Hugging Face's logo

chauhoang
/
db54502c-9bcf-e45b-708b-a7b514a6c592

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
4fffdd5
·
verified ·
1 Parent(s): 8ea8f74

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 sha256:3eb9bc1499013ce2abbd47d34e041b4116b42828dcadd069b2dabdb90db1f258
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b579285f7497c51e41acb20066b48d1f4b5a6ec85ce15427e5930943dcf6b61
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10d1cc2db2ebd368709ccf12bd3587a4d1a79bc30ed1204f03908ac39421ac8d
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8c813a469fa70a7f9fd8a38695ef48f9ac9b8f58d3c0a2689e832519ecf28b0
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
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": 0.41823056300268097,
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": 1.5744,
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": 7213300567769088.0,
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": 0.5361930294906166,
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": 1.5744,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.4289544235924933,
94
+ "grad_norm": 5.524008750915527,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.3467,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.4289544235924933,
101
+ "eval_loss": 1.4648765325546265,
102
+ "eval_runtime": 2.9269,
103
+ "eval_samples_per_second": 13.666,
104
+ "eval_steps_per_second": 6.833,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.48257372654155495,
109
+ "grad_norm": 4.456066608428955,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.5109,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.5361930294906166,
116
+ "grad_norm": 4.297540664672852,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.453,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.5361930294906166,
123
+ "eval_loss": 1.4569414854049683,
124
+ "eval_runtime": 2.8819,
125
+ "eval_samples_per_second": 13.88,
126
+ "eval_steps_per_second": 6.94,
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": 9247821240729600.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null