Training in progress, step 3840, 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:d00a87700fa23fe5b0accb72e3eb7049236428036cc6b3bcddc1509245f441f4
|
| 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:e2ffa87a36ae70652ee838fb9649ccad5a4a2d6ca942b1c535a31099c2e3c20a
|
| 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 sha256:40d64318f3804b28d550506a81f9d0e7a13426403427520d4c9093d31d5c4e9d
|
| 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": 29.
|
| 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,
|
|
@@ -6902,6 +6902,24 @@
|
|
| 6902 |
"mean_token_accuracy": 0.6359264075756073,
|
| 6903 |
"num_tokens": 13969103.0,
|
| 6904 |
"step": 3830
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6905 |
}
|
| 6906 |
],
|
| 6907 |
"logging_steps": 5,
|
|
@@ -6921,7 +6939,7 @@
|
|
| 6921 |
"attributes": {}
|
| 6922 |
}
|
| 6923 |
},
|
| 6924 |
-
"total_flos": 7.
|
| 6925 |
"train_batch_size": 4,
|
| 6926 |
"trial_name": null,
|
| 6927 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 29.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3840,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6902 |
"mean_token_accuracy": 0.6359264075756073,
|
| 6903 |
"num_tokens": 13969103.0,
|
| 6904 |
"step": 3830
|
| 6905 |
+
},
|
| 6906 |
+
{
|
| 6907 |
+
"epoch": 29.5,
|
| 6908 |
+
"grad_norm": 0.0,
|
| 6909 |
+
"learning_rate": 3.083e-05,
|
| 6910 |
+
"loss": 1.7199,
|
| 6911 |
+
"mean_token_accuracy": 0.6523585051298142,
|
| 6912 |
+
"num_tokens": 13987413.0,
|
| 6913 |
+
"step": 3835
|
| 6914 |
+
},
|
| 6915 |
+
{
|
| 6916 |
+
"epoch": 29.53846153846154,
|
| 6917 |
+
"grad_norm": 0.0,
|
| 6918 |
+
"learning_rate": 3.0805e-05,
|
| 6919 |
+
"loss": 1.8455,
|
| 6920 |
+
"mean_token_accuracy": 0.6313353180885315,
|
| 6921 |
+
"num_tokens": 14004497.0,
|
| 6922 |
+
"step": 3840
|
| 6923 |
}
|
| 6924 |
],
|
| 6925 |
"logging_steps": 5,
|
|
|
|
| 6939 |
"attributes": {}
|
| 6940 |
}
|
| 6941 |
},
|
| 6942 |
+
"total_flos": 7.097015011147776e+17,
|
| 6943 |
"train_batch_size": 4,
|
| 6944 |
"trial_name": null,
|
| 6945 |
"trial_params": null
|