Hugging Face's logo

CharlesLi
/
OpenELM-1_1B-DPO-full-max-14-reward

Text Generation
Transformers
TensorBoard
Safetensors
openelm
trl
dpo
alignment-handbook
Generated from Trainer
conversational
custom_code
Model card Files Metrics Community
CharlesLi commited on
Commit
f021d10
•
1 Parent(s): b33a043

Model save

Browse files
Files changed (10) hide show
  1. README.md +38 -38
  2. all_results.json +4 -4
  3. config.json +2 -2
  4. generation_config.json +1 -1
  5. model.safetensors +1 -1
  6. runs/Oct05_14-26-22_xe8545-a100-15/events.out.tfevents.1728132296.xe8545-a100-15.1049253.0 +3 -0
  7. tokenizer.json +0 -0
  8. train_results.json +4 -4
  9. trainer_state.json +0 -0
  10. training_args.bin +2 -2
README.md CHANGED
@@ -16,13 +16,13 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model was trained from scratch on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.2507
20
- - Rewards/chosen: -4.0938
21
- - Rewards/rejected: -4.5
22
- - Rewards/accuracies: 0.4961
23
- - Rewards/margins: 0.4277
24
- - Logps/rejected: -740.0
25
- - Logps/chosen: -728.0
26
  - Logits/rejected: -16.125
27
  - Logits/chosen: -16.375
28
 
