Training in progress, step 1780, 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:e23613d628fd461acd160677e673e94e45185decee30c9aec3cff2870d444b1c
|
| 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:b8755c7eca7e6c31b1fa6c4638df42ae00d6b6330a0a57f2ba1fc73a61913de2
|
| 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 sha256:11cccb2c0add2d34a4285ac64232eeb3914d8fa5137d6c43039a842a9394aa11
|
| 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": 13.
|
| 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,
|
|
@@ -3194,6 +3194,24 @@
|
|
| 3194 |
"mean_token_accuracy": 0.6407437533140182,
|
| 3195 |
"num_tokens": 6453594.0,
|
| 3196 |
"step": 1770
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3197 |
}
|
| 3198 |
],
|
| 3199 |
"logging_steps": 5,
|
|
@@ -3213,7 +3231,7 @@
|
|
| 3213 |
"attributes": {}
|
| 3214 |
}
|
| 3215 |
},
|
| 3216 |
-
"total_flos": 3.
|
| 3217 |
"train_batch_size": 4,
|
| 3218 |
"trial_name": null,
|
| 3219 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 13.692307692307692,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1780,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 3194 |
"mean_token_accuracy": 0.6407437533140182,
|
| 3195 |
"num_tokens": 6453594.0,
|
| 3196 |
"step": 1770
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 13.653846153846153,
|
| 3200 |
+
"grad_norm": 0.0,
|
| 3201 |
+
"learning_rate": 4.113e-05,
|
| 3202 |
+
"loss": 1.7622,
|
| 3203 |
+
"mean_token_accuracy": 0.642905455827713,
|
| 3204 |
+
"num_tokens": 6471529.0,
|
| 3205 |
+
"step": 1775
|
| 3206 |
+
},
|
| 3207 |
+
{
|
| 3208 |
+
"epoch": 13.692307692307692,
|
| 3209 |
+
"grad_norm": 0.0,
|
| 3210 |
+
"learning_rate": 4.110500000000001e-05,
|
| 3211 |
+
"loss": 1.7422,
|
| 3212 |
+
"mean_token_accuracy": 0.6522348582744598,
|
| 3213 |
+
"num_tokens": 6489689.0,
|
| 3214 |
+
"step": 1780
|
| 3215 |
}
|
| 3216 |
],
|
| 3217 |
"logging_steps": 5,
|
|
|
|
| 3231 |
"attributes": {}
|
| 3232 |
}
|
| 3233 |
},
|
| 3234 |
+
"total_flos": 3.2875079327760384e+17,
|
| 3235 |
"train_batch_size": 4,
|
| 3236 |
"trial_name": null,
|
| 3237 |
"trial_params": null
|