Hugging Face's logo

lewtun
/
zephyr-7b-sft-qlora

PEFT
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
sft
4-bit precision
bitsandbytes
Model card Files Metrics Community
lewtun HF staff commited on
Commit
dcf4103
•
1 Parent(s): b790b2b

Model save

Browse files
Files changed (8) hide show
  1. adapter_config.json +4 -4
  2. all_results.json +5 -5
  3. eval_results.json +2 -2
  4. runs/Jan04_11-16-18_ip-26-0-165-24/events.out.tfevents.1704367061.ip-26-0-165-24.2274601.0 +3 -0
  5. runs/Jan04_11-16-18_ip-26-0-165-24/events.out.tfevents.1704368210.ip-26-0-165-24.2274601.1 +3 -0
  6. train_results.json +3 -3
  7. trainer_state.json +6 -6
  8. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "k_proj",
23
  "q_proj",
24
  "down_proj",
25
- "o_proj",
26
- "gate_proj",
27
  "v_proj",
28
- "up_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
22
  "q_proj",
23
  "down_proj",
24
+ "k_proj",
25
+ "up_proj",
26
  "v_proj",
27
+ "gate_proj",
28
+ "o_proj"
29
  ],
30
  "task_type": "CAUSAL_LM"
31
  }
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 0.9502018094062805,
4
- "eval_runtime": 365.2439,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 42.248,
7
  "eval_steps_per_second": 0.663,
8
  "train_loss": 0.03432130868306889,
9
- "train_runtime": 783.0861,
10
  "train_samples": 207865,
11
- "train_samples_per_second": 178.047,
12
- "train_steps_per_second": 2.783
13
  }
 
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 0.9502018094062805,
4
+ "eval_runtime": 365.0584,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 42.27,
7
  "eval_steps_per_second": 0.663,
8
  "train_loss": 0.03432130868306889,
9
+ "train_runtime": 783.2781,
10
  "train_samples": 207865,
11
+ "train_samples_per_second": 178.003,
12
+ "train_steps_per_second": 2.782
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 0.9502018094062805,
4
- "eval_runtime": 365.2439,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 42.248,
7
  "eval_steps_per_second": 0.663
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "eval_loss": 0.9502018094062805,
4
+ "eval_runtime": 365.0584,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 42.27,
7
  "eval_steps_per_second": 0.663
8
  }
runs/Jan04_11-16-18_ip-26-0-165-24/events.out.tfevents.1704367061.ip-26-0-165-24.2274601.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6548b8b051262639033d0bac43788b87b661780ca8a893e318b2d77b2a3873d6
3
+ size 7801
runs/Jan04_11-16-18_ip-26-0-165-24/events.out.tfevents.1704368210.ip-26-0-165-24.2274601.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60d066719fd0ac15bd9d35b0d1650f8fe2ad270ee1745aa04f0ec354e3e881a7
3
+ size 359
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.03432130868306889,
4
- "train_runtime": 783.0861,
5
  "train_samples": 207865,
6
- "train_samples_per_second": 178.047,
7
- "train_steps_per_second": 2.783
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "train_loss": 0.03432130868306889,
4
+ "train_runtime": 783.2781,
5
  "train_samples": 207865,
6
+ "train_samples_per_second": 178.003,
7
+ "train_steps_per_second": 2.782
8
  }
trainer_state.json CHANGED
@@ -2627,9 +2627,9 @@
2627
  {
2628
  "epoch": 1.0,
2629
  "eval_loss": 0.9502018094062805,
2630
- "eval_runtime": 365.5893,
2631
- "eval_samples_per_second": 42.209,
2632
- "eval_steps_per_second": 0.662,
2633
  "step": 2179
2634
  },
2635
  {
@@ -2637,9 +2637,9 @@
2637
  "step": 2179,
2638
  "total_flos": 1.225695388701714e+19,
2639
  "train_loss": 0.03432130868306889,
2640
- "train_runtime": 783.0861,
2641
- "train_samples_per_second": 178.047,
2642
- "train_steps_per_second": 2.783
2643
  }
2644
  ],
2645
  "logging_steps": 5,
 
2627
  {
2628
  "epoch": 1.0,
2629
  "eval_loss": 0.9502018094062805,
2630
+ "eval_runtime": 365.9285,
2631
+ "eval_samples_per_second": 42.169,
2632
+ "eval_steps_per_second": 0.661,
2633
  "step": 2179
2634
  },
2635
  {
 
2637
  "step": 2179,
2638
  "total_flos": 1.225695388701714e+19,
2639
  "train_loss": 0.03432130868306889,
2640
+ "train_runtime": 783.2781,
2641
+ "train_samples_per_second": 178.003,
2642
+ "train_steps_per_second": 2.782
2643
  }
2644
  ],
2645
  "logging_steps": 5,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8296efc6b3d38092e1e15f62d34f32c6b6ebdfe40f00e6b26c05539ebef4b8b6
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e4d8f4a9fbb85e52781910d73f1ebd7b696695be6d362a5441200e65205e397
3
  size 4728