@@ -61,39 +61,39 @@ The following hyperparameters were used during training:
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
63
  |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
64
- | 0.0575 | 0.1047 | 100 | 0.6934 | -1.2422 | -1.5469 | 0.5840 | 0.3027 | -444.0 | -442.0 | -9.75 | -10.0 |
65
- | 0.0427 | 0.2094 | 200 | 0.7579 | -1.125 | -1.2812 | 0.5039 | 0.1602 | -418.0 | -430.0 | -14.8125 | -15.0 |
66
- | 0.0532 | 0.3141 | 300 | 1.6151 | -6.3125 | -6.875 | 0.4844 | 0.5820 | -976.0 | -948.0 | -13.75 | -13.9375 |
67
- | 0.0436 | 0.4188 | 400 | 0.8565 | -1.5625 | -1.6719 | 0.4785 | 0.1069 | -456.0 | -474.0 | -15.5 | -15.5625 |
68
- | 0.0331 | 0.5236 | 500 | 0.9544 | -2.875 | -3.125 | 0.4863 | 0.2539 | -600.0 | -608.0 | -10.9375 | -11.4375 |
69
- | 0.043 | 0.6283 | 600 | 0.9331 | -2.7812 | -2.9219 | 0.4551 | 0.1396 | -580.0 | -596.0 | -16.625 | -16.75 |
70
- | 0.037 | 0.7330 | 700 | 0.8353 | -2.9062 | -3.0781 | 0.5156 | 0.1777 | -596.0 | -608.0 | -12.6875 | -13.0625 |
71
- | 0.0295 | 0.8377 | 800 | 0.9349 | -2.8438 | -3.0156 | 0.4863 | 0.1611 | -588.0 | -604.0 | -18.25 | -18.375 |
72
- | 0.0344 | 0.9424 | 900 | 0.9633 | -3.2188 | -3.3281 | 0.4824 | 0.1157 | -624.0 | -640.0 | -14.8125 | -15.25 |
73
- | 0.0067 | 1.0471 | 1000 | 1.0684 | -3.3438 | -3.6719 | 0.4863 | 0.3281 | -656.0 | -652.0 | -17.5 | -17.75 |
74
- | 0.0165 | 1.1518 | 1100 | 1.1375 | -3.8906 | -4.3125 | 0.4727 | 0.4082 | -720.0 | -708.0 | -15.9375 | -16.375 |
75
- | 0.0019 | 1.2565 | 1200 | 0.9505 | -2.875 | -3.0625 | 0.4902 | 0.1973 | -596.0 | -604.0 | -17.25 | -17.25 |
76
- | 0.0016 | 1.3613 | 1300 | 1.0801 | -3.6562 | -4.0 | 0.4824 | 0.3457 | -688.0 | -684.0 | -13.125 | -13.625 |
77
- | 0.0015 | 1.4660 | 1400 | 1.0415 | -3.4375 | -3.7969 | 0.5020 | 0.3633 | -668.0 | -660.0 | -14.375 | -14.75 |
78
- | 0.0037 | 1.5707 | 1500 | 1.0121 | -3.1406 | -3.4375 | 0.5 | 0.2930 | -632.0 | -632.0 | -14.0 | -14.375 |
79
- | 0.0025 | 1.6754 | 1600 | 1.1921 | -3.8125 | -4.2188 | 0.4902 | 0.3984 | -708.0 | -700.0 | -15.125 | -15.4375 |
80
- | 0.0029 | 1.7801 | 1700 | 1.4103 | -4.9375 | -5.4375 | 0.4902 | 0.5078 | -832.0 | -812.0 | -12.8125 | -13.1875 |
81
- | 0.0009 | 1.8848 | 1800 | 1.1241 | -3.7344 | -4.0 | 0.4766 | 0.2852 | -688.0 | -692.0 | -15.6875 | -15.875 |
82
- | 0.0052 | 1.9895 | 1900 | 1.1658 | -3.6406 | -3.9062 | 0.4688 | 0.2676 | -680.0 | -684.0 | -16.25 | -16.375 |
83
- | 0.0003 | 2.0942 | 2000 | 1.1422 | -3.7188 | -4.0312 | 0.4785 | 0.3105 | -692.0 | -692.0 | -16.5 | -16.625 |
84
- | 0.0008 | 2.1990 | 2100 | 1.2501 | -4.0938 | -4.5 | 0.4863 | 0.4043 | -736.0 | -728.0 | -16.125 | -16.375 |
85
- | 0.0002 | 2.3037 | 2200 | 1.2498 | -4.0625 | -4.4688 | 0.4902 | 0.4180 | -736.0 | -724.0 | -16.25 | -16.375 |
86
- | 0.0004 | 2.4084 | 2300 | 1.2577 | -4.0938 | -4.5312 | 0.4941 | 0.4258 | -740.0 | -728.0 | -16.25 | -16.375 |
87
- | 0.0002 | 2.5131 | 2400 | 1.2621 | -4.125 | -4.5625 | 0.4941 | 0.4355 | -744.0 | -732.0 | -16.0 | -16.25 |
88
- | 0.0001 | 2.6178 | 2500 | 1.2696 | -4.1562 | -4.5938 | 0.4961 | 0.4453 | -748.0 | -736.0 | -15.9375 | -16.125 |
89
- | 0.0073 | 2.7225 | 2600 | 1.2632 | -4.125 | -4.5625 | 0.5020 | 0.4375 | -744.0 | -732.0 | -16.125 | -16.375 |
90
- | 0.0002 | 2.8272 | 2700 | 1.2520 | -4.0938 | -4.5 | 0.4922 | 0.4258 | -740.0 | -728.0 | -16.125 | -16.375 |
91
- | 0.0002 | 2.9319 | 2800 | 1.2507 | -4.0938 | -4.5 | 0.4961 | 0.4277 | -740.0 | -728.0 | -16.125 | -16.375 |
92
 
93
 
94
  ### Framework versions
95
 
96
- - Transformers 4.44.2
97
  - Pytorch 2.3.0
98
- - Datasets 3.0.0
99
- - Tokenizers 0.19.1
 
16
 
17
  This model was trained from scratch on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 1.1391
20
+ - Rewards/chosen: -3.7969
21
+ - Rewards/rejected: -4.2188
22
+ - Rewards/accuracies: 0.5
23
+ - Rewards/margins: 0.4238
24
+ - Logps/rejected: -712.0
25
+ - Logps/chosen: -696.0
26
  - Logits/rejected: -16.125
27
  - Logits/chosen: -16.375
28
 
