Training in progress, step 6080, 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:f7365530e6cec23caad600582a05bab0a6042df2799d9d43b69f7aabebb17bfa
|
| 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 sha256:231cc54e97454b10cf5daad87ad627a03403200c0d9de97eba14b7f7d410c11f
|
| 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:af228ff0650c0edda187500f13b801cd4efb2110ba49124182a1e912b2bca95c
|
| 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": 46.
|
| 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,
|
|
@@ -10934,6 +10934,24 @@
|
|
| 10934 |
"mean_token_accuracy": 0.6524038523435592,
|
| 10935 |
"num_tokens": 22136815.0,
|
| 10936 |
"step": 6070
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10937 |
}
|
| 10938 |
],
|
| 10939 |
"logging_steps": 5,
|
|
@@ -10953,7 +10971,7 @@
|
|
| 10953 |
"attributes": {}
|
| 10954 |
}
|
| 10955 |
},
|
| 10956 |
-
"total_flos": 1.
|
| 10957 |
"train_batch_size": 4,
|
| 10958 |
"trial_name": null,
|
| 10959 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6080,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10934 |
"mean_token_accuracy": 0.6524038523435592,
|
| 10935 |
"num_tokens": 22136815.0,
|
| 10936 |
"step": 6070
|
| 10937 |
+
},
|
| 10938 |
+
{
|
| 10939 |
+
"epoch": 46.73076923076923,
|
| 10940 |
+
"grad_norm": 0.0,
|
| 10941 |
+
"learning_rate": 1.963e-05,
|
| 10942 |
+
"loss": 1.7857,
|
| 10943 |
+
"mean_token_accuracy": 0.6441529363393783,
|
| 10944 |
+
"num_tokens": 22154538.0,
|
| 10945 |
+
"step": 6075
|
| 10946 |
+
},
|
| 10947 |
+
{
|
| 10948 |
+
"epoch": 46.76923076923077,
|
| 10949 |
+
"grad_norm": 0.0,
|
| 10950 |
+
"learning_rate": 1.9605e-05,
|
| 10951 |
+
"loss": 1.7715,
|
| 10952 |
+
"mean_token_accuracy": 0.6463933974504471,
|
| 10953 |
+
"num_tokens": 22173083.0,
|
| 10954 |
+
"step": 6080
|
| 10955 |
}
|
| 10956 |
],
|
| 10957 |
"logging_steps": 5,
|
|
|
|
| 10971 |
"attributes": {}
|
| 10972 |
}
|
| 10973 |
},
|
| 10974 |
+
"total_flos": 1.1236814469527962e+18,
|
| 10975 |
"train_batch_size": 4,
|
| 10976 |
"trial_name": null,
|
| 10977 |
"trial_params": null
|