Training in progress, step 4470, 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:e9db690d4c1cbb8b42e3f89ea61e45dfc98c196340f3b0d78c41e774dc1ba45a
|
| 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 sha256:5ffcb32695e4ade3d79bf774905c465d60361b3939547b1c9ff4f75a71dbf25b
|
| 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:a6ef2579558878f8e416b8cb25ad2c204fd9d6e13969f88696672da7bd02a4da
|
| 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": 34.
|
| 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,
|
|
@@ -8036,6 +8036,24 @@
|
|
| 8036 |
"mean_token_accuracy": 0.6431075096130371,
|
| 8037 |
"num_tokens": 16265073.0,
|
| 8038 |
"step": 4460
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8039 |
}
|
| 8040 |
],
|
| 8041 |
"logging_steps": 5,
|
|
@@ -8055,7 +8073,7 @@
|
|
| 8055 |
"attributes": {}
|
| 8056 |
}
|
| 8057 |
},
|
| 8058 |
-
"total_flos": 8.
|
| 8059 |
"train_batch_size": 4,
|
| 8060 |
"trial_name": null,
|
| 8061 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 34.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 4470,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 8036 |
"mean_token_accuracy": 0.6431075096130371,
|
| 8037 |
"num_tokens": 16265073.0,
|
| 8038 |
"step": 4460
|
| 8039 |
+
},
|
| 8040 |
+
{
|
| 8041 |
+
"epoch": 34.34615384615385,
|
| 8042 |
+
"grad_norm": 0.0,
|
| 8043 |
+
"learning_rate": 2.768e-05,
|
| 8044 |
+
"loss": 1.6605,
|
| 8045 |
+
"mean_token_accuracy": 0.6640267461538315,
|
| 8046 |
+
"num_tokens": 16283741.0,
|
| 8047 |
+
"step": 4465
|
| 8048 |
+
},
|
| 8049 |
+
{
|
| 8050 |
+
"epoch": 34.38461538461539,
|
| 8051 |
+
"grad_norm": 0.0,
|
| 8052 |
+
"learning_rate": 2.7655000000000002e-05,
|
| 8053 |
+
"loss": 1.7335,
|
| 8054 |
+
"mean_token_accuracy": 0.6550962030887604,
|
| 8055 |
+
"num_tokens": 16301795.0,
|
| 8056 |
+
"step": 4470
|
| 8057 |
}
|
| 8058 |
],
|
| 8059 |
"logging_steps": 5,
|
|
|
|
| 8073 |
"attributes": {}
|
| 8074 |
}
|
| 8075 |
},
|
| 8076 |
+
"total_flos": 8.260910611247923e+17,
|
| 8077 |
"train_batch_size": 4,
|
| 8078 |
"trial_name": null,
|
| 8079 |
"trial_params": null
|