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
343cfd8
·
verified ·
1 Parent(s): 94e5f8f

Training in progress, step 160, 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 sha256:7f64683d4c8831f9b3e2febf41d40dd0c0239b51f2283a5c0dcdfdd253b6d755
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d3bbaaad92c2bab08d3113a0ea582a05e35266734501e8adf3663ec77c735e2
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:618799e1f69323eeabfbf249c6a3726278d81a61303b16a367ed9c62713b56fe
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a38c76c016b6229224b093f8ae2a436c21ac3401e920cd32051ddf289735c8f1
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4604a4b5237b87986eb44e035d79c1465c0958193ad1bb8451bd8a32011c9813
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ebccf7f0f93621164f759f50d59e77da154fa73578a89447dcd40a6ec3b195
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:080e787c96fa8b09f9b8bcf88f51a3766bad6b6691637c9fc0b084cb355db333
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
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": 0.23622047244094488,
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,
@@ -60,6 +60,21 @@
60
  "eval_samples_per_second": 149.172,
61
  "eval_steps_per_second": 74.586,
62
  "step": 120
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 40,
@@ -79,7 +94,7 @@
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 95179014144.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.31496062992125984,
5
  "eval_steps": 40,
6
+ "global_step": 160,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 149.172,
61
  "eval_steps_per_second": 74.586,
62
  "step": 120
63
+ },
64
+ {
65
+ "epoch": 0.31496062992125984,
66
+ "grad_norm": 0.008034692145884037,
67
+ "learning_rate": 5.000000000000003e-06,
68
+ "loss": 11.9303,
69
+ "step": 160
70
+ },
71
+ {
72
+ "epoch": 0.31496062992125984,
73
+ "eval_loss": 11.930480003356934,
74
+ "eval_runtime": 5.7325,
75
+ "eval_samples_per_second": 149.325,
76
+ "eval_steps_per_second": 74.662,
77
+ "step": 160
78
  }
79
  ],
80
  "logging_steps": 40,
 
94
  "attributes": {}
95
  }
96
  },
97
+ "total_flos": 125900980224.0,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null