Hugging Face's logo

cwaud
/
fcb794f8-87e5-450a-803b-1de44a075f71

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
cwaud commited on
Commit
7b81330
·
verified ·
1 Parent(s): 56c5997

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 sha256:8a6dd8d351729d3be059c189d5fedc716a173386468da6a4ca738dd8a04d5840
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9e0b2f0ccb7bedbf1423554ea4daf321bec00553f16c8e8c52d86531abfa5ac
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:181689150539e93aa3989452dd95d8d4d8eb8f433b317d8310a365d87b3275c3
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c53956421fddbaf93c55e4a2eb1d51b18db6a9b07127a396b631db74d4d917
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:b36ec73cd9827ba8c91a0ea58ebc4faca053e31799036ef42ba948ded2c240c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb9d08c0b334d9c658abb3d40df84aecfe981b90b2b6b261a2674c7046e68562
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": 0.029556650246305417,
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": 4.308,
74
  "eval_steps_per_second": 2.154,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2219477097775104.0,
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": 0.04433497536945813,
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": 4.308,
74
  "eval_steps_per_second": 2.154,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.034482758620689655,
79
+ "grad_norm": 33.94437789916992,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.6181,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.03940886699507389,
86
+ "grad_norm": 37.8486442565918,
87
+ "learning_rate": 0.00016,
88
+ "loss": 5.4599,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.04433497536945813,
93
+ "grad_norm": 33.13700485229492,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.997,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.04433497536945813,
100
+ "eval_loss": 2.348573684692383,
101
+ "eval_runtime": 19.9544,
102
+ "eval_samples_per_second": 4.31,
103
+ "eval_steps_per_second": 2.155,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3329215646662656.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null