Hugging Face's logo

cwaud
/
f5fd42be-f8cb-4dca-b32f-c0b597a2d94b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cwaud commited on
Commit
632e9c7
•
1 Parent(s): 1f0f155

Training in progress, epoch 4, checkpoint

Browse files
Files changed (8) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a295c65e834df6ad30155bea457609562e22ee1d02ad16d907b73d7d1f2909aa
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92e7653553106f5487b4568f065fcff01e871b5064b6ce0b6be2a6c2beaa4c9a
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:837c97016731cf82a7f70db849f6a5c120df2bdf43f36ce90e75730f85b44101
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32c9cd4c566095fb2c1f4c86ecefd67df698f79b0bdd2b5f3067e827186551b4
3
  size 170920084
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:353237ee00be739aac349f3ae4d1668ab41bdc74256634bf292a550e8ff50b5f
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3dcc2adfce09a6f4f8abee2ad2a06a4f04d93c4de476348d1fc8756787ebe03
3
  size 14960
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea0b93d76c78fd074764661821c85184a3c21a89deb10a6ac1a945344e25c6a6
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f3aab31e30d4e7ee314a381103779b056990764aad78d13f5806d0aeb883884
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3c40c6ce6c50dec9e38b006a82b4787c409519fa47d0fd30f00c97173d5d8b4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:507b540a2616276d6d39c39fe95e592fceb7ffd243ca7797f42ee1e2782a66d4
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7f357db828fc496f1dcfca45a8024cb91e63e2fcb8c2cfcb8ae31118aac3c68
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d59c15a60713c0c98220c72356036bf9b7133d5e83e621b6e33931ff542a3af6
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0263b1d852f25ca982e43a5d055004a85e649ca920793a8227ab5994ef136aa4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad5a5e2b4c54f46f276383a1fb17b730a33b1cc24c2198ee57c75fec0991496
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": 3.9888205701509225,
5
  "eval_steps": 500,
6
- "global_step": 223,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1568,6 +1568,13 @@
1568
  "learning_rate": 1.0004894577208057e-05,
1569
  "loss": 0.54,
1570
  "step": 223
 
 
 
 
 
 
 
1571
  }
1572
  ],
1573
  "logging_steps": 1,
@@ -1582,12 +1589,12 @@
1582
  "should_evaluate": false,
1583
  "should_log": false,
1584
  "should_save": true,
1585
- "should_training_stop": false
1586
  },
1587
  "attributes": {}
1588
  }
1589
  },
1590
- "total_flos": 5.338450796092588e+18,
1591
  "train_batch_size": 2,
1592
  "trial_name": null,
1593
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.0067076579094465,
5
  "eval_steps": 500,
6
+ "global_step": 224,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1568
  "learning_rate": 1.0004894577208057e-05,
1569
  "loss": 0.54,
1570
  "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 4.0067076579094465,
1574
+ "grad_norm": 0.5844184756278992,
1575
+ "learning_rate": 1e-05,
1576
+ "loss": 0.6349,
1577
+ "step": 224
1578
  }
1579
  ],
1580
  "logging_steps": 1,
 
1589
  "should_evaluate": false,
1590
  "should_log": false,
1591
  "should_save": true,
1592
+ "should_training_stop": true
1593
  },
1594
  "attributes": {}
1595
  }
1596
  },
1597
+ "total_flos": 5.347402921518563e+18,
1598
  "train_batch_size": 2,
1599
  "trial_name": null,
1600
  "trial_params": null