Training in progress, step 2300, 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 sha256:25777d4b1e19df6938f93a49ae4fd6a643a672eac4d577326d1235e09e721b8f
|
| 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 sha256:5916a8da5ddd576cc53de1bf016fda8ea98257e9143268097f444b9289e4abf5
|
| 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 sha256:85a542bdaa1414ef24dba57f4b2761bab55cae65a1369f43ae3040c3682ff5ce
|
| 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 sha256:935c260d8d47f6c3b3e6dac00fe9f85351319b3b4cc067e993776e133bb21141
|
| 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,
|
|
@@ -2308,6 +2308,16 @@
|
|
| 2308 |
"mean_token_accuracy": 0.7727992206811904,
|
| 2309 |
"num_tokens": 10640977.0,
|
| 2310 |
"step": 2290
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2311 |
}
|
| 2312 |
],
|
| 2313 |
"logging_steps": 10,
|
|
@@ -2327,7 +2337,7 @@
|
|
| 2327 |
"attributes": {}
|
| 2328 |
}
|
| 2329 |
},
|
| 2330 |
-
"total_flos": 5.
|
| 2331 |
"train_batch_size": 4,
|
| 2332 |
"trial_name": null,
|
| 2333 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.49066666666666664,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 2300,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 2308 |
"mean_token_accuracy": 0.7727992206811904,
|
| 2309 |
"num_tokens": 10640977.0,
|
| 2310 |
"step": 2290
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"entropy": 0.912187123298645,
|
| 2314 |
+
"epoch": 0.49066666666666664,
|
| 2315 |
+
"grad_norm": 0.2530852258205414,
|
| 2316 |
+
"learning_rate": 8.850049721021537e-05,
|
| 2317 |
+
"loss": 1.026146125793457,
|
| 2318 |
+
"mean_token_accuracy": 0.7669046297669411,
|
| 2319 |
+
"num_tokens": 10691324.0,
|
| 2320 |
+
"step": 2300
|
| 2321 |
}
|
| 2322 |
],
|
| 2323 |
"logging_steps": 10,
|
|
|
|
| 2337 |
"attributes": {}
|
| 2338 |
}
|
| 2339 |
},
|
| 2340 |
+
"total_flos": 5.068992285879091e+16,
|
| 2341 |
"train_batch_size": 4,
|
| 2342 |
"trial_name": null,
|
| 2343 |
"trial_params": null
|