Hugging Face's logo

tuantmdev
/
08ad529c-12b5-4748-b0b2-fdd63cf52842

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
a20cf96
·
verified ·
1 Parent(s): baaff78

Training in progress, step 200, 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 +27 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9a9ff5b6a92149c6b4903fb0a4bd134e185c44574bf7827f617c42e3c3d03c8
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2c5c0d015035441f62b2f1b2f504b13db0c2cc6d40462ccfcb1cf7a2f546928
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea14ce63870d043b67ff9bc7a29ca65d5da1e925d9ab0fd7657e48f2b3f2c864
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e369b5b958c0c8c87d301ec2571b16adf83cf1aa890434a47029b8ebcd7bb4
3
  size 170920084
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a98105186cbb82ad207dac0f9621b6c41d109b068ef2e4504fd2f6962f5b002
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365ff522e6a64dc210d2add16db5b2f8bcdf04a8afd80613c56a2d1e8335b11e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.14303329586982727,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.05083022704168079,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,28 @@
60
  "eval_samples_per_second": 11.37,
61
  "eval_steps_per_second": 5.687,
62
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 40,
@@ -74,7 +96,7 @@
74
  "early_stopping_threshold": 0.0
75
  },
76
  "attributes": {
77
- "early_stopping_patience_counter": 2
78
  }
79
  },
80
  "TrainerControl": {
@@ -83,12 +105,12 @@
83
  "should_evaluate": false,
84
  "should_log": false,
85
  "should_save": true,
86
- "should_training_stop": false
87
  },
88
  "attributes": {}
89
  }
90
  },
91
- "total_flos": 7.563191822529331e+16,
92
  "train_batch_size": 2,
93
  "trial_name": null,
94
  "trial_params": null
 
1
  {
2
  "best_metric": 0.14303329586982727,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
+ "epoch": 0.06777363605557438,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 11.37,
61
  "eval_steps_per_second": 5.687,
62
  "step": 150
63
+ },
64
+ {
65
+ "epoch": 0.054218908844459505,
66
+ "grad_norm": 7.59006404876709,
67
+ "learning_rate": 8.535533905932738e-05,
68
+ "loss": 1.2949,
69
+ "step": 160
70
+ },
71
+ {
72
+ "epoch": 0.06777363605557438,
73
+ "grad_norm": 27.78662109375,
74
+ "learning_rate": 6.91341716182545e-05,
75
+ "loss": 1.2253,
76
+ "step": 200
77
+ },
78
+ {
79
+ "epoch": 0.06777363605557438,
80
+ "eval_loss": 0.16803918778896332,
81
+ "eval_runtime": 217.9448,
82
+ "eval_samples_per_second": 11.402,
83
+ "eval_steps_per_second": 5.703,
84
+ "step": 200
85
  }
86
  ],
87
  "logging_steps": 40,
 
96
  "early_stopping_threshold": 0.0
97
  },
98
  "attributes": {
99
+ "early_stopping_patience_counter": 3
100
  }
101
  },
102
  "TrainerControl": {
 
105
  "should_evaluate": false,
106
  "should_log": false,
107
  "should_save": true,
108
+ "should_training_stop": true
109
  },
110
  "attributes": {}
111
  }
112
  },
113
+ "total_flos": 1.0126985660674867e+17,
114
  "train_batch_size": 2,
115
  "trial_name": null,
116
  "trial_params": null