Hugging Face's logo

awsuineg
/
zephyr-7b-dpo-qlora

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
dpo
Inference Endpoints
Model card Files Metrics Community
awsuineg commited on
Commit
ba206a2
·
verified ·
1 Parent(s): e71f6be

Model save

Browse files
Files changed (6) hide show
  1. adapter_config.json +2 -2
  2. all_results.json +4 -4
  3. runs/Nov18_14-09-30_d28f7adca72c/events.out.tfevents.1731939048.d28f7adca72c.1685093.0 +3 -0
  4. train_results.json +4 -4
  5. trainer_state.json +4 -4
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -23,10 +23,10 @@
23
  "gate_proj",
24
  "q_proj",
25
  "o_proj",
 
26
  "v_proj",
27
- "up_proj",
28
  "k_proj",
29
- "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
23
  "gate_proj",
24
  "q_proj",
25
  "o_proj",
26
+ "down_proj",
27
  "v_proj",
 
28
  "k_proj",
29
+ "up_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9994111874386653,
3
  "total_flos": 0.0,
4
- "train_loss": 0.5438023588363335,
5
- "train_runtime": 16632.8648,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 3.675,
8
- "train_steps_per_second": 0.077
9
  }
 
1
  {
2
  "epoch": 0.9994111874386653,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.0132,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 4647380.664,
8
+ "train_steps_per_second": 96772.918
9
  }
runs/Nov18_14-09-30_d28f7adca72c/events.out.tfevents.1731939048.d28f7adca72c.1685093.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da2ba2fa6103e00ce75dcf567de6caa11d752ece668f9287e1961792b1cc515
3
+ size 6799
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 0.9994111874386653,
3
  "total_flos": 0.0,
4
- "train_loss": 0.5438023588363335,
5
- "train_runtime": 16632.8648,
6
  "train_samples": 61134,
7
- "train_samples_per_second": 3.675,
8
- "train_steps_per_second": 0.077
9
  }
 
1
  {
2
  "epoch": 0.9994111874386653,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.0132,
6
  "train_samples": 61134,
7
+ "train_samples_per_second": 4647380.664,
8
+ "train_steps_per_second": 96772.918
9
  }
trainer_state.json CHANGED
@@ -2124,10 +2124,10 @@
2124
  "epoch": 0.9994111874386653,
2125
  "step": 1273,
2126
  "total_flos": 0.0,
2127
- "train_loss": 0.5438023588363335,
2128
- "train_runtime": 16632.8648,
2129
- "train_samples_per_second": 3.675,
2130
- "train_steps_per_second": 0.077
2131
  }
2132
  ],
2133
  "logging_steps": 10,
 
2124
  "epoch": 0.9994111874386653,
2125
  "step": 1273,
2126
  "total_flos": 0.0,
2127
+ "train_loss": 0.0,
2128
+ "train_runtime": 0.0132,
2129
+ "train_samples_per_second": 4647380.664,
2130
+ "train_steps_per_second": 96772.918
2131
  }
2132
  ],
2133
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1e5c711814c8908294b4588d04b7f50c4175fef7498158c02d1600c8482c7a6b
3
  size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150dd618575a824787a08ba24d7b16d0ad6d5e1b42e515d39094de816bb41198
3
  size 6136