Training in progress, step 5540, 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 sha256:894864f2c0091428cf8a2ead0c98d03edeb1ecf22f4f60488fc973ef582771b6
|
| 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 sha256:814957d7455183df1806218eae5dd9d723142474fec74cee628ef112879f1a99
|
| 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:f2a19e8b3ee6d3c7dab465988cf27054742034b565ee343ed1f837c8b6fa0389
|
| 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,
|
|
@@ -9962,6 +9962,24 @@
|
|
| 9962 |
"mean_token_accuracy": 0.6519591569900512,
|
| 9963 |
"num_tokens": 20167484.0,
|
| 9964 |
"step": 5530
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9965 |
}
|
| 9966 |
],
|
| 9967 |
"logging_steps": 5,
|
|
@@ -9981,7 +9999,7 @@
|
|
| 9981 |
"attributes": {}
|
| 9982 |
}
|
| 9983 |
},
|
| 9984 |
-
"total_flos": 1.
|
| 9985 |
"train_batch_size": 4,
|
| 9986 |
"trial_name": null,
|
| 9987 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 42.61538461538461,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 5540,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 9962 |
"mean_token_accuracy": 0.6519591569900512,
|
| 9963 |
"num_tokens": 20167484.0,
|
| 9964 |
"step": 5530
|
| 9965 |
+
},
|
| 9966 |
+
{
|
| 9967 |
+
"epoch": 42.57692307692308,
|
| 9968 |
+
"grad_norm": 0.0,
|
| 9969 |
+
"learning_rate": 2.233e-05,
|
| 9970 |
+
"loss": 1.7865,
|
| 9971 |
+
"mean_token_accuracy": 0.6391574621200562,
|
| 9972 |
+
"num_tokens": 20184976.0,
|
| 9973 |
+
"step": 5535
|
| 9974 |
+
},
|
| 9975 |
+
{
|
| 9976 |
+
"epoch": 42.61538461538461,
|
| 9977 |
+
"grad_norm": 0.0,
|
| 9978 |
+
"learning_rate": 2.2305e-05,
|
| 9979 |
+
"loss": 1.6944,
|
| 9980 |
+
"mean_token_accuracy": 0.658808296918869,
|
| 9981 |
+
"num_tokens": 20203744.0,
|
| 9982 |
+
"step": 5540
|
| 9983 |
}
|
| 9984 |
],
|
| 9985 |
"logging_steps": 5,
|
|
|
|
| 9999 |
"attributes": {}
|
| 10000 |
}
|
| 10001 |
},
|
| 10002 |
+
"total_flos": 1.0237615714448179e+18,
|
| 10003 |
"train_batch_size": 4,
|
| 10004 |
"trial_name": null,
|
| 10005 |
"trial_params": null
|