Training in progress, step 2310, 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 sha256:5e3821f12f70f1fab88c8f69103be533fe5949c6b54be983c1e27933fb882a1a
|
| 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 sha256:3f426757bbfb5fa5684a160c886c281209bde4530c28b026925403ae78155200
|
| 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:fb95902d5fd5ba6c17854ef1d9ee94a8532ddb5c2aad6dd87156343153781609
|
| 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,
|
|
@@ -4148,6 +4148,24 @@
|
|
| 4148 |
"mean_token_accuracy": 0.6537044525146485,
|
| 4149 |
"num_tokens": 8389636.0,
|
| 4150 |
"step": 2300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4151 |
}
|
| 4152 |
],
|
| 4153 |
"logging_steps": 5,
|
|
@@ -4167,7 +4185,7 @@
|
|
| 4167 |
"attributes": {}
|
| 4168 |
}
|
| 4169 |
},
|
| 4170 |
-
"total_flos": 4.
|
| 4171 |
"train_batch_size": 4,
|
| 4172 |
"trial_name": null,
|
| 4173 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 17.76923076923077,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2310,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 4148 |
"mean_token_accuracy": 0.6537044525146485,
|
| 4149 |
"num_tokens": 8389636.0,
|
| 4150 |
"step": 2300
|
| 4151 |
+
},
|
| 4152 |
+
{
|
| 4153 |
+
"epoch": 17.73076923076923,
|
| 4154 |
+
"grad_norm": 0.0,
|
| 4155 |
+
"learning_rate": 3.848e-05,
|
| 4156 |
+
"loss": 1.7573,
|
| 4157 |
+
"mean_token_accuracy": 0.6542636543512345,
|
| 4158 |
+
"num_tokens": 8407513.0,
|
| 4159 |
+
"step": 2305
|
| 4160 |
+
},
|
| 4161 |
+
{
|
| 4162 |
+
"epoch": 17.76923076923077,
|
| 4163 |
+
"grad_norm": 0.0,
|
| 4164 |
+
"learning_rate": 3.8455000000000004e-05,
|
| 4165 |
+
"loss": 1.7613,
|
| 4166 |
+
"mean_token_accuracy": 0.641442459821701,
|
| 4167 |
+
"num_tokens": 8425390.0,
|
| 4168 |
+
"step": 2310
|
| 4169 |
}
|
| 4170 |
],
|
| 4171 |
"logging_steps": 5,
|
|
|
|
| 4185 |
"attributes": {}
|
| 4186 |
}
|
| 4187 |
},
|
| 4188 |
+
"total_flos": 4.2696331662606336e+17,
|
| 4189 |
"train_batch_size": 4,
|
| 4190 |
"trial_name": null,
|
| 4191 |
"trial_params": null
|