Training in progress, step 2260, 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 sha256:144677f64bb722a75657910254c9b53aec73907bb30f7fae21289a37c6ba9fcb
|
| 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 sha256:25309e1202347ad8fc1909537945da38c655b35564d3016adc8c6918761c8845
|
| 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 sha256:54ff895d49694534dbcf457c4364135e9e4df0a9c7bb41cb2b8a6e65dea20252
|
| 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 sha256:43e4106416f0e18c625209614bc82c2d49db0dbb5dcdfd6ed70850245c8dbfa1
|
| 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,
|
|
@@ -2268,6 +2268,16 @@
|
|
| 2268 |
"mean_token_accuracy": 0.7611462950706482,
|
| 2269 |
"num_tokens": 10457804.0,
|
| 2270 |
"step": 2250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2271 |
}
|
| 2272 |
],
|
| 2273 |
"logging_steps": 10,
|
|
@@ -2287,7 +2297,7 @@
|
|
| 2287 |
"attributes": {}
|
| 2288 |
}
|
| 2289 |
},
|
| 2290 |
-
"total_flos": 4.
|
| 2291 |
"train_batch_size": 4,
|
| 2292 |
"trial_name": null,
|
| 2293 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.48213333333333336,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2260,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2268 |
"mean_token_accuracy": 0.7611462950706482,
|
| 2269 |
"num_tokens": 10457804.0,
|
| 2270 |
"step": 2250
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"entropy": 0.8710766941308975,
|
| 2274 |
+
"epoch": 0.48213333333333336,
|
| 2275 |
+
"grad_norm": 0.23925144970417023,
|
| 2276 |
+
"learning_rate": 8.893849318116868e-05,
|
| 2277 |
+
"loss": 0.9463179588317872,
|
| 2278 |
+
"mean_token_accuracy": 0.7805656388401985,
|
| 2279 |
+
"num_tokens": 10496592.0,
|
| 2280 |
+
"step": 2260
|
| 2281 |
}
|
| 2282 |
],
|
| 2283 |
"logging_steps": 10,
|
|
|
|
| 2297 |
"attributes": {}
|
| 2298 |
}
|
| 2299 |
},
|
| 2300 |
+
"total_flos": 4.977467747646259e+16,
|
| 2301 |
"train_batch_size": 4,
|
| 2302 |
"trial_name": null,
|
| 2303 |
"trial_params": null
|