Training in progress, step 6090, 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:d85d6d880e92130ba91dc8eba1d039505fd2d8fb2f3de834ad798c24594b5477
|
| 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:cdf2878f594c55959f1062659245a443eea0ed58a5b66df9cc2fd3ac81306b8d
|
| 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 sha256:6c2e85aeca47628f6862dac0d4a13b894a3fbdcb1888dee39baad6d72b20d717
|
| 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,
|
|
@@ -10952,6 +10952,24 @@
|
|
| 10952 |
"mean_token_accuracy": 0.6463933974504471,
|
| 10953 |
"num_tokens": 22173083.0,
|
| 10954 |
"step": 6080
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10955 |
}
|
| 10956 |
],
|
| 10957 |
"logging_steps": 5,
|
|
@@ -10971,7 +10989,7 @@
|
|
| 10971 |
"attributes": {}
|
| 10972 |
}
|
| 10973 |
},
|
| 10974 |
-
"total_flos": 1.
|
| 10975 |
"train_batch_size": 4,
|
| 10976 |
"trial_name": null,
|
| 10977 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 46.84615384615385,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6090,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 10952 |
"mean_token_accuracy": 0.6463933974504471,
|
| 10953 |
"num_tokens": 22173083.0,
|
| 10954 |
"step": 6080
|
| 10955 |
+
},
|
| 10956 |
+
{
|
| 10957 |
+
"epoch": 46.80769230769231,
|
| 10958 |
+
"grad_norm": 0.0,
|
| 10959 |
+
"learning_rate": 1.9580000000000002e-05,
|
| 10960 |
+
"loss": 1.6809,
|
| 10961 |
+
"mean_token_accuracy": 0.6644227296113968,
|
| 10962 |
+
"num_tokens": 22191785.0,
|
| 10963 |
+
"step": 6085
|
| 10964 |
+
},
|
| 10965 |
+
{
|
| 10966 |
+
"epoch": 46.84615384615385,
|
| 10967 |
+
"grad_norm": 0.0,
|
| 10968 |
+
"learning_rate": 1.9555e-05,
|
| 10969 |
+
"loss": 1.6764,
|
| 10970 |
+
"mean_token_accuracy": 0.6619850039482117,
|
| 10971 |
+
"num_tokens": 22210517.0,
|
| 10972 |
+
"step": 6090
|
| 10973 |
}
|
| 10974 |
],
|
| 10975 |
"logging_steps": 5,
|
|
|
|
| 10989 |
"attributes": {}
|
| 10990 |
}
|
| 10991 |
},
|
| 10992 |
+
"total_flos": 1.1255944181066957e+18,
|
| 10993 |
"train_batch_size": 4,
|
| 10994 |
"trial_name": null,
|
| 10995 |
"trial_params": null
|