Hugging Face's logo

cwaud
/
8b9f3ed8-32c8-4775-8c13-0340b6b5faf3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cwaud commited on
Commit
7a63fba
•
1 Parent(s): 24f5db4

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 sha256:33ea8293e2ebba1645119b756f24536e47fd3cd2d5ed6d00bbe4dc202448e3fd
3
  size 97307544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac3627d6de3069b3e0fdf02b18c77895820c6d900ae7ed20c1d2a0cbf44ecb79
3
  size 97307544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29d04aad36858bf9988b7b2d49a78263db6ef1c2f4c13d8e97709961f0105fa4
3
  size 49846260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:642d842b2bfad90c8e6a93509ba68c4a3c169ceede9ef766f57f6452307e02c1
3
  size 49846260
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4911704193622166ee1ec426e2f5fd91f07b22078787c2fef6eb75e76ecfcebd
3
  size 14960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb8ce3b246ac7b214e8511f0933702c8eef2a192e03552fbd70bb29a15b06b11
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 sha256:7888e2cd4eccd4158073069db68c90b5a2a705a76d137387387b1327ab01b450
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9973d48d9bbe51ec0d66d6ad554d481faa409d2b1fb44e0ca5d08c274d21dc20
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:d95b812422568710ba718fb8a8d9f5eefb569a379b0b351686aa876aa4e735fd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:328ffded67cfa6abf4c93f77182952d6956017dd426f6d8589aecffd3c33a7a1
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 sha256:7b97f3eeaebec80884f44979aea2187cef9f94a36e6bca59ee17aa729de5af80
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c29b2f22a894575acde8eee9b3345021e389b523d4b883ec19eaf701b9fb5369
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5797a1f8ad35c151f6fb72a157c600abf1c5b502880ee9b620a878a10eb438e4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea67b5da66f242c315a67190bee42ac01d2c7b5f9d79262964d41c22411bb70
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": 3.6363636363636362,
5
  "eval_steps": 500,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -35,6 +35,13 @@
35
  "learning_rate": 1.8594235253127375e-05,
36
  "loss": 0.8338,
37
  "step": 4
 
 
 
 
 
 
 
38
  }
39
  ],
40
  "logging_steps": 1,
@@ -49,12 +56,12 @@
49
  "should_evaluate": false,
50
  "should_log": false,
51
  "should_save": true,
52
- "should_training_stop": false
53
  },
54
  "attributes": {}
55
  }
56
  },
57
- "total_flos": 3.689192720275866e+16,
58
  "train_batch_size": 6,
59
  "trial_name": null,
60
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 4.545454545454545,
5
  "eval_steps": 500,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
35
  "learning_rate": 1.8594235253127375e-05,
36
  "loss": 0.8338,
37
  "step": 4
38
+ },
39
+ {
40
+ "epoch": 4.545454545454545,
41
+ "grad_norm": 0.25607359409332275,
42
+ "learning_rate": 1e-05,
43
+ "loss": 0.8635,
44
+ "step": 5
45
  }
46
  ],
47
  "logging_steps": 1,
 
56
  "should_evaluate": false,
57
  "should_log": false,
58
  "should_save": true,
59
+ "should_training_stop": true
60
  },
61
  "attributes": {}
62
  }
63
  },
64
+ "total_flos": 4.192264440827085e+16,
65
  "train_batch_size": 6,
66
  "trial_name": null,
67
  "trial_params": null