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
8ca073d
·
verified ·
1 Parent(s): e42cd89

Training in progress, step 200, 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 +19 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d3bbaaad92c2bab08d3113a0ea582a05e35266734501e8adf3663ec77c735e2
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84f61bbb41c146be284d361f8b0e7a2730394542d723a0dde4288d04e20fa082
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a38c76c016b6229224b093f8ae2a436c21ac3401e920cd32051ddf289735c8f1
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa32b5d8ae18b2bdd58ea2392c575cfe2b62522d9149b62ca765cd3724b2652
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50ebccf7f0f93621164f759f50d59e77da154fa73578a89447dcd40a6ec3b195
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b72bfe0071fe658596730395196fb52cda2ae9dc7b226a1cb240af98895ddc1c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb148ad6cd6502048dc3eee274a6708e5b4f6b72c0d56ebc272935446c220acd
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": 0.31496062992125984,
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,
@@ -75,6 +75,21 @@
75
  "eval_samples_per_second": 149.325,
76
  "eval_steps_per_second": 74.662,
77
  "step": 160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  }
79
  ],
80
  "logging_steps": 40,
@@ -89,12 +104,12 @@
89
  "should_evaluate": false,
90
  "should_log": false,
91
  "should_save": true,
92
- "should_training_stop": false
93
  },
94
  "attributes": {}
95
  }
96
  },
97
- "total_flos": 125900980224.0,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3937007874015748,
5
  "eval_steps": 40,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
75
  "eval_samples_per_second": 149.325,
76
  "eval_steps_per_second": 74.662,
77
  "step": 160
78
+ },
79
+ {
80
+ "epoch": 0.3937007874015748,
81
+ "grad_norm": 0.015014749951660633,
82
+ "learning_rate": 0.0,
83
+ "loss": 11.9303,
84
+ "step": 200
85
+ },
86
+ {
87
+ "epoch": 0.3937007874015748,
88
+ "eval_loss": 11.930471420288086,
89
+ "eval_runtime": 5.7288,
90
+ "eval_samples_per_second": 149.42,
91
+ "eval_steps_per_second": 74.71,
92
+ "step": 200
93
  }
94
  ],
95
  "logging_steps": 40,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 156977430528.0,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null