Training in progress, step 7350, 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 sha256:43629f7b135d3a644cf1c3aa290313f254d45692fdf41931358f4436488edfe0
|
| 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:eb6194167e22aade60befb2f57cad10f8994f7537abbea4996915165d11a4c6c
|
| 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:c1f81e5c58e9b2327305a1bdae0f89416dc24dcd1803ca91fbb12492434b4c59
|
| 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": 56.
|
| 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,
|
|
@@ -13220,6 +13220,24 @@
|
|
| 13220 |
"mean_token_accuracy": 0.6441579282283783,
|
| 13221 |
"num_tokens": 26767123.0,
|
| 13222 |
"step": 7340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13223 |
}
|
| 13224 |
],
|
| 13225 |
"logging_steps": 5,
|
|
@@ -13239,7 +13257,7 @@
|
|
| 13239 |
"attributes": {}
|
| 13240 |
}
|
| 13241 |
},
|
| 13242 |
-
"total_flos": 1.
|
| 13243 |
"train_batch_size": 4,
|
| 13244 |
"trial_name": null,
|
| 13245 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 56.53846153846154,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 7350,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 13220 |
"mean_token_accuracy": 0.6441579282283783,
|
| 13221 |
"num_tokens": 26767123.0,
|
| 13222 |
"step": 7340
|
| 13223 |
+
},
|
| 13224 |
+
{
|
| 13225 |
+
"epoch": 56.5,
|
| 13226 |
+
"grad_norm": 0.0,
|
| 13227 |
+
"learning_rate": 1.3280000000000002e-05,
|
| 13228 |
+
"loss": 1.7293,
|
| 13229 |
+
"mean_token_accuracy": 0.6540816992521286,
|
| 13230 |
+
"num_tokens": 26785021.0,
|
| 13231 |
+
"step": 7345
|
| 13232 |
+
},
|
| 13233 |
+
{
|
| 13234 |
+
"epoch": 56.53846153846154,
|
| 13235 |
+
"grad_norm": 0.0,
|
| 13236 |
+
"learning_rate": 1.3255000000000001e-05,
|
| 13237 |
+
"loss": 1.7353,
|
| 13238 |
+
"mean_token_accuracy": 0.6520332425832749,
|
| 13239 |
+
"num_tokens": 26803690.0,
|
| 13240 |
+
"step": 7350
|
| 13241 |
}
|
| 13242 |
],
|
| 13243 |
"logging_steps": 5,
|
|
|
|
| 13257 |
"attributes": {}
|
| 13258 |
}
|
| 13259 |
},
|
| 13260 |
+
"total_flos": 1.359002621104128e+18,
|
| 13261 |
"train_batch_size": 4,
|
| 13262 |
"trial_name": null,
|
| 13263 |
"trial_params": null
|