Hugging Face's logo

AlexiaJM
/
zephyr-7b-dpo-full-repnew

Text Generation
Transformers
TensorBoard
Safetensors
mistral
alignment-handbook
Generated from Trainer
trl
dpo
conversational
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
AlexiaJM commited on
Commit
e8ddc6a
•
1 Parent(s): 06e112d

Model save

Browse files
Files changed (8) hide show
  1. README.md +2 -2
  2. all_results.json +7 -7
  3. eval_results.json +3 -3
  4. runs/Feb22_16-18-37_cn-g029.server.mila.quebec/events.out.tfevents.1708636793.cn-g029.server.mila.quebec.2844469.0 +3 -0
  5. runs/Feb22_16-18-37_cn-g029.server.mila.quebec/events.out.tfevents.1708639698.cn-g029.server.mila.quebec.2844469.1 +3 -0
  6. train_results.json +4 -4
  7. trainer_state.json +4 -4
  8. training_args.bin +1 -1
README.md CHANGED
@@ -64,8 +64,8 @@ The following hyperparameters were used during training:
64
  |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
65
  | 0.5666 | 0.21 | 100 | -1.6453 | -1.5540 | -378.9401 | -411.0335 | 0.5780 | 0.7282 | -0.9484 | 0.5442 | -1.4926 |
66
  | 0.5107 | 0.42 | 200 | -0.1291 | 0.3999 | -386.8341 | -445.9254 | 0.5233 | 0.7480 | -1.0273 | 0.8142 | -1.8415 |
67
- | 0.5036 | 0.63 | 300 | 0.5109 | -1.0310 | -1.8791 | 0.7599 | 0.8481 | -449.6839 | -387.1995 | 0.7446 | -0.0425 |
68
- | 0.485 | 0.84 | 400 | 0.5047 | -1.1308 | -2.0694 | 0.7639 | 0.9387 | -468.7184 | -397.1799 | 0.9022 | 0.0635 |
69
 
70
 
71
  ### Framework versions
 
64
  |:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
65
  | 0.5666 | 0.21 | 100 | -1.6453 | -1.5540 | -378.9401 | -411.0335 | 0.5780 | 0.7282 | -0.9484 | 0.5442 | -1.4926 |
66
  | 0.5107 | 0.42 | 200 | -0.1291 | 0.3999 | -386.8341 | -445.9254 | 0.5233 | 0.7480 | -1.0273 | 0.8142 | -1.8415 |
67
+ | 0.5036 | 0.63 | 300 | -0.0425 | 0.7446 | -387.1995 | -449.6839 | 0.5109 | 0.7599 | -1.0310 | 0.8481 | -1.8791 |
68
+ | 0.485 | 0.84 | 400 | 0.0635 | 0.9022 | -397.1799 | -468.7184 | 0.5047 | 0.7639 | -1.1308 | 0.9387 | -2.0694 |
69
 
70
 
71
  ### Framework versions
all_results.json CHANGED
@@ -9,13 +9,13 @@
9
  "eval_rewards/chosen": -1.1057459115982056,
10
  "eval_rewards/margins": 0.9401550889015198,
11
  "eval_rewards/rejected": -2.04590106010437,
12
- "eval_runtime": 208.7421,
13
  "eval_samples": 2000,
14
- "eval_samples_per_second": 9.581,
15
- "eval_steps_per_second": 0.302,
16
- "train_loss": 0.2921084338014231,
17
- "train_runtime": 10286.7931,
18
  "train_samples": 61135,
19
- "train_samples_per_second": 5.943,
20
- "train_steps_per_second": 0.046
21
  }
 
9
  "eval_rewards/chosen": -1.1057459115982056,
10
  "eval_rewards/margins": 0.9401550889015198,
11
  "eval_rewards/rejected": -2.04590106010437,
12
+ "eval_runtime": 207.7886,
13
  "eval_samples": 2000,
14
+ "eval_samples_per_second": 9.625,
15
+ "eval_steps_per_second": 0.303,
16
+ "train_loss": 0.08043583084202413,
17
+ "train_runtime": 2697.0957,
18
  "train_samples": 61135,
19
+ "train_samples_per_second": 22.667,
20
+ "train_steps_per_second": 0.177
21
  }
eval_results.json CHANGED
@@ -9,8 +9,8 @@
9
  "eval_rewards/chosen": -1.1057459115982056,
10
  "eval_rewards/margins": 0.9401550889015198,
11
  "eval_rewards/rejected": -2.04590106010437,
12
- "eval_runtime": 208.7421,
13
  "eval_samples": 2000,
14
- "eval_samples_per_second": 9.581,
15
- "eval_steps_per_second": 0.302
16
  }
 
9
  "eval_rewards/chosen": -1.1057459115982056,
10
  "eval_rewards/margins": 0.9401550889015198,
11
  "eval_rewards/rejected": -2.04590106010437,
12
+ "eval_runtime": 207.7886,
13
  "eval_samples": 2000,
14
+ "eval_samples_per_second": 9.625,
15
+ "eval_steps_per_second": 0.303
16
  }
runs/Feb22_16-18-37_cn-g029.server.mila.quebec/events.out.tfevents.1708636793.cn-g029.server.mila.quebec.2844469.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0d61e540ca6ac95e2922448e9ba4259b1f1c163dc2c948eada0491b75ac1cd1
3
+ size 9463
runs/Feb22_16-18-37_cn-g029.server.mila.quebec/events.out.tfevents.1708639698.cn-g029.server.mila.quebec.2844469.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b0e05dac2b4618153922604b90ff8e79765cfa5c38573e9b0cd9e0fb68e531c
3
+ size 828
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
- "train_loss": 0.2921084338014231,
4
- "train_runtime": 10286.7931,
5
  "train_samples": 61135,
6
- "train_samples_per_second": 5.943,
7
- "train_steps_per_second": 0.046
8
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "train_loss": 0.08043583084202413,
4
+ "train_runtime": 2697.0957,
5
  "train_samples": 61135,
6
+ "train_samples_per_second": 22.667,
7
+ "train_steps_per_second": 0.177
8
  }
trainer_state.json CHANGED
@@ -748,10 +748,10 @@
748
  "epoch": 1.0,
749
  "step": 477,
750
  "total_flos": 0.0,
751
- "train_loss": 0.2921084338014231,
752
- "train_runtime": 10286.7931,
753
- "train_samples_per_second": 5.943,
754
- "train_steps_per_second": 0.046
755
  }
756
  ],
757
  "logging_steps": 10,
 
748
  "epoch": 1.0,
749
  "step": 477,
750
  "total_flos": 0.0,
751
+ "train_loss": 0.08043583084202413,
752
+ "train_runtime": 2697.0957,
753
+ "train_samples_per_second": 22.667,
754
+ "train_steps_per_second": 0.177
755
  }
756
  ],
757
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69a789519b0b0d251c1235be8592d4f9fa808bc80130d806801cc3e06d793a33
3
  size 6072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec71fa8f0c6a223ade55eb038408c955538877668aaefaf5bbd56372333a2e7
3
  size 6072