Training in progress, step 2290, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 70430032
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d972981bb70eec13eb230710f7d5fccc5c887035bdfd2f7f15f03673e797dba
|
| 3 |
size 70430032
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 141058579
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7ce96f7d7e489dcdab86e3a3f942398aaee186cd3644e541195f5e52a7cd898
|
| 3 |
size 141058579
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14645
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c2c6eb6e7a4b97be96175fc8cab533692b090f8e51f686250e1a39cb0acf203b
|
| 3 |
size 14645
|
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 sha256:99294bfd0bbfeb373d87ec34ab1c460706fc9f847c7dc4efa72f661c0a51b705
|
| 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": 0.
|
| 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,
|
|
@@ -2298,6 +2298,16 @@
|
|
| 2298 |
"mean_token_accuracy": 0.7575721621513367,
|
| 2299 |
"num_tokens": 10598042.0,
|
| 2300 |
"step": 2280
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2301 |
}
|
| 2302 |
],
|
| 2303 |
"logging_steps": 10,
|
|
@@ -2317,7 +2327,7 @@
|
|
| 2317 |
"attributes": {}
|
| 2318 |
}
|
| 2319 |
},
|
| 2320 |
-
"total_flos": 5.
|
| 2321 |
"train_batch_size": 4,
|
| 2322 |
"trial_name": null,
|
| 2323 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.4885333333333333,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2290,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2298 |
"mean_token_accuracy": 0.7575721621513367,
|
| 2299 |
"num_tokens": 10598042.0,
|
| 2300 |
"step": 2280
|
| 2301 |
+
},
|
| 2302 |
+
{
|
| 2303 |
+
"entropy": 0.9136553466320038,
|
| 2304 |
+
"epoch": 0.4885333333333333,
|
| 2305 |
+
"grad_norm": 0.2523214519023895,
|
| 2306 |
+
"learning_rate": 8.861069143594423e-05,
|
| 2307 |
+
"loss": 0.9898375511169434,
|
| 2308 |
+
"mean_token_accuracy": 0.7727992206811904,
|
| 2309 |
+
"num_tokens": 10640977.0,
|
| 2310 |
+
"step": 2290
|
| 2311 |
}
|
| 2312 |
],
|
| 2313 |
"logging_steps": 10,
|
|
|
|
| 2327 |
"attributes": {}
|
| 2328 |
}
|
| 2329 |
},
|
| 2330 |
+
"total_flos": 5.045623609225728e+16,
|
| 2331 |
"train_batch_size": 4,
|
| 2332 |
"trial_name": null,
|
| 2333 |
"trial_params": null
|