Training in progress, step 1070, 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 sha256:5df9ad7ac5119616ad6089f0f0a5eb894f5872befa741992474a9f0e5c93cbac
|
| 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 sha256:4d67f121aed1622bbb6341c6393be434df3517580d228dc9a35aa90a3e8a23c4
|
| 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 sha256:47bd5264ebc706a3cdfa305583ccf962ae9ee6651190f8e5d379fff5ade52708
|
| 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": 8.
|
| 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,
|
|
@@ -1916,6 +1916,24 @@
|
|
| 1916 |
"mean_token_accuracy": 0.6457870662212372,
|
| 1917 |
"num_tokens": 3864589.0,
|
| 1918 |
"step": 1060
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1919 |
}
|
| 1920 |
],
|
| 1921 |
"logging_steps": 5,
|
|
@@ -1935,7 +1953,7 @@
|
|
| 1935 |
"attributes": {}
|
| 1936 |
}
|
| 1937 |
},
|
| 1938 |
-
"total_flos": 1.
|
| 1939 |
"train_batch_size": 4,
|
| 1940 |
"trial_name": null,
|
| 1941 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.23076923076923,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1070,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1916 |
"mean_token_accuracy": 0.6457870662212372,
|
| 1917 |
"num_tokens": 3864589.0,
|
| 1918 |
"step": 1060
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 8.192307692307692,
|
| 1922 |
+
"grad_norm": 0.0,
|
| 1923 |
+
"learning_rate": 4.468e-05,
|
| 1924 |
+
"loss": 1.7206,
|
| 1925 |
+
"mean_token_accuracy": 0.655270129442215,
|
| 1926 |
+
"num_tokens": 3882774.0,
|
| 1927 |
+
"step": 1065
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 8.23076923076923,
|
| 1931 |
+
"grad_norm": 0.0,
|
| 1932 |
+
"learning_rate": 4.4655000000000005e-05,
|
| 1933 |
+
"loss": 1.6979,
|
| 1934 |
+
"mean_token_accuracy": 0.6581394881010055,
|
| 1935 |
+
"num_tokens": 3901162.0,
|
| 1936 |
+
"step": 1070
|
| 1937 |
}
|
| 1938 |
],
|
| 1939 |
"logging_steps": 5,
|
|
|
|
| 1953 |
"attributes": {}
|
| 1954 |
}
|
| 1955 |
},
|
| 1956 |
+
"total_flos": 1.9777403432337408e+17,
|
| 1957 |
"train_batch_size": 4,
|
| 1958 |
"trial_name": null,
|
| 1959 |
"trial_params": null
|