Hugging Face's logo

kk-aivio
/
184cd68c-4605-4181-8db3-30a16b52267c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
kk-aivio commited on
Commit
e7bc728
·
verified ·
1 Parent(s): 82fb4db

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 sha256:50342cea90ef0389c787092950c0af4ef2c5005db21d9944a08c5e3a5280a108
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d21655269ae1db642c5a93fd7d83bb67190682610ae780323a8b03c043d682cf
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4452f66b76d56385c9384b80cede09a58bc72262838f815889cd9ad3dab06ef
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:230cb71b6316400f1650f2636005f9004917baed232d51a8bab83cf5920bfdcf
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f89ee07fe03d1a05ba9f35a1ae7e0f887e7de2494b1948e33f324c76bd30d853
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96a5a857ed41b50df491280680008400b63a0cea9bbaf95bf767f775a18248db
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": 0.004559270516717325,
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": 128.341,
74
  "eval_steps_per_second": 64.286,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 770312896512.0,
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": 0.006838905775075988,
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": 128.341,
74
  "eval_steps_per_second": 64.286,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.005319148936170213,
79
+ "grad_norm": 3.2952821254730225,
80
+ "learning_rate": 0.00014,
81
+ "loss": 8.6017,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0060790273556231,
86
+ "grad_norm": 2.317990779876709,
87
+ "learning_rate": 0.00016,
88
+ "loss": 7.7968,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006838905775075988,
93
+ "grad_norm": 2.775648593902588,
94
+ "learning_rate": 0.00018,
95
+ "loss": 8.2047,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006838905775075988,
100
+ "eval_loss": 8.484367370605469,
101
+ "eval_runtime": 4.3445,
102
+ "eval_samples_per_second": 127.748,
103
+ "eval_steps_per_second": 63.989,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1130884890624.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null