Hugging Face's logo

duyphu
/
7a756b67-4517-44e5-816c-210c1c002eb7

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
7a5ebb9
·
verified ·
1 Parent(s): 76c55e5

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 sha256:07e2d0e59622e9fd9a8205adcdc84841c386a4ced7761f5779bbbcb246e72dca
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7ddcd389282e0622d2f59e3527288cf3571e475dea2d884a67d795d1ed009f
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6fb815bc85c6508a2100820762f568115f879765d956898272bd93cd4c51c3cd
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0df0954b39bc834ee3c4e8d8f1731f5f4597c6da823eb5674e7ee25a11bcbfd
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c1039e96a4ec12087edaa8ab2d18eba7c359b91687856664d415beaa872acc5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19a5c3c72e60ff810542ede55f7b859d77b4dd5935294cc01a9f9bf4d605e2e8
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": 0.03317031681905167,
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": 11.9303,
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": 4608294912.0,
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": 0.0425260472039124,
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": 11.9303,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.03402083776312992,
94
+ "grad_norm": 0.022298870608210564,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 11.933,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.03402083776312992,
101
+ "eval_loss": 11.931011199951172,
102
+ "eval_runtime": 4.6353,
103
+ "eval_samples_per_second": 106.789,
104
+ "eval_steps_per_second": 53.502,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.03827344248352116,
109
+ "grad_norm": 0.016301140189170837,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 11.9294,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.0425260472039124,
116
+ "grad_norm": 0.020248446613550186,
117
+ "learning_rate": 0.0,
118
+ "loss": 11.9298,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.0425260472039124,
123
+ "eval_loss": 11.931008338928223,
124
+ "eval_runtime": 4.4599,
125
+ "eval_samples_per_second": 110.989,
126
+ "eval_steps_per_second": 55.606,
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": 5908070400.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null