Hugging Face's logo

duyphu
/
64d858fd-0ea9-bb1f-71f7-76dcd02f019f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
a8c6b0d
·
verified ·
1 Parent(s): 42e636b

Training in progress, step 26, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d459a0aea7c30cdd5b24b413c0474fb9242ef3b51745d27b00ca36583f0f86af
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa77daec98f4682dae9feaf287ce29fd89b4a4e2c6c0db04e33afe6dbd7b186f
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ae1a4013bfa6f5cd73b044f1cac13236ec595f2d83d14dc3fe283bf1293450e
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ac35e10218eaa88185a04809740300cf5a43901badc4d4e11921777af837f86
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
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": 0.0202729044834308,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 82.03,
38
  "eval_steps_per_second": 41.015,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 852261076992.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0405458089668616,
5
  "eval_steps": 10,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 82.03,
38
  "eval_steps_per_second": 41.015,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.023391812865497075,
43
+ "grad_norm": 2.732011556625366,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 10.1745,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.031189083820662766,
50
+ "grad_norm": 2.1478426456451416,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 10.0241,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.031189083820662766,
57
+ "eval_loss": 9.92287540435791,
58
+ "eval_runtime": 3.3845,
59
+ "eval_samples_per_second": 79.775,
60
+ "eval_steps_per_second": 39.888,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.03898635477582846,
65
+ "grad_norm": 1.9648786783218384,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 9.803,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1704522153984.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null