Training in progress, step 2240, 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:cbf8f35e02b47be1e56ca46ef473195ff9bd66be3066b8b56f63e7ee5fdcce16
|
| 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:bd0fa2722f88764cd80539c3c5b906b8436dfcc9ac950d5e32dfa77ed4c7ee9d
|
| 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 sha256:42e11840fa8572f47268c4bc4265601f3d257b8489303f069446375c7e013c53
|
| 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:f7191e8aec39dbfe02c73ac365799b6b127692ceda3fc10016619123797f49d7
|
| 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,
|
|
@@ -2248,6 +2248,16 @@
|
|
| 2248 |
"mean_token_accuracy": 0.7472389042377472,
|
| 2249 |
"num_tokens": 10361473.0,
|
| 2250 |
"step": 2230
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2251 |
}
|
| 2252 |
],
|
| 2253 |
"logging_steps": 10,
|
|
@@ -2267,7 +2277,7 @@
|
|
| 2267 |
"attributes": {}
|
| 2268 |
}
|
| 2269 |
},
|
| 2270 |
-
"total_flos": 4.
|
| 2271 |
"train_batch_size": 4,
|
| 2272 |
"trial_name": null,
|
| 2273 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.47786666666666666,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2240,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2248 |
"mean_token_accuracy": 0.7472389042377472,
|
| 2249 |
"num_tokens": 10361473.0,
|
| 2250 |
"step": 2230
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"entropy": 1.0787047080695629,
|
| 2254 |
+
"epoch": 0.47786666666666666,
|
| 2255 |
+
"grad_norm": 0.21470828354358673,
|
| 2256 |
+
"learning_rate": 8.915469715679175e-05,
|
| 2257 |
+
"loss": 1.2236790657043457,
|
| 2258 |
+
"mean_token_accuracy": 0.7383568711578846,
|
| 2259 |
+
"num_tokens": 10412214.0,
|
| 2260 |
+
"step": 2240
|
| 2261 |
}
|
| 2262 |
],
|
| 2263 |
"logging_steps": 10,
|
|
|
|
| 2277 |
"attributes": {}
|
| 2278 |
}
|
| 2279 |
},
|
| 2280 |
+
"total_flos": 4.938071462559744e+16,
|
| 2281 |
"train_batch_size": 4,
|
| 2282 |
"trial_name": null,
|
| 2283 |
"trial_params": null
|