Hugging Face's logo

fenguhao
/
zephyr-7b-sft-qlora

Transformers
TensorBoard
Safetensors
Generated from Trainer
trl
sft
Model card Files Metrics Community
fenguhao commited on
Commit
0df140d
·
verified ·
1 Parent(s): 1de912e

Model save

Browse files
Files changed (6) hide show
  1. adapter_config.json +4 -4
  2. all_results.json +4 -4
  3. runs/Nov28_06-32-21_RLHF000/events.out.tfevents.1732775550.RLHF000.96163.0 +3 -0
  4. train_results.json +4 -4
  5. trainer_state.json +4 -12
  6. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "q_proj",
24
- "o_proj",
25
  "gate_proj",
26
  "k_proj",
27
- "down_proj",
28
  "up_proj",
29
- "v_proj"
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "v_proj",
 
24
  "gate_proj",
25
  "k_proj",
 
26
  "up_proj",
27
+ "o_proj",
28
+ "q_proj",
29
+ "down_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 5.19321114598441e+16,
4
- "train_loss": 0.29640919991901943,
5
- "train_runtime": 283.2891,
6
  "train_samples": 9000,
7
- "train_samples_per_second": 1.966,
8
- "train_steps_per_second": 0.124
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 5.19321114598441e+16,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.0101,
6
  "train_samples": 9000,
7
+ "train_samples_per_second": 54933.863,
8
+ "train_steps_per_second": 3451.859
9
  }
runs/Nov28_06-32-21_RLHF000/events.out.tfevents.1732775550.RLHF000.96163.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f439e3132d286dc02122dd87645020e0d87963d802f2476664d634e71bc87e0
3
+ size 7260
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 5.19321114598441e+16,
4
- "train_loss": 0.29640919991901943,
5
- "train_runtime": 283.2891,
6
  "train_samples": 9000,
7
- "train_samples_per_second": 1.966,
8
- "train_steps_per_second": 0.124
9
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 5.19321114598441e+16,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 0.0101,
6
  "train_samples": 9000,
7
+ "train_samples_per_second": 54933.863,
8
+ "train_steps_per_second": 3451.859
9
  }
trainer_state.json CHANGED
@@ -64,22 +64,14 @@
64
  "loss": 0.1105,
65
  "step": 35
66
  },
67
- {
68
- "epoch": 1.0,
69
- "eval_loss": 0.11027031391859055,
70
- "eval_runtime": 9.0841,
71
- "eval_samples_per_second": 6.715,
72
- "eval_steps_per_second": 0.44,
73
- "step": 35
74
- },
75
  {
76
  "epoch": 1.0,
77
  "step": 35,
78
  "total_flos": 5.19321114598441e+16,
79
- "train_loss": 0.29640919991901943,
80
- "train_runtime": 283.2891,
81
- "train_samples_per_second": 1.966,
82
- "train_steps_per_second": 0.124
83
  }
84
  ],
85
  "logging_steps": 5,
 
64
  "loss": 0.1105,
65
  "step": 35
66
  },
 
 
 
 
 
 
 
 
67
  {
68
  "epoch": 1.0,
69
  "step": 35,
70
  "total_flos": 5.19321114598441e+16,
71
+ "train_loss": 0.0,
72
+ "train_runtime": 0.0101,
73
+ "train_samples_per_second": 54933.863,
74
+ "train_steps_per_second": 3451.859
75
  }
76
  ],
77
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f15a816755935c765d06466ad254b6b1fc53c7fad1a2d6152c2acfb2e238d7a
3
  size 6328
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b5a4eaa042445efe6b2a06ce6686184fbd6b4858ba94e63f557be79d5dde1e
3
  size 6328