Hugging Face's logo

quannh197
/
5dd5a0fb-0035-4ea8-8e65-beaf15e840a6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
quannh197 commited on
Commit
932ef91
·
verified ·
1 Parent(s): 9f48323

Training in progress, step 9, 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:a74d4e7323475e0f7d7b0ab44b5efda9803e02f5db6d821bed7cda338d51d324
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e433df6a607d12af7010901b064ee80022db71b2ed232727a4a1787c714b7a74
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d5664b716305caa59f85e320aef88cf71a03def911e33380d95a11318e0abf4
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f298be8c1a9eecf00bb44eb0b27dbddb2a83969d784c4c7c20a2c1c56ab37d5c
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6bf19e75a59ee8c6a96e9c63d30b78c698cbfef05ceb7eb28dd7602d0b1a826
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea4a6c63434c27a483922b729f3295cf32c5e237d07366009f63d639620f157
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.005488223187742968,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 32.337,
74
  "eval_steps_per_second": 16.204,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109757876240384.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.008232334781614453,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 32.337,
74
  "eval_steps_per_second": 16.204,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006402927052366796,
79
+ "grad_norm": 1.59661066532135,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.8453,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.007317630916990624,
86
+ "grad_norm": 1.6485153436660767,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.6767,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.008232334781614453,
93
+ "grad_norm": 1.4121031761169434,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.5341,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.008232334781614453,
100
+ "eval_loss": 1.4102096557617188,
101
+ "eval_runtime": 14.2189,
102
+ "eval_samples_per_second": 32.422,
103
+ "eval_steps_per_second": 16.246,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664636814360576.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null