Training in progress, step 8870, 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 sha256:2b80591a35723747b1873355a07ae3427cf1ddc88e766df5afb942d03fe092f0
|
| 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 sha256:9265ed3845ef523b2188e3601804458096fa1a2a25d6eb54e0c0b1845d976308
|
| 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 sha256:17286af1b707a147172d984723836e15992a3116583aa9b575634d4b49594757
|
| 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,
|
|
@@ -15956,6 +15956,24 @@
|
|
| 15956 |
"mean_token_accuracy": 0.6563062936067581,
|
| 15957 |
"num_tokens": 32311081.0,
|
| 15958 |
"step": 8860
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15959 |
}
|
| 15960 |
],
|
| 15961 |
"logging_steps": 5,
|
|
@@ -15975,7 +15993,7 @@
|
|
| 15975 |
"attributes": {}
|
| 15976 |
}
|
| 15977 |
},
|
| 15978 |
-
"total_flos": 1.
|
| 15979 |
"train_batch_size": 4,
|
| 15980 |
"trial_name": null,
|
| 15981 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 68.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 8870,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 15956 |
"mean_token_accuracy": 0.6563062936067581,
|
| 15957 |
"num_tokens": 32311081.0,
|
| 15958 |
"step": 8860
|
| 15959 |
+
},
|
| 15960 |
+
{
|
| 15961 |
+
"epoch": 68.1923076923077,
|
| 15962 |
+
"grad_norm": 0.0,
|
| 15963 |
+
"learning_rate": 5.680000000000001e-06,
|
| 15964 |
+
"loss": 1.7643,
|
| 15965 |
+
"mean_token_accuracy": 0.6508367985486985,
|
| 15966 |
+
"num_tokens": 32328973.0,
|
| 15967 |
+
"step": 8865
|
| 15968 |
+
},
|
| 15969 |
+
{
|
| 15970 |
+
"epoch": 68.23076923076923,
|
| 15971 |
+
"grad_norm": 0.0,
|
| 15972 |
+
"learning_rate": 5.655000000000001e-06,
|
| 15973 |
+
"loss": 1.7741,
|
| 15974 |
+
"mean_token_accuracy": 0.6429946154356003,
|
| 15975 |
+
"num_tokens": 32346455.0,
|
| 15976 |
+
"step": 8870
|
| 15977 |
}
|
| 15978 |
],
|
| 15979 |
"logging_steps": 5,
|
|
|
|
| 15993 |
"attributes": {}
|
| 15994 |
}
|
| 15995 |
},
|
| 15996 |
+
"total_flos": 1.6401101437609574e+18,
|
| 15997 |
"train_batch_size": 4,
|
| 15998 |
"trial_name": null,
|
| 15999 |
"trial_params": null
|