Hugging Face's logo

tuantmdev
/
6860d41c-54b0-429a-b48d-4e896b5c9961

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
acdb7db
·
verified ·
1 Parent(s): 4969ed4

Training in progress, step 350, 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 +19 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e11e6d209148544acb18b4a8bd842d9dbb98a810f6a020d89f9359c42762dfc8
3
  size 2436967616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7486d601c6a18aacfdfeed2bd2b54565c661839b313247cd4bc7278b0704927
3
  size 2436967616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0c41836182a36eb57cfd91220c427d52ed1f15bf75b93a6a6c632269855d6ab
3
  size 170920532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c9d50313bdd1f25ae62148e0793e8d6b47ca8137ec2284a8926c1c89d09a7f
3
  size 170920532
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bda7dfaa785e89c1c3fd04d94117e45d1a8fef595eb33b17fe54e47fafcad92a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33eb612e08d19c1cbd851b37d45e5358a268bbf325344a2480d41bdd2efcb680
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef9686b06e8feaa36ed10d72ecd8afef7e62f88744e516a900f077a3e6a083d3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.5710722208023071,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-300",
4
- "epoch": 0.018497109826589597,
5
  "eval_steps": 50,
6
- "global_step": 300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -112,6 +112,21 @@
112
  "eval_samples_per_second": 13.118,
113
  "eval_steps_per_second": 6.559,
114
  "step": 300
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
115
  }
116
  ],
117
  "logging_steps": 40,
@@ -126,7 +141,7 @@
126
  "early_stopping_threshold": 0.0
127
  },
128
  "attributes": {
129
- "early_stopping_patience_counter": 0
130
  }
131
  },
132
  "TrainerControl": {
@@ -140,7 +155,7 @@
140
  "attributes": {}
141
  }
142
  },
143
- "total_flos": 1.2295191400965734e+17,
144
  "train_batch_size": 2,
145
  "trial_name": null,
146
  "trial_params": null
 
1
  {
2
  "best_metric": 1.5710722208023071,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-300",
4
+ "epoch": 0.02157996146435453,
5
  "eval_steps": 50,
6
+ "global_step": 350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
112
  "eval_samples_per_second": 13.118,
113
  "eval_steps_per_second": 6.559,
114
  "step": 300
115
+ },
116
+ {
117
+ "epoch": 0.01973025048169557,
118
+ "grad_norm": 0.7950920462608337,
119
+ "learning_rate": 1.4644660940672627e-05,
120
+ "loss": 1.606,
121
+ "step": 320
122
+ },
123
+ {
124
+ "epoch": 0.02157996146435453,
125
+ "eval_loss": 1.5714285373687744,
126
+ "eval_runtime": 1042.0279,
127
+ "eval_samples_per_second": 13.107,
128
+ "eval_steps_per_second": 6.554,
129
+ "step": 350
130
  }
131
  ],
132
  "logging_steps": 40,
 
141
  "early_stopping_threshold": 0.0
142
  },
143
  "attributes": {
144
+ "early_stopping_patience_counter": 1
145
  }
146
  },
147
  "TrainerControl": {
 
155
  "attributes": {}
156
  }
157
  },
158
+ "total_flos": 1.4318745844658995e+17,
159
  "train_batch_size": 2,
160
  "trial_name": null,
161
  "trial_params": null