Hugging Face's logo

gavrilstep
/
85aa9e5d-cbb6-4fe6-9e71-d69f333295b0

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files
xet
 Community
gavrilstep commited on
Commit
e094218
·
verified ·
1 Parent(s): 4b062d3

Training in progress, step 21, 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 +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507ffae19608e05d267d8fc7426f662c43799c93b0d70a96acd68b1ce8c6914e
3
  size 2269195160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67ac56cd9db30a61599826af0ab3bd4c7044ff66011a6282be997288c0695f8
3
  size 2269195160
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76cd945f1ecedbe508e5d2e0a7e736275edf9bf451a1a75b71369a5ca9e1ef20
3
  size 335922386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c30b65cb429d0d59fe29d101b8a0e6b476017d442b9edf62edaa27553a7fc16f
3
  size 335922386
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b787a89658b42bf16ddbbd6bd90065cd8d3499be1970e968875c6e35532ecab
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7bb161926d3ea8b8ad8b5d8af1ee3fd436d358e0f6304d9f88656b94d5968bb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:017f7d123df6134e490bc0a4b797f60b72418d2b0df64facc9dfb4c2e38ddeb5
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": 0.975609756097561,
5
  "eval_steps": 5,
6
- "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -89,6 +89,13 @@
89
  "eval_samples_per_second": 4.791,
90
  "eval_steps_per_second": 2.662,
91
  "step": 20
 
 
 
 
 
 
 
92
  }
93
  ],
94
  "logging_steps": 3,
@@ -103,12 +110,12 @@
103
  "should_evaluate": false,
104
  "should_log": false,
105
  "should_save": true,
106
- "should_training_stop": false
107
  },
108
  "attributes": {}
109
  }
110
  },
111
- "total_flos": 7418876862136320.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.024390243902439,
5
  "eval_steps": 5,
6
+ "global_step": 21,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
89
  "eval_samples_per_second": 4.791,
90
  "eval_steps_per_second": 2.662,
91
  "step": 20
92
+ },
93
+ {
94
+ "epoch": 1.024390243902439,
95
+ "grad_norm": 1.889438509941101,
96
+ "learning_rate": 0.0,
97
+ "loss": 1.3178,
98
+ "step": 21
99
  }
100
  ],
101
  "logging_steps": 3,
 
110
  "should_evaluate": false,
111
  "should_log": false,
112
  "should_save": true,
113
+ "should_training_stop": true
114
  },
115
  "attributes": {}
116
  }
117
  },
118
+ "total_flos": 7789820705243136.0,
119
  "train_batch_size": 2,
120
  "trial_name": null,
121
  "trial_params": null