Hugging Face's logo

chauhoang
/
4ccc321d-991e-4c63-b481-6e243305b407

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
c8c60e8
·
verified ·
1 Parent(s): eedecfb

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:e575516f38afcfc99392c6c96cf43e2da88e10bb6a86086027f603c5704f1fdc
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ebc87bbab8164691873103edd6eb447a0898460c68609d39102c85cc0e36bf6
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a7fafbad1fdf1b94c77a27336dec9584e09f8fa3ef0928eea9ad391535aa022
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca790762270c996bc16d508f4d1e77382bbf74d4a5098056dc243b941962cbe5
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:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdedc6314c9f75a198e58bac1038c3adc8fc2a5f73e82a6a71a371fdac27e199
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": 0.0025356370788160525,
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": 6.5863,
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": 5031618281472.0,
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": 0.0032508167677128877,
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": 6.5863,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.00260065341417031,
94
+ "grad_norm": 2.789621591567993,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 6.3783,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.00260065341417031,
101
+ "eval_loss": 6.456869125366211,
102
+ "eval_runtime": 86.6189,
103
+ "eval_samples_per_second": 74.776,
104
+ "eval_steps_per_second": 37.394,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.002925735090941599,
109
+ "grad_norm": 3.052328109741211,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 6.1808,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.0032508167677128877,
116
+ "grad_norm": 3.4268128871917725,
117
+ "learning_rate": 0.0,
118
+ "loss": 6.6516,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.0032508167677128877,
123
+ "eval_loss": 6.452789783477783,
124
+ "eval_runtime": 86.0149,
125
+ "eval_samples_per_second": 75.301,
126
+ "eval_steps_per_second": 37.656,
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": 6441126985728.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null