Hugging Face's logo

tuantmdev
/
98c4404c-a951-4c8a-bd5b-7b42b6e12bf3

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
54252b9
·
verified ·
1 Parent(s): 7983dbb

Training in progress, step 120, 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 +18 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e45808247a98d905d56634458e45b56485f2c466bf3a2f36b2252c43c3809d5f
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f64683d4c8831f9b3e2febf41d40dd0c0239b51f2283a5c0dcdfdd253b6d755
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1215cc7c08790572b905259cccbd89955668654ccd365095130839b90289c409
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618799e1f69323eeabfbf249c6a3726278d81a61303b16a367ed9c62713b56fe
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e8963894e7d1e2c8464383a18c62429bb7e43744c459821239facd89eb57750
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4604a4b5237b87986eb44e035d79c1465c0958193ad1bb8451bd8a32011c9813
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:774252ad2ca59a173251c393bb9775b6ad50592c78a9adb425c0845b0166a283
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
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": 0.15748031496062992,
5
  "eval_steps": 40,
6
- "global_step": 80,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 149.158,
46
  "eval_steps_per_second": 74.579,
47
  "step": 80
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 40,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 63393595392.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.23622047244094488,
5
  "eval_steps": 40,
6
+ "global_step": 120,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 149.158,
46
  "eval_steps_per_second": 74.579,
47
  "step": 80
48
+ },
49
+ {
50
+ "epoch": 0.23622047244094488,
51
+ "grad_norm": 0.010611936450004578,
52
+ "learning_rate": 1.5000000000000002e-05,
53
+ "loss": 11.9305,
54
+ "step": 120
55
+ },
56
+ {
57
+ "epoch": 0.23622047244094488,
58
+ "eval_loss": 11.930538177490234,
59
+ "eval_runtime": 5.7383,
60
+ "eval_samples_per_second": 149.172,
61
+ "eval_steps_per_second": 74.586,
62
+ "step": 120
63
  }
64
  ],
65
  "logging_steps": 40,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 95179014144.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null