Hugging Face's logo

quannh197
/
8e0fd235-c40a-4533-b8a4-14cc3cb82a5b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
quannh197 commited on
Commit
2b92d15
·
verified ·
1 Parent(s): 446a408

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:e9b7b895591026ed7e0a6ed493fbfda2c46adb557fed5979c366f8f669734cea
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abe6a020839451beed3622101094edb31135d079e1b88a749fd3622b70286637
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee28496989d105945f7c6121bf5a20aa7aae99d28fa7fb5573512c7f71c18f12
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2576d6bb187d7d29b2aa1040a9b58938b1ca4f4f397a43ff6505edb20d9870f
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd67821c9edb352a2a7a6b1031c16b950b3518af15c398996c9dc36265dc4d1a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d87e31e70bd00544a171f1f4d95a75e20cac3097ae8bfe86653f57d1d07c450
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": 0.0015091492171288435,
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": 28.639,
74
  "eval_steps_per_second": 14.328,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 834867654819840.0,
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": 0.0022637238256932655,
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": 28.639,
74
  "eval_steps_per_second": 14.328,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0017606740866503176,
79
+ "grad_norm": NaN,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.8465,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0020121989561717917,
86
+ "grad_norm": 0.24796241521835327,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.7513,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0022637238256932655,
93
+ "grad_norm": 0.2246653288602829,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.5931,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0022637238256932655,
100
+ "eval_loss": NaN,
101
+ "eval_runtime": 58.4907,
102
+ "eval_samples_per_second": 28.637,
103
+ "eval_steps_per_second": 14.327,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1252301482229760.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null