Hugging Face's logo

mamung
/
29b84e13-2f1c-406f-9e7e-fd35b6e5ff49

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
mamung commited on
Commit
7d55efb
·
verified ·
1 Parent(s): 18e996a

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 sha256:6ced54c5cf5a769f0a915e42b0b0af11d2b042c020ba4b09790c2db88d14acc4
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5f14e62202baca2158365e624a3c2d601cb64395726a7e5216231aee1c44a0f
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0436dfba133e66b15d94ee68740359a7646eb0d0801a4b92f4233801f5077182
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f85eb80651f83b6f992b8781133e612eeefb184e648aa43720ea337be35f70
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8780d7db06ab4ab1a3d9fe0bbb5d24157ffc53e0a958625307e31b1c79f0a6c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a3ea2b103f5b4e7eb9a3a54d0002e4ea0da0ac169ade0960b1834e914e4713
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": 0.00036038741647270814,
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": 11.673,
74
  "eval_steps_per_second": 5.837,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 779046231736320.0,
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": 0.0005405811247090622,
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": 11.673,
74
  "eval_steps_per_second": 5.837,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0004204519858848262,
79
+ "grad_norm": 0.18312940001487732,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.8521,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00048051655529694423,
86
+ "grad_norm": 0.19604727625846863,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.7933,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0005405811247090622,
93
+ "grad_norm": 0.1954066902399063,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.7782,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0005405811247090622,
100
+ "eval_loss": 1.6387897729873657,
101
+ "eval_runtime": 600.7873,
102
+ "eval_samples_per_second": 11.67,
103
+ "eval_steps_per_second": 5.836,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1168569347604480.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null