Training in progress, step 9480, 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 sha256:73c7ac765e6168c3fb1951cb9245e4d923527ebad53c604af0a23dd52b3b4eef
|
| 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:d9e62542fd159d489e59a8118497cdef3a0697c536af7b82a54aa1e6793cd728
|
| 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:f8756a40088de91ecc3ee09da067331eb446dc4695470d8a1b21e408c8220ad9
|
| 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": 72.
|
| 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,
|
|
@@ -17054,6 +17054,24 @@
|
|
| 17054 |
"mean_token_accuracy": 0.6577578127384186,
|
| 17055 |
"num_tokens": 34535704.0,
|
| 17056 |
"step": 9470
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17057 |
}
|
| 17058 |
],
|
| 17059 |
"logging_steps": 5,
|
|
@@ -17073,7 +17091,7 @@
|
|
| 17073 |
"attributes": {}
|
| 17074 |
}
|
| 17075 |
},
|
| 17076 |
-
"total_flos": 1.
|
| 17077 |
"train_batch_size": 4,
|
| 17078 |
"trial_name": null,
|
| 17079 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 72.92307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 9480,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 17054 |
"mean_token_accuracy": 0.6577578127384186,
|
| 17055 |
"num_tokens": 34535704.0,
|
| 17056 |
"step": 9470
|
| 17057 |
+
},
|
| 17058 |
+
{
|
| 17059 |
+
"epoch": 72.88461538461539,
|
| 17060 |
+
"grad_norm": 0.0,
|
| 17061 |
+
"learning_rate": 2.6300000000000002e-06,
|
| 17062 |
+
"loss": 1.7822,
|
| 17063 |
+
"mean_token_accuracy": 0.6439197540283204,
|
| 17064 |
+
"num_tokens": 34553487.0,
|
| 17065 |
+
"step": 9475
|
| 17066 |
+
},
|
| 17067 |
+
{
|
| 17068 |
+
"epoch": 72.92307692307692,
|
| 17069 |
+
"grad_norm": 0.0,
|
| 17070 |
+
"learning_rate": 2.605e-06,
|
| 17071 |
+
"loss": 1.6994,
|
| 17072 |
+
"mean_token_accuracy": 0.6599182695150375,
|
| 17073 |
+
"num_tokens": 34572061.0,
|
| 17074 |
+
"step": 9480
|
| 17075 |
}
|
| 17076 |
],
|
| 17077 |
"logging_steps": 5,
|
|
|
|
| 17091 |
"attributes": {}
|
| 17092 |
}
|
| 17093 |
},
|
| 17094 |
+
"total_flos": 1.753122153772155e+18,
|
| 17095 |
"train_batch_size": 4,
|
| 17096 |
"trial_name": null,
|
| 17097 |
"trial_params": null
|