Training in progress, step 5510, 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:f3277a760b752450a53ba55c1b1c42633266d918ac9030b1e7f23ec146004393
|
| 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:d97a827592f7a2eb85c640aae9de83400891d9b49b459dadc5206b9491d51610
|
| 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 sha256:4fe80c1b6ab3b23674dd490767755aa250f40e99a42bbb9cdc59e501a2c3934a
|
| 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": 42.
|
| 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,
|
|
@@ -9908,6 +9908,24 @@
|
|
| 9908 |
"mean_token_accuracy": 0.647400951385498,
|
| 9909 |
"num_tokens": 20056196.0,
|
| 9910 |
"step": 5500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9911 |
}
|
| 9912 |
],
|
| 9913 |
"logging_steps": 5,
|
|
@@ -9927,7 +9945,7 @@
|
|
| 9927 |
"attributes": {}
|
| 9928 |
}
|
| 9929 |
},
|
| 9930 |
-
"total_flos": 1.
|
| 9931 |
"train_batch_size": 4,
|
| 9932 |
"trial_name": null,
|
| 9933 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.38461538461539,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5510,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9908 |
"mean_token_accuracy": 0.647400951385498,
|
| 9909 |
"num_tokens": 20056196.0,
|
| 9910 |
"step": 5500
|
| 9911 |
+
},
|
| 9912 |
+
{
|
| 9913 |
+
"epoch": 42.34615384615385,
|
| 9914 |
+
"grad_norm": 0.0,
|
| 9915 |
+
"learning_rate": 2.248e-05,
|
| 9916 |
+
"loss": 1.6555,
|
| 9917 |
+
"mean_token_accuracy": 0.6666512668132782,
|
| 9918 |
+
"num_tokens": 20075099.0,
|
| 9919 |
+
"step": 5505
|
| 9920 |
+
},
|
| 9921 |
+
{
|
| 9922 |
+
"epoch": 42.38461538461539,
|
| 9923 |
+
"grad_norm": 0.0,
|
| 9924 |
+
"learning_rate": 2.2455e-05,
|
| 9925 |
+
"loss": 1.7001,
|
| 9926 |
+
"mean_token_accuracy": 0.6635800451040268,
|
| 9927 |
+
"num_tokens": 20094237.0,
|
| 9928 |
+
"step": 5510
|
| 9929 |
}
|
| 9930 |
],
|
| 9931 |
"logging_steps": 5,
|
|
|
|
| 9945 |
"attributes": {}
|
| 9946 |
}
|
| 9947 |
},
|
| 9948 |
+
"total_flos": 1.0182141456334848e+18,
|
| 9949 |
"train_batch_size": 4,
|
| 9950 |
"trial_name": null,
|
| 9951 |
"trial_params": null
|