Training in progress, step 4960, 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 sha256:5803eb3e233fed994d071be3174a9e7575c29dc974feacc20af552145dc84020
|
| 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:a6fb503713b093ea13a3bc9517dac93309c60fd035ae0d1329e06dd12e42458a
|
| 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:e65be7ecf6e6d63af3300120682a219a65bf0b57c1eb7ff70ee62bb26e0661b8
|
| 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": 38.
|
| 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,
|
|
@@ -8918,6 +8918,24 @@
|
|
| 8918 |
"mean_token_accuracy": 0.6524750530719757,
|
| 8919 |
"num_tokens": 18052519.0,
|
| 8920 |
"step": 4950
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8921 |
}
|
| 8922 |
],
|
| 8923 |
"logging_steps": 5,
|
|
@@ -8937,7 +8955,7 @@
|
|
| 8937 |
"attributes": {}
|
| 8938 |
}
|
| 8939 |
},
|
| 8940 |
-
"total_flos": 9.
|
| 8941 |
"train_batch_size": 4,
|
| 8942 |
"trial_name": null,
|
| 8943 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 38.15384615384615,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4960,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8918 |
"mean_token_accuracy": 0.6524750530719757,
|
| 8919 |
"num_tokens": 18052519.0,
|
| 8920 |
"step": 4950
|
| 8921 |
+
},
|
| 8922 |
+
{
|
| 8923 |
+
"epoch": 38.11538461538461,
|
| 8924 |
+
"grad_norm": 0.0,
|
| 8925 |
+
"learning_rate": 2.5230000000000004e-05,
|
| 8926 |
+
"loss": 1.7571,
|
| 8927 |
+
"mean_token_accuracy": 0.6480519741773605,
|
| 8928 |
+
"num_tokens": 18070400.0,
|
| 8929 |
+
"step": 4955
|
| 8930 |
+
},
|
| 8931 |
+
{
|
| 8932 |
+
"epoch": 38.15384615384615,
|
| 8933 |
+
"grad_norm": 0.0,
|
| 8934 |
+
"learning_rate": 2.5205e-05,
|
| 8935 |
+
"loss": 1.6892,
|
| 8936 |
+
"mean_token_accuracy": 0.6499431103467941,
|
| 8937 |
+
"num_tokens": 18089731.0,
|
| 8938 |
+
"step": 4960
|
| 8939 |
}
|
| 8940 |
],
|
| 8941 |
"logging_steps": 5,
|
|
|
|
| 8955 |
"attributes": {}
|
| 8956 |
}
|
| 8957 |
},
|
| 8958 |
+
"total_flos": 9.167412512961331e+17,
|
| 8959 |
"train_batch_size": 4,
|
| 8960 |
"trial_name": null,
|
| 8961 |
"trial_params": null
|