Hugging Face's logo

phungkhaccuong
/
2c364321-bc92-4760-abd4-5dfbb8bc02c8

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
phungkhaccuong commited on
Commit
058795d
·
verified ·
1 Parent(s): dc80e4b

Training in progress, step 50, 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 +41 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af7228f2f7f7c0bd02e410e8792a3a9a248b5c3b30105ff92560843fb0256ac6
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73d733fd92b0a74857e23ebb5e3d55887433356054b7da6fb1ea90aa48a9170a
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37c6fadc733fb68c680e6428db145c1fcbe10677c173fc250bad8daa59298145
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0292a8456d6f7677404cdaee9bac9654b6a6f32ea3e709f2a12c9df757130773
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1542c12b1c38878d0bf713af077c56cb60e0f19147c5c8f6f20fb0942baee8b8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b72cf74d489e5841ae4de8ec493255d408573406e6792be6bc5adc1ae2332f80
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.09955328653477984,
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,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 2.6019,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 3722118294405120.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1276324186343331,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 2.6019,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.1021059349074665,
94
+ "grad_norm": 0.6996490359306335,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 2.7452,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.1021059349074665,
101
+ "eval_loss": 2.7188756465911865,
102
+ "eval_runtime": 9.4298,
103
+ "eval_samples_per_second": 17.498,
104
+ "eval_steps_per_second": 8.802,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.1148691767708998,
109
+ "grad_norm": 0.6797233819961548,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 2.7534,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.1276324186343331,
116
+ "grad_norm": 0.6642326712608337,
117
+ "learning_rate": 0.0,
118
+ "loss": 2.6603,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.1276324186343331,
123
+ "eval_loss": 2.717184543609619,
124
+ "eval_runtime": 9.3197,
125
+ "eval_samples_per_second": 17.704,
126
+ "eval_steps_per_second": 8.906,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 4713523634503680.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null