Training in progress, step 15000, 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 8137792
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab62b036e6c74bbea4fb69133e34abb4845491f60ea7967f3f5d600d5293ada1
|
| 3 |
size 8137792
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 16386426
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71b67f31952b3ecf63d396c77002ec5b7f12d69c0d298d33e626c92e4236c805
|
| 3 |
size 16386426
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 15006
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5b60e51865475feea7983a999a9c8ee1c1ae4a2105bdd341789ac523b37238d
|
| 3 |
size 15006
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adf5bf452761c234e3daa85a999070bcf12b7ea957b65555b14a80fc069fa45d
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 29.
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -1282,6 +1282,21 @@
|
|
| 1282 |
"learning_rate": 6.666666666666667e-07,
|
| 1283 |
"loss": 1.2187,
|
| 1284 |
"step": 14900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1285 |
}
|
| 1286 |
],
|
| 1287 |
"logging_steps": 100,
|
|
@@ -1296,12 +1311,12 @@
|
|
| 1296 |
"should_evaluate": false,
|
| 1297 |
"should_log": false,
|
| 1298 |
"should_save": true,
|
| 1299 |
-
"should_training_stop":
|
| 1300 |
},
|
| 1301 |
"attributes": {}
|
| 1302 |
}
|
| 1303 |
},
|
| 1304 |
-
"total_flos": 2.
|
| 1305 |
"train_batch_size": 8,
|
| 1306 |
"trial_name": null,
|
| 1307 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 29.995313232307453,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 15000,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 1282 |
"learning_rate": 6.666666666666667e-07,
|
| 1283 |
"loss": 1.2187,
|
| 1284 |
"step": 14900
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 29.995313232307453,
|
| 1288 |
+
"grad_norm": 0.2524297833442688,
|
| 1289 |
+
"learning_rate": 0.0,
|
| 1290 |
+
"loss": 1.2169,
|
| 1291 |
+
"step": 15000
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 29.995313232307453,
|
| 1295 |
+
"eval_loss": 1.1003856658935547,
|
| 1296 |
+
"eval_runtime": 781.9983,
|
| 1297 |
+
"eval_samples_per_second": 19.849,
|
| 1298 |
+
"eval_steps_per_second": 2.482,
|
| 1299 |
+
"step": 15000
|
| 1300 |
}
|
| 1301 |
],
|
| 1302 |
"logging_steps": 100,
|
|
|
|
| 1311 |
"should_evaluate": false,
|
| 1312 |
"should_log": false,
|
| 1313 |
"should_save": true,
|
| 1314 |
+
"should_training_stop": true
|
| 1315 |
},
|
| 1316 |
"attributes": {}
|
| 1317 |
}
|
| 1318 |
},
|
| 1319 |
+
"total_flos": 2.341098012898702e+19,
|
| 1320 |
"train_batch_size": 8,
|
| 1321 |
"trial_name": null,
|
| 1322 |
"trial_params": null
|