Hugging Face's logo

chauhoang
/
3c77d416-4727-4166-82e3-fc3d49d5eaa1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
0964d89
·
verified ·
1 Parent(s): c3901be

Training in progress, step 39, 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 +25 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93397146fd762b20c90d7da44cee13a083d754ec07c00547511a28aa2e472e29
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6afe5ae0b6f719ddfe821729d50b5767ada2380e9d4e9fa7eb28f3a70081b94d
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61e947e92603e5b224bb97201b04f8d717aaf40724f54a70b0ad4ebc32237d65
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2e16fd4d732d30c4912e6f673ac4bab44e55c001a8d0ffcf986bc8037656181
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6f9f48a237397d5cfdeb9df77d920aa4f1ec6cf9e776435f83348bc85efdef4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f9b9752f49f9f52e6605be303590b8adaa339e8456ccb350b68c2878cbc286
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.009026994184532592,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.3223,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1291749490163712.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01354049127679889,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.3223,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.01041576252061453,
72
+ "grad_norm": 0.5429520606994629,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.328,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.01041576252061453,
79
+ "eval_loss": 1.1442904472351074,
80
+ "eval_runtime": 41.5056,
81
+ "eval_samples_per_second": 29.225,
82
+ "eval_steps_per_second": 14.625,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.012151722940716952,
87
+ "grad_norm": 0.6467339396476746,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.1885,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1931229435789312.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null