Training in progress, step 3440, 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 sha256:0656844c232bc4d3c14d31d83c0195a80186ab974a56d12612a10954c92af95f
|
| 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:ddc2fe5feac311dcca1abc1bf3c1e840ddbdeefd10c63236d30962089df9d09a
|
| 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:b155dc9690f39852c3f6d72f47a25cf1d63d5ab7a3c6479cdf979c88cbe8de79
|
| 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": 26.
|
| 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,
|
|
@@ -6182,6 +6182,24 @@
|
|
| 6182 |
"mean_token_accuracy": 0.6600462704896927,
|
| 6183 |
"num_tokens": 12510093.0,
|
| 6184 |
"step": 3430
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6185 |
}
|
| 6186 |
],
|
| 6187 |
"logging_steps": 5,
|
|
@@ -6201,7 +6219,7 @@
|
|
| 6201 |
"attributes": {}
|
| 6202 |
}
|
| 6203 |
},
|
| 6204 |
-
"total_flos": 6.
|
| 6205 |
"train_batch_size": 4,
|
| 6206 |
"trial_name": null,
|
| 6207 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 26.46153846153846,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 3440,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 6182 |
"mean_token_accuracy": 0.6600462704896927,
|
| 6183 |
"num_tokens": 12510093.0,
|
| 6184 |
"step": 3430
|
| 6185 |
+
},
|
| 6186 |
+
{
|
| 6187 |
+
"epoch": 26.423076923076923,
|
| 6188 |
+
"grad_norm": 0.0,
|
| 6189 |
+
"learning_rate": 3.283e-05,
|
| 6190 |
+
"loss": 1.7006,
|
| 6191 |
+
"mean_token_accuracy": 0.6607132166624069,
|
| 6192 |
+
"num_tokens": 12529121.0,
|
| 6193 |
+
"step": 3435
|
| 6194 |
+
},
|
| 6195 |
+
{
|
| 6196 |
+
"epoch": 26.46153846153846,
|
| 6197 |
+
"grad_norm": 0.0,
|
| 6198 |
+
"learning_rate": 3.2805e-05,
|
| 6199 |
+
"loss": 1.7692,
|
| 6200 |
+
"mean_token_accuracy": 0.6444113343954087,
|
| 6201 |
+
"num_tokens": 12546721.0,
|
| 6202 |
+
"step": 3440
|
| 6203 |
}
|
| 6204 |
],
|
| 6205 |
"logging_steps": 5,
|
|
|
|
| 6219 |
"attributes": {}
|
| 6220 |
}
|
| 6221 |
},
|
| 6222 |
+
"total_flos": 6.356846967452467e+17,
|
| 6223 |
"train_batch_size": 4,
|
| 6224 |
"trial_name": null,
|
| 6225 |
"trial_params": null
|