 
61
 
62
  | Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
63
  |:-------------:|:------:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
64
+ | 0.0531 | 0.1047 | 100 | 0.7024 | -1.0781 | -1.4297 | 0.5801 | 0.3477 | -432.0 | -426.0 | -9.6875 | -9.9375 |
65
+ | 0.0523 | 0.2094 | 200 | 0.7657 | -1.1016 | -1.3125 | 0.5195 | 0.2061 | -420.0 | -428.0 | -13.9375 | -14.3125 |
66
+ | 0.0716 | 0.3141 | 300 | 1.2495 | -2.9844 | -3.5156 | 0.5137 | 0.5391 | -640.0 | -616.0 | -13.5 | -13.9375 |
67
+ | 0.0472 | 0.4188 | 400 | 0.8801 | -1.7344 | -1.9688 | 0.4961 | 0.2393 | -486.0 | -492.0 | -11.9375 | -12.3125 |
68
+ | 0.0394 | 0.5236 | 500 | 0.9541 | -2.7812 | -2.9688 | 0.4922 | 0.1904 | -584.0 | -596.0 | -16.125 | -16.25 |
69
+ | 0.0707 | 0.6283 | 600 | 0.8604 | -2.25 | -2.4375 | 0.4922 | 0.1934 | -532.0 | -544.0 | -14.9375 | -15.125 |
70
+ | 0.045 | 0.7330 | 700 | 0.9378 | -3.0312 | -3.25 | 0.4863 | 0.2168 | -612.0 | -620.0 | -15.25 | -15.5 |
71
+ | 0.0278 | 0.8377 | 800 | 0.9400 | -2.5156 | -2.6719 | 0.4863 | 0.1641 | -556.0 | -568.0 | -18.0 | -17.75 |
72
+ | 0.018 | 0.9424 | 900 | 1.1675 | -3.8438 | -4.125 | 0.4902 | 0.2969 | -704.0 | -704.0 | -15.625 | -15.625 |
73
+ | 0.0043 | 1.0471 | 1000 | 1.0828 | -3.5156 | -3.9531 | 0.4844 | 0.4336 | -684.0 | -672.0 | -14.25 | -14.4375 |
74
+ | 0.0034 | 1.1518 | 1100 | 1.2924 | -4.9062 | -5.375 | 0.5020 | 0.4629 | -828.0 | -808.0 | -14.8125 | -14.9375 |
75
+ | 0.0056 | 1.2565 | 1200 | 1.0445 | -3.6562 | -3.9062 | 0.4941 | 0.2412 | -680.0 | -684.0 | -17.25 | -17.125 |
76
+ | 0.0049 | 1.3613 | 1300 | 1.0296 | -3.4062 | -3.6562 | 0.4883 | 0.2461 | -656.0 | -660.0 | -16.875 | -16.75 |
77
+ | 0.0009 | 1.4660 | 1400 | 1.0903 | -3.8125 | -4.1875 | 0.4902 | 0.3828 | -708.0 | -700.0 | -16.625 | -16.625 |
78
+ | 0.0026 | 1.5707 | 1500 | 0.9407 | -3.0781 | -3.3594 | 0.4980 | 0.2910 | -624.0 | -624.0 | -16.75 | -16.75 |
79
+ | 0.0009 | 1.6754 | 1600 | 0.9907 | -3.3438 | -3.6719 | 0.4980 | 0.3418 | -656.0 | -652.0 | -16.75 | -17.0 |
80
+ | 0.0078 | 1.7801 | 1700 | 0.9547 | -3.3281 | -3.625 | 0.4941 | 0.2910 | -652.0 | -652.0 | -12.5 | -12.75 |
81
+ | 0.0022 | 1.8848 | 1800 | 0.9916 | -3.0 | -3.3281 | 0.4922 | 0.3281 | -620.0 | -616.0 | -15.5625 | -15.875 |
82
+ | 0.0041 | 1.9895 | 1900 | 0.9828 | -2.8594 | -3.1562 | 0.5059 | 0.2969 | -604.0 | -604.0 | -16.125 | -16.25 |
83
+ | 0.0002 | 2.0942 | 2000 | 1.0311 | -3.1562 | -3.4688 | 0.4961 | 0.3184 | -636.0 | -636.0 | -16.0 | -16.25 |
84
+ | 0.0004 | 2.1990 | 2100 | 1.0823 | -3.4688 | -3.8438 | 0.5 | 0.3691 | -672.0 | -664.0 | -16.125 | -16.375 |
85
+ | 0.0003 | 2.3037 | 2200 | 1.1156 | -3.625 | -4.0312 | 0.4941 | 0.4004 | -692.0 | -680.0 | -16.25 | -16.375 |
86
+ | 0.0003 | 2.4084 | 2300 | 1.1278 | -3.7031 | -4.125 | 0.4980 | 0.4141 | -700.0 | -688.0 | -16.25 | -16.375 |
87
+ | 0.0001 | 2.5131 | 2400 | 1.1339 | -3.7344 | -4.1562 | 0.5020 | 0.4180 | -704.0 | -692.0 | -16.25 | -16.5 |
88
+ | 0.0001 | 2.6178 | 2500 | 1.1372 | -3.7656 | -4.1875 | 0.5020 | 0.4219 | -708.0 | -696.0 | -16.125 | -16.375 |
89
+ | 0.0017 | 2.7225 | 2600 | 1.1389 | -3.7812 | -4.2188 | 0.5020 | 0.4219 | -708.0 | -696.0 | -16.125 | -16.375 |
90
+ | 0.0002 | 2.8272 | 2700 | 1.1391 | -3.7812 | -4.2188 | 0.5059 | 0.4238 | -712.0 | -696.0 | -16.125 | -16.375 |
91
+ | 0.0005 | 2.9319 | 2800 | 1.1391 | -3.7969 | -4.2188 | 0.5 | 0.4238 | -712.0 | -696.0 | -16.125 | -16.375 |
92
 
