Hugging Face's logo

VERSIL91
/
b821e296-afdc-4570-bf34-01917a945fd2

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
b482a2b
·
verified ·
1 Parent(s): fc2fc08

Training in progress, step 10, 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 +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c0461a9617d9f9dd277ef637f7fb067a4e4ab45293d071942bcd84da9c1c0e6
3
  size 228140600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb60e94ca7dd7e2db4671ad6e44c3d1c09ad724157dcbae30e331d36a4a520c3
3
  size 228140600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc2ecdc163215d8d22ff0d3dfa949bc3648659239933c57e85f69e44d114a943
3
  size 116472340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b0f9d438477373c26551c6c45f695198021b39f1af011b0d02bc3f6c06dc33
3
  size 116472340
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03ad0c4652463f1096182a18d963eb133233e4b3378834bfb14790c18a607c56
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff7a7bf575bf735c43664a9f3e7d6224b8e0f70881552070db80cfa952aae28
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
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": 0.03903496882624018,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 4.739,
103
  "eval_steps_per_second": 2.375,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 8.234209697071104e+16,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04337218758471131,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 4.739,
103
  "eval_steps_per_second": 2.375,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.04337218758471131,
108
+ "grad_norm": 192.78652954101562,
109
+ "learning_rate": 0.0001,
110
+ "loss": 53.0197,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 9.14912188563456e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null