mgh6 commited on
Commit
1b85407
·
verified ·
1 Parent(s): b45c668

Training in progress, step 14200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83578fd1ef847fbd512434e8e814b73214d4fe18b14da21938b0f1de430261a6
3
  size 8137792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a147ace780debb052006ef0eb04b1a9032dc02fb4383dd6f414cbf2326fa0b18
3
  size 8137792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f905659e27f07ff50feaf499ba3ff1f47905ec7392b038a71f228d2d96f4c530
3
  size 16386426
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4ab35c2c843a653cf3c0cec9c6284c9a079aefa7b19d92900ada2d0216234b
3
  size 16386426
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a9b04c899ea1a89096f164722838a31a13b7a0ea9ce50adea36a19a8764daea
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3f5cef0735bcc19bcd7240e6e9cb2709e7dd5bfaf6866d251f87ffd212fee40
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:456554d245f035021e2d35e5a86d11dd3ca6fef050137ba0f14e1801fe663639
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a379f28116fa8f30f2a5172371798929e0706b2a69c8dcbdbc485a0201d9b0f
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": 28.195594438369003,
5
  "eval_steps": 500,
6
- "global_step": 14100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1218,6 +1218,13 @@
1218
  "learning_rate": 6e-06,
1219
  "loss": 1.2172,
1220
  "step": 14100
 
 
 
 
 
 
 
1221
  }
1222
  ],
1223
  "logging_steps": 100,
@@ -1237,7 +1244,7 @@
1237
  "attributes": {}
1238
  }
1239
  },
1240
- "total_flos": 2.2006314545163796e+19,
1241
  "train_batch_size": 8,
1242
  "trial_name": null,
1243
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 28.395563193251053,
5
  "eval_steps": 500,
6
+ "global_step": 14200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1218
  "learning_rate": 6e-06,
1219
  "loss": 1.2172,
1220
  "step": 14100
1221
+ },
1222
+ {
1223
+ "epoch": 28.395563193251053,
1224
+ "grad_norm": 0.2334292083978653,
1225
+ "learning_rate": 5.333333333333334e-06,
1226
+ "loss": 1.2236,
1227
+ "step": 14200
1228
  }
1229
  ],
1230
  "logging_steps": 100,
 
1244
  "attributes": {}
1245
  }
1246
  },
1247
+ "total_flos": 2.2162389516351963e+19,
1248
  "train_batch_size": 8,
1249
  "trial_name": null,
1250
  "trial_params": null