93
 
94
  ### Framework versions
95
 
96
+ - Transformers 4.45.1
97
  - Pytorch 2.3.0
98
+ - Datasets 3.0.1
99
+ - Tokenizers 0.20.0
all_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.02219091602174458,
5
- "train_runtime": 12517.1932,
6
  "train_samples": 61119,
7
- "train_samples_per_second": 14.648,
8
- "train_steps_per_second": 0.229
9
  }
 
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.022635619988056292,
5
+ "train_runtime": 12425.7414,
6
  "train_samples": 61119,
7
+ "train_samples_per_second": 14.756,
8
+ "train_steps_per_second": 0.231
9
  }
config.json CHANGED
@@ -6,7 +6,7 @@
6
  ],
7
  "auto_map": {
8
  "AutoConfig": "configuration_openelm.OpenELMConfig",
9
- "AutoModelForCausalLM": "modeling_openelm.OpenELMForCausalLM"
10
  },
11
  "bos_token_id": 1,
12
  "eos_token_id": 2,
@@ -119,7 +119,7 @@
119
  "rope_max_length": 4096,
120
  "share_input_output_layers": true,
121
  "torch_dtype": "bfloat16",
122
- "transformers_version": "4.44.2",
123
  "use_cache": false,
124
  "vocab_size": 32000
125
  }
 
6
  ],
7
  "auto_map": {
8
  "AutoConfig": "configuration_openelm.OpenELMConfig",
9
+ "AutoModelForCausalLM": "apple/OpenELM-1_1B--modeling_openelm.OpenELMForCausalLM"
10
  },
11
  "bos_token_id": 1,
12
  "eos_token_id": 2,
 
119
  "rope_max_length": 4096,
120
  "share_input_output_layers": true,
121
  "torch_dtype": "bfloat16",
122
+ "transformers_version": "4.45.1",
123
  "use_cache": false,
124
  "vocab_size": 32000
125
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.44.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.45.1"
6
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fad92ac9eb0b4415cc9666d11ad9fc5438a967550d047e33e2932e0d0ae91de
3
  size 2159808696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5754786595921cf1141f812a1a7c971cd25a9336649fbbbef1a3d49f88c4ce8
3
  size 2159808696
runs/Oct05_14-26-22_xe8545-a100-15/events.out.tfevents.1728132296.xe8545-a100-15.1049253.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:285f295a3d71996c14baae3ae8c63fcb2c0e6b8e421af6b77f87f51ab2d6d111
3
+ size 225711
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
train_results.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 0.0,
4
- "train_loss": 0.02219091602174458,
5
- "train_runtime": 12517.1932,
6
  "train_samples": 61119,
7
- "train_samples_per_second": 14.648,
8
- "train_steps_per_second": 0.229
9
  }
 
1
  {
2
  "epoch": 3.0,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.022635619988056292,
5
+ "train_runtime": 12425.7414,
6
  "train_samples": 61119,
7
+ "train_samples_per_second": 14.756,
8
+ "train_steps_per_second": 0.231
9
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c42c8d9c2aa038bb3810004d7a14035e51fe1dbf460f7a7fc498854ffdbaf1c
3
- size 7544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07e4d96ca6b830df4676f6214a3b4e222535d6d35da37130cdb19b17bd990b62
3
+ size 7672