Training in progress, step 2250, 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 sha256:36a8a3aa9593ce7e0458cc46521a36de0fa69e814f208db1edf3df6cc6c3ff06
|
| 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 sha256:8fc47c7bca4c986f3bc028295db0e6388dbd95079eb7ccd3903c25f47a60c22d
|
| 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 sha256:47ba7c0e1c66428a81418352b39e1639a120150de6ba322c36180515e7b5c222
|
| 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": 17.
|
| 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,
|
|
@@ -4040,6 +4040,24 @@
|
|
| 4040 |
"mean_token_accuracy": 0.6476239621639251,
|
| 4041 |
"num_tokens": 8170218.0,
|
| 4042 |
"step": 2240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4043 |
}
|
| 4044 |
],
|
| 4045 |
"logging_steps": 5,
|
|
@@ -4059,7 +4077,7 @@
|
|
| 4059 |
"attributes": {}
|
| 4060 |
}
|
| 4061 |
},
|
| 4062 |
-
"total_flos": 4.
|
| 4063 |
"train_batch_size": 4,
|
| 4064 |
"trial_name": null,
|
| 4065 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.307692307692307,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2250,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4040 |
"mean_token_accuracy": 0.6476239621639251,
|
| 4041 |
"num_tokens": 8170218.0,
|
| 4042 |
"step": 2240
|
| 4043 |
+
},
|
| 4044 |
+
{
|
| 4045 |
+
"epoch": 17.26923076923077,
|
| 4046 |
+
"grad_norm": 0.0,
|
| 4047 |
+
"learning_rate": 3.878e-05,
|
| 4048 |
+
"loss": 1.7575,
|
| 4049 |
+
"mean_token_accuracy": 0.6513453900814057,
|
| 4050 |
+
"num_tokens": 8188203.0,
|
| 4051 |
+
"step": 2245
|
| 4052 |
+
},
|
| 4053 |
+
{
|
| 4054 |
+
"epoch": 17.307692307692307,
|
| 4055 |
+
"grad_norm": 0.0,
|
| 4056 |
+
"learning_rate": 3.8755000000000004e-05,
|
| 4057 |
+
"loss": 1.794,
|
| 4058 |
+
"mean_token_accuracy": 0.6376719444990158,
|
| 4059 |
+
"num_tokens": 8206190.0,
|
| 4060 |
+
"step": 2250
|
| 4061 |
}
|
| 4062 |
],
|
| 4063 |
"logging_steps": 5,
|
|
|
|
| 4077 |
"attributes": {}
|
| 4078 |
}
|
| 4079 |
},
|
| 4080 |
+
"total_flos": 4.1586624209534976e+17,
|
| 4081 |
"train_batch_size": 4,
|
| 4082 |
"trial_name": null,
|
| 4083 |
"trial_params": null
|