vwxyzjn commited on
Commit
04b6346
1 Parent(s): 3004cad

End of training

Browse files
README.md CHANGED
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
19
 
20
  This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
- - Loss: 0.6636
23
- - Accuracy: 0.7
24
 
25
  ## Model description
26
 
@@ -40,11 +40,11 @@ More information needed
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 3e-06
43
- - train_batch_size: 2
44
- - eval_batch_size: 2
45
  - seed: 42
46
  - gradient_accumulation_steps: 32
47
- - total_train_batch_size: 64
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - num_epochs: 1.0
@@ -53,12 +53,12 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|
56
- | 0.582 | 0.9945 | 84 | 0.6636 | 0.7 |
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.40.1
62
- - Pytorch 2.2.0+cu121
63
- - Datasets 2.19.0
64
  - Tokenizers 0.19.1
 
19
 
20
  This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on an unknown dataset.
21
  It achieves the following results on the evaluation set:
22
+ - Loss: 0.6757
23
+ - Accuracy: 0.5840
24
 
25
  ## Model description
26
 
 
40
 
41
  The following hyperparameters were used during training:
42
  - learning_rate: 3e-06
43
+ - train_batch_size: 1
44
+ - eval_batch_size: 1
45
  - seed: 42
46
  - gradient_accumulation_steps: 32
47
+ - total_train_batch_size: 32
48
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
49
  - lr_scheduler_type: linear
50
  - num_epochs: 1.0
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Accuracy |
55
  |:-------------:|:------:|:----:|:---------------:|:--------:|
56
+ | 0.6608 | 0.6410 | 100 | 0.6802 | 0.5656 |
57
 
58
 
59
  ### Framework versions
60
 
61
  - Transformers 4.40.1
62
+ - Pytorch 2.2.1+cu121
63
+ - Datasets 2.18.0
64
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a22bdd494728efc51057cf301afebf2b706cef7fe824699e473bf783cd71086f
3
  size 494777904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9129b6c3d88669bd490c3bf72dc6e4a64f282d9b52672e2e81ca4518a04e9f4e
3
  size 494777904
runs/Jun20_17-42-56_ip-26-0-161-178/events.out.tfevents.1718905394.ip-26-0-161-178.1632827.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de3faf40b725bc9231de8e48161748b9eab0b67ed44edca7db03e0cc9853a317
3
+ size 47541
runs/Jun20_18-01-42_ip-26-0-161-178/events.out.tfevents.1718906510.ip-26-0-161-178.1637208.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7049d131125239f43709cba254cbc68f1495f73459d362b95e5b3a4bde4ece77
3
+ size 5951
runs/Jun20_18-02-26_ip-26-0-161-178/events.out.tfevents.1718906551.ip-26-0-161-178.1638380.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a1e577611eceda40c2b62c4bd778342b2b33305ac268ef963078e48225be116
3
+ size 5951
runs/Jun20_18-03-36_ip-26-0-161-178/events.out.tfevents.1718906620.ip-26-0-161-178.1639641.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13023009a9c6f11df5e94b542bfc6fc35dda0b6cb0f777b8ba813396c2ea7b1a
3
+ size 5951
runs/Jun20_18-04-22_ip-26-0-161-178/events.out.tfevents.1718906667.ip-26-0-161-178.1640700.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9519ad55f8e3365630e88b3f4758c8821e3d350e7dd26b1acd6f81c11dfa9b01
3
+ size 8655
runs/Jun20_18-08-27_ip-26-0-161-178/events.out.tfevents.1718906912.ip-26-0-161-178.1642587.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330a08ee06f2710a48014951461d30e68fa1c814c8b0f458a9f16f66580c0666
3
+ size 5951
runs/Jun20_18-09-40_ip-26-0-161-178/events.out.tfevents.1718906985.ip-26-0-161-178.1644192.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1d347beaa57eb65770238191a155339073e53cc7c2ad63fb576194b7ab19abe
3
+ size 5951
runs/Jun20_18-10-52_ip-26-0-161-178/events.out.tfevents.1718907057.ip-26-0-161-178.1645288.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c0f06e742c19ed0ead3056f87aee5ec773b786a235a8799dcaeb1d235365ad5
3
+ size 7303
runs/Jun20_18-39-19_ip-26-0-161-178/events.out.tfevents.1718908781.ip-26-0-161-178.1656246.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53d30c3732fc5b8dc0e937f151baeb70d549cd1b79bf4bce886b27997806ad24
3
+ size 21347
runs/Jun20_18-43-53_ip-26-0-161-178/events.out.tfevents.1718909037.ip-26-0-161-178.1659807.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0f6585931612e7ca617b0fb7eb3409b0977e9d865f99c6176df619397e4b9f7
3
+ size 37997
runs/Jun20_18-43-53_ip-26-0-161-178/events.out.tfevents.1718909328.ip-26-0-161-178.1659807.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f0a4c87e34c3d86d4d11193d24ff30fe14ecdc5585180b4dadf4e783e679a40
3
+ size 411
tokenizer_config.json CHANGED
@@ -213,7 +213,7 @@
213
  }
214
  },
215
  "bos_token": "<|endoftext|>",
216
- "chat_template": "{% for message in messages %}{{' ' + message['content']}}{% endfor %}{{ eos_token }}",
217
  "clean_up_tokenization_spaces": true,
218
  "eos_token": "<|endoftext|>",
219
  "model_max_length": 1000000000000000019884624838656,
 
213
  }
214
  },
215
  "bos_token": "<|endoftext|>",
216
+ "chat_template": "{% for message in messages %}{{' ' if not loop.first else ''}}{{message['content']}}{% endfor %}{{eos_token}}",
217
  "clean_up_tokenization_spaces": true,
218
  "eos_token": "<|endoftext|>",
219
  "model_max_length": 1000000000000000019884624838656,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1dd12ccfa859bc7c89c28add183777d0f8b96286b40e504c49e6b54d6b9dbb0a
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:547507e758c8dacf821780596b08c9306babae7e0e98f6ce41439d2bdc3a9414
3
  size 4984