Training in progress, step 6240, 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:ef06dd2c2d7d6f97d7505849242dd61075bf48e9c3b63adbe39362bea7019fb1
|
| 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 sha256:2925af07797340fadb051d5b4621836fca1ac81472b67f21d0565c9ebae3b4a1
|
| 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 sha256:4fd8499aa1e60ae571d3af76eba49e34169775b5cc34369a47a9cebae944bece
|
| 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":
|
| 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,
|
|
@@ -11222,6 +11222,24 @@
|
|
| 11222 |
"mean_token_accuracy": 0.6557220876216888,
|
| 11223 |
"num_tokens": 22720730.0,
|
| 11224 |
"step": 6230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11225 |
}
|
| 11226 |
],
|
| 11227 |
"logging_steps": 5,
|
|
@@ -11241,7 +11259,7 @@
|
|
| 11241 |
"attributes": {}
|
| 11242 |
}
|
| 11243 |
},
|
| 11244 |
-
"total_flos": 1.
|
| 11245 |
"train_batch_size": 4,
|
| 11246 |
"trial_name": null,
|
| 11247 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 48.0,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 6240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 11222 |
"mean_token_accuracy": 0.6557220876216888,
|
| 11223 |
"num_tokens": 22720730.0,
|
| 11224 |
"step": 6230
|
| 11225 |
+
},
|
| 11226 |
+
{
|
| 11227 |
+
"epoch": 47.96153846153846,
|
| 11228 |
+
"grad_norm": 0.0,
|
| 11229 |
+
"learning_rate": 1.883e-05,
|
| 11230 |
+
"loss": 1.7548,
|
| 11231 |
+
"mean_token_accuracy": 0.6476509481668472,
|
| 11232 |
+
"num_tokens": 22739451.0,
|
| 11233 |
+
"step": 6235
|
| 11234 |
+
},
|
| 11235 |
+
{
|
| 11236 |
+
"epoch": 48.0,
|
| 11237 |
+
"grad_norm": 0.0,
|
| 11238 |
+
"learning_rate": 1.8805e-05,
|
| 11239 |
+
"loss": 1.7672,
|
| 11240 |
+
"mean_token_accuracy": 0.6477993667125702,
|
| 11241 |
+
"num_tokens": 22757040.0,
|
| 11242 |
+
"step": 6240
|
| 11243 |
}
|
| 11244 |
],
|
| 11245 |
"logging_steps": 5,
|
|
|
|
| 11259 |
"attributes": {}
|
| 11260 |
}
|
| 11261 |
},
|
| 11262 |
+
"total_flos": 1.153488738518139e+18,
|
| 11263 |
"train_batch_size": 4,
|
| 11264 |
"trial_name": null,
|
| 11265 |
"trial_params": null
|