Training in progress, step 1270, 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 sha256:87ca00a7083a3256421e0381919bba0ebafa8d68b0e038658a422c7ce79d52db
|
| 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 sha256:4547fef62ff4f39ed064ef9de064fd1aeff78fb2358129d94a1bff396e500d06
|
| 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 sha256:8c85ee6137205f46e6996743e6b55ffe0e0dcef40881494371a2c2f4c496d7d5
|
| 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 sha256:85627d36101078e134580414ab80328219c1e02227f84dc20f633834c211738c
|
| 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,
|
|
@@ -1278,6 +1278,16 @@
|
|
| 1278 |
"mean_token_accuracy": 0.7427652187645435,
|
| 1279 |
"num_tokens": 5864952.0,
|
| 1280 |
"step": 1260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1281 |
}
|
| 1282 |
],
|
| 1283 |
"logging_steps": 10,
|
|
@@ -1297,7 +1307,7 @@
|
|
| 1297 |
"attributes": {}
|
| 1298 |
}
|
| 1299 |
},
|
| 1300 |
-
"total_flos": 2.
|
| 1301 |
"train_batch_size": 4,
|
| 1302 |
"trial_name": null,
|
| 1303 |
"trial_params": null
|
|
|
|
| 2 |
"best_global_step": null,
|
| 3 |
"best_metric": null,
|
| 4 |
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.27093333333333336,
|
| 6 |
"eval_steps": 500,
|
| 7 |
+
"global_step": 1270,
|
| 8 |
"is_hyper_param_search": false,
|
| 9 |
"is_local_process_zero": true,
|
| 10 |
"is_world_process_zero": true,
|
|
|
|
| 1278 |
"mean_token_accuracy": 0.7427652187645435,
|
| 1279 |
"num_tokens": 5864952.0,
|
| 1280 |
"step": 1260
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"entropy": 1.0392154708504677,
|
| 1284 |
+
"epoch": 0.27093333333333336,
|
| 1285 |
+
"grad_norm": 0.2563996911048889,
|
| 1286 |
+
"learning_rate": 9.721373163146148e-05,
|
| 1287 |
+
"loss": 1.1769997596740722,
|
| 1288 |
+
"mean_token_accuracy": 0.7434597261250019,
|
| 1289 |
+
"num_tokens": 5910222.0,
|
| 1290 |
+
"step": 1270
|
| 1291 |
}
|
| 1292 |
],
|
| 1293 |
"logging_steps": 10,
|
|
|
|
| 1307 |
"attributes": {}
|
| 1308 |
}
|
| 1309 |
},
|
| 1310 |
+
"total_flos": 2.8041555856512e+16,
|
| 1311 |
"train_batch_size": 4,
|
| 1312 |
"trial_name": null,
|
| 1313 |
"trial_params": null
|