mgh6 commited on
Commit
077b486
·
verified ·
1 Parent(s): b4e4fc1

Training in progress, step 14900, 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:cf358de268a54776074310a54a7c12deb56462a5265576a1eda5921bba9c5323
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:254cb097d82f52b48192688439d847879779c84b9e7b185bc2bb3f35b20334c9
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0900ea58dd3831eedc9c64342e3517f37a47cd080a491487aa6e546116ba536d
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:878115f71d99220166294f74655505452e397cf1951036c84279398c72e9463a
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:c3385d00673ab26e974b24f32d495806cac9e9d296dd8eda75a158061b999e4f
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bee009a53a9aa4478b8e761b3c13ed15cacd0c8d68b6ea4c6a72494429254a
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4cbddae73c69a5a5e030d3ce88a9a12a39562863a4aaa77890660f67f9be7c7e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fb55b7bb8a389ad80171ddaf4f0710697d6e1dcfc19f3b0b419ab29c315d33
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": 29.595375722543352,
5
  "eval_steps": 500,
6
- "global_step": 14800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1275,6 +1275,13 @@
1275
  "learning_rate": 1.3333333333333334e-06,
1276
  "loss": 1.2181,
1277
  "step": 14800
 
 
 
 
 
 
 
1278
  }
1279
  ],
1280
  "logging_steps": 100,
@@ -1294,7 +1301,7 @@
1294
  "attributes": {}
1295
  }
1296
  },
1297
- "total_flos": 2.309883018661069e+19,
1298
  "train_batch_size": 8,
1299
  "trial_name": null,
1300
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 29.795344477425402,
5
  "eval_steps": 500,
6
+ "global_step": 14900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1275
  "learning_rate": 1.3333333333333334e-06,
1276
  "loss": 1.2181,
1277
  "step": 14800
1278
+ },
1279
+ {
1280
+ "epoch": 29.795344477425402,
1281
+ "grad_norm": 0.24452446401119232,
1282
+ "learning_rate": 6.666666666666667e-07,
1283
+ "loss": 1.2187,
1284
+ "step": 14900
1285
  }
1286
  ],
1287
  "logging_steps": 100,
 
1301
  "attributes": {}
1302
  }
1303
  },
1304
+ "total_flos": 2.3254905157798855e+19,
1305
  "train_batch_size": 8,
1306
  "trial_name": null,
1307
  "trial_params": null