Hugging Face's logo

VERSIL91
/
f459d8a1-bdd7-43f5-a793-3bf2efb7e9c4

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
5fdeb95
·
verified ·
1 Parent(s): 9a39cd6

Training in progress, step 8, 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 +26 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b4a366716e92acd954e30ab9d3d60e7dd40c19db5948b1689ba4d803eb6486e
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:591457a7d85945e20c1f6355910df3cd6bbe79e0500209db4be6ed3501be5817
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fd73b7eaac5174145301610a439b30957974cc586fcfb33b5c62902d9149d44
3
  size 6614970
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c69463b10f69c9e900e42e3a8ef6e28cce2663c7e57c0fc1f56d4c6120b45d84
3
  size 6614970
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c30b90cacd6043668a9fceb65b4815e3ca7a9635af8292b75bda3517456e3b3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9647c1d1489472b2eb35ef1640e8fbfd2b703ac05016081caaa618a2891d4551
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
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": 0.8067226890756303,
5
  "eval_steps": 2,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -81,6 +81,28 @@
81
  "eval_samples_per_second": 145.68,
82
  "eval_steps_per_second": 78.443,
83
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
84
  }
85
  ],
86
  "logging_steps": 1,
@@ -95,12 +117,12 @@
95
  "should_evaluate": false,
96
  "should_log": false,
97
  "should_save": true,
98
- "should_training_stop": false
99
  },
100
  "attributes": {}
101
  }
102
  },
103
- "total_flos": 210548557873152.0,
104
  "train_batch_size": 2,
105
  "trial_name": null,
106
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0756302521008403,
5
  "eval_steps": 2,
6
+ "global_step": 8,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
81
  "eval_samples_per_second": 145.68,
82
  "eval_steps_per_second": 78.443,
83
  "step": 6
84
+ },
85
+ {
86
+ "epoch": 0.9411764705882353,
87
+ "grad_norm": 44.79998779296875,
88
+ "learning_rate": 7e-05,
89
+ "loss": 10.6719,
90
+ "step": 7
91
+ },
92
+ {
93
+ "epoch": 1.0756302521008403,
94
+ "grad_norm": 50.22980880737305,
95
+ "learning_rate": 8e-05,
96
+ "loss": 10.1758,
97
+ "step": 8
98
+ },
99
+ {
100
+ "epoch": 1.0756302521008403,
101
+ "eval_loss": 0.6066706776618958,
102
+ "eval_runtime": 0.0922,
103
+ "eval_samples_per_second": 140.947,
104
+ "eval_steps_per_second": 75.894,
105
+ "step": 8
106
  }
107
  ],
108
  "logging_steps": 1,
 
117
  "should_evaluate": false,
118
  "should_log": false,
119
  "should_save": true,
120
+ "should_training_stop": true
121
  },
122
  "attributes": {}
123
  }
124
  },
125
+ "total_flos": 280731410497536.0,
126
  "train_batch_size": 2,
127
  "trial_name": null,
128
  "trial_params": null