Training in progress, step 8860, 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:be267ac24f4f527fccfb6a115b3b53411bc9db14a98c1a364992ffd91c1bedde
|
| 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:fbeb8704b2c233ec72b0d6884350fb3c35bae261e546e7879880120eb315490c
|
| 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:c1477ff2b8403e5397adaed42502cb85a3a45a02b428bf787cdd9090309437e6
|
| 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": 68.
|
| 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,
|
|
@@ -15938,6 +15938,24 @@
|
|
| 15938 |
"mean_token_accuracy": 0.6579635113477706,
|
| 15939 |
"num_tokens": 32275029.0,
|
| 15940 |
"step": 8850
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15941 |
}
|
| 15942 |
],
|
| 15943 |
"logging_steps": 5,
|
|
@@ -15957,7 +15975,7 @@
|
|
| 15957 |
"attributes": {}
|
| 15958 |
}
|
| 15959 |
},
|
| 15960 |
-
"total_flos": 1.
|
| 15961 |
"train_batch_size": 4,
|
| 15962 |
"trial_name": null,
|
| 15963 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.15384615384616,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8860,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15938 |
"mean_token_accuracy": 0.6579635113477706,
|
| 15939 |
"num_tokens": 32275029.0,
|
| 15940 |
"step": 8850
|
| 15941 |
+
},
|
| 15942 |
+
{
|
| 15943 |
+
"epoch": 68.11538461538461,
|
| 15944 |
+
"grad_norm": 0.0,
|
| 15945 |
+
"learning_rate": 5.73e-06,
|
| 15946 |
+
"loss": 1.7521,
|
| 15947 |
+
"mean_token_accuracy": 0.6502374112606049,
|
| 15948 |
+
"num_tokens": 32292737.0,
|
| 15949 |
+
"step": 8855
|
| 15950 |
+
},
|
| 15951 |
+
{
|
| 15952 |
+
"epoch": 68.15384615384616,
|
| 15953 |
+
"grad_norm": 0.0,
|
| 15954 |
+
"learning_rate": 5.705e-06,
|
| 15955 |
+
"loss": 1.7176,
|
| 15956 |
+
"mean_token_accuracy": 0.6563062936067581,
|
| 15957 |
+
"num_tokens": 32311081.0,
|
| 15958 |
+
"step": 8860
|
| 15959 |
}
|
| 15960 |
],
|
| 15961 |
"logging_steps": 5,
|
|
|
|
| 15975 |
"attributes": {}
|
| 15976 |
}
|
| 15977 |
},
|
| 15978 |
+
"total_flos": 1.6383515059372032e+18,
|
| 15979 |
"train_batch_size": 4,
|
| 15980 |
"trial_name": null,
|
| 15981 |
"trial_params": null
|