Training in progress, step 510, 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:bf6caf3e778eef6b82cb5f838f414f4fe822e397cdfc9e1af4eb45213a34f5f1
|
| 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:f0a3fc71ee4cf01f780cc456f982aea91c0193b5e9b869c8cf346dfd99019cf2
|
| 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 sha256:3c85034853ecf8d241187033524202c8c549d2ced634eb4d1b552d3727ae073c
|
| 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": 3.
|
| 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,
|
|
@@ -908,6 +908,24 @@
|
|
| 908 |
"mean_token_accuracy": 0.6660710662603379,
|
| 909 |
"num_tokens": 1826017.0,
|
| 910 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 911 |
}
|
| 912 |
],
|
| 913 |
"logging_steps": 5,
|
|
@@ -927,7 +945,7 @@
|
|
| 927 |
"attributes": {}
|
| 928 |
}
|
| 929 |
},
|
| 930 |
-
"total_flos": 9.
|
| 931 |
"train_batch_size": 4,
|
| 932 |
"trial_name": null,
|
| 933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.9230769230769234,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 908 |
"mean_token_accuracy": 0.6660710662603379,
|
| 909 |
"num_tokens": 1826017.0,
|
| 910 |
"step": 500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 3.8846153846153846,
|
| 914 |
+
"grad_norm": 0.0,
|
| 915 |
+
"learning_rate": 4.748e-05,
|
| 916 |
+
"loss": 1.7516,
|
| 917 |
+
"mean_token_accuracy": 0.6497161477804184,
|
| 918 |
+
"num_tokens": 1843251.0,
|
| 919 |
+
"step": 505
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 3.9230769230769234,
|
| 923 |
+
"grad_norm": 0.0,
|
| 924 |
+
"learning_rate": 4.7455000000000006e-05,
|
| 925 |
+
"loss": 1.7586,
|
| 926 |
+
"mean_token_accuracy": 0.6480034649372101,
|
| 927 |
+
"num_tokens": 1861334.0,
|
| 928 |
+
"step": 510
|
| 929 |
}
|
| 930 |
],
|
| 931 |
"logging_steps": 5,
|
|
|
|
| 945 |
"attributes": {}
|
| 946 |
}
|
| 947 |
},
|
| 948 |
+
"total_flos": 9.433466025984e+16,
|
| 949 |
"train_batch_size": 4,
|
| 950 |
"trial_name": null,
|
| 951 |
"trial_params": null
|