Hugging Face's logo

KaixuanJi
/
zephyr-7b-dpo-lora

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
Jerry Ji commited on
Commit
f74cf6b
·
1 Parent(s): 8f9976c

Training in progress, epoch 1

Browse files
Files changed (9) hide show
  1. adapter_config.json +3 -3
  2. adapter_model.safetensors +1 -1
  3. all_results.json +3 -3
  4. runs/Dec10_15-50-15_uclaml03.cs.ucla.edu/events.out.tfevents.1702252380.uclaml03.cs.ucla.edu.2934315.2 +3 -0
  5. runs/Dec10_15-54-10_uclaml03.cs.ucla.edu/events.out.tfevents.1702252518.uclaml03.cs.ucla.edu.2935560.0 +3 -0
  6. runs/Dec10_16-11-47_uclaml03.cs.ucla.edu/events.out.tfevents.1702253573.uclaml03.cs.ucla.edu.2936686.0 +3 -0
  7. train_results.json +3 -3
  8. trainer_state.json +6 -6
  9. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -16,10 +16,10 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "k_proj",
20
- "v_proj",
21
  "o_proj",
22
- "q_proj"
 
 
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "o_proj",
20
+ "v_proj",
21
+ "q_proj",
22
+ "k_proj"
23
  ],
24
  "task_type": "CAUSAL_LM"
25
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9dcafb75e33763bcbb1dcac4844987b4bc4804afc8cd5a98e4c454d0a897ab4
3
  size 218138576
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4851d0fda021876b9eb5ecbd6ec0d108d643bb4b81a517a68af72134d8b407
3
  size 218138576
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.3465735912322998,
4
- "train_runtime": 29.428,
5
  "train_samples": 61966,
6
- "train_samples_per_second": 0.34,
7
- "train_steps_per_second": 0.034
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.3465735912322998,
4
+ "train_runtime": 27.423,
5
  "train_samples": 61966,
6
+ "train_samples_per_second": 0.365,
7
+ "train_steps_per_second": 0.036
8
  }
runs/Dec10_15-50-15_uclaml03.cs.ucla.edu/events.out.tfevents.1702252380.uclaml03.cs.ucla.edu.2934315.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eeaf65bedb948a73e5464787e75332cda5530611077497d8767ab3d5c68efe5
3
+ size 5014
runs/Dec10_15-54-10_uclaml03.cs.ucla.edu/events.out.tfevents.1702252518.uclaml03.cs.ucla.edu.2935560.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0a6e888bc54bfc56eeb3dd34be3ab5662c5a420ebb755f05ae4af5f286726c1
3
+ size 5014
runs/Dec10_16-11-47_uclaml03.cs.ucla.edu/events.out.tfevents.1702253573.uclaml03.cs.ucla.edu.2936686.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:344e5a977fb32afd76982187f1a68b0b695352951a919b4c6907a71d77d4150a
3
+ size 6089
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.3465735912322998,
4
- "train_runtime": 29.428,
5
  "train_samples": 61966,
6
- "train_samples_per_second": 0.34,
7
- "train_steps_per_second": 0.034
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.3465735912322998,
4
+ "train_runtime": 27.423,
5
  "train_samples": 61966,
6
+ "train_samples_per_second": 0.365,
7
+ "train_steps_per_second": 0.036
8
  }
trainer_state.json CHANGED
@@ -33,9 +33,9 @@
33
  "eval_rewards/chosen": 0.0,
34
  "eval_rewards/margins": 0.0,
35
  "eval_rewards/rejected": 0.0,
36
- "eval_runtime": 4.8717,
37
- "eval_samples_per_second": 2.053,
38
- "eval_steps_per_second": 0.205,
39
  "step": 1
40
  },
41
  {
@@ -43,9 +43,9 @@
43
  "step": 1,
44
  "total_flos": 0.0,
45
  "train_loss": 0.3465735912322998,
46
- "train_runtime": 29.428,
47
- "train_samples_per_second": 0.34,
48
- "train_steps_per_second": 0.034
49
  }
50
  ],
51
  "logging_steps": 10,
 
33
  "eval_rewards/chosen": 0.0,
34
  "eval_rewards/margins": 0.0,
35
  "eval_rewards/rejected": 0.0,
36
+ "eval_runtime": 4.843,
37
+ "eval_samples_per_second": 2.065,
38
+ "eval_steps_per_second": 0.206,
39
  "step": 1
40
  },
41
  {
 
43
  "step": 1,
44
  "total_flos": 0.0,
45
  "train_loss": 0.3465735912322998,
46
+ "train_runtime": 27.423,
47
+ "train_samples_per_second": 0.365,
48
+ "train_steps_per_second": 0.036
49
  }
50
  ],
51
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec4905268afde7298ef64cdb697a8ff0826e47c1f6ef513acb72701fae23abfc
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af127de1e15272d9776374c2dc0c0af574e44154cdffec6a8945b02c4c43facb
3
  size 4728