Hugging Face's logo

tuanna08go
/
d03b1aa7-3120-4eb3-9690-a45cc19e5306

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
388287c
·
verified ·
1 Parent(s): c58244c

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 sha256:5d30a51b79f45ed2228946b823303ec720b0124b08c27806aadbb6594e172634
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba5aeda3197e956325b6cc5bff56dab286ee79f78a116fb173a92b920084caa0
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43f44f2cead9013a850a430851247facf1bb0c533d278e6b69596faa54aaf000
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51dd603cef886cf9776c032079f5dc15019c6af7422cf2684f8f76d741e966e3
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b5c24709107a16c4a366ef695fabf1bcf47b8db012ccbceb7d99c5d75c4b350
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65941554dfccfdcf0ed28341039200adb2012eef3c09ec7b1fbc4a815a622955
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": 0.0703336339044184,
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": 3.9661,
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": 6966870401875968.0,
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": 0.09017132551848513,
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": 3.9661,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.0721370604147881,
94
+ "grad_norm": 5.879969120025635,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 3.7932,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.0721370604147881,
101
+ "eval_loss": 0.959617555141449,
102
+ "eval_runtime": 15.7241,
103
+ "eval_samples_per_second": 14.882,
104
+ "eval_steps_per_second": 7.441,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0811541929666366,
109
+ "grad_norm": 6.4072957038879395,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 3.7872,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.09017132551848513,
116
+ "grad_norm": 6.380867958068848,
117
+ "learning_rate": 0.0,
118
+ "loss": 3.6417,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.09017132551848513,
123
+ "eval_loss": 0.9541131258010864,
124
+ "eval_runtime": 15.5353,
125
+ "eval_samples_per_second": 15.062,
126
+ "eval_steps_per_second": 7.531,
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": 8894809381011456.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null