |
"trial_params": null
|