Hugging Face's logo

Kaspar
/
gpt-finetuned-newspapers-hmd

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
Kaspar commited on
Commit
7ae226d
•
1 Parent(s): f7c807b

Training in progress, step 500, checkpoint

Browse files
Files changed (10) hide show
  1. last-checkpoint/config.json +1 -1
  2. last-checkpoint/generation_config.json +1 -1
  3. last-checkpoint/model.safetensors +1 -1
  4. last-checkpoint/optimizer.pt +1 -1
  5. last-checkpoint/rng_state.pth +1 -1
  6. last-checkpoint/scheduler.pt +1 -1
  7. last-checkpoint/tokenizer.json +0 -0
  8. last-checkpoint/tokenizer_config.json +1 -1
  9. last-checkpoint/trainer_state.json +5 -5
  10. last-checkpoint/training_args.bin +1 -1
last-checkpoint/config.json CHANGED
@@ -33,7 +33,7 @@
33
  }
34
  },
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.44.2",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
 
33
  }
34
  },
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.45.1",
37
  "use_cache": true,
38
  "vocab_size": 50257
39
  }
last-checkpoint/generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.44.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.45.1"
6
  }
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:667bd867027c05d4d7a383ca3cbe77566f0c87e0df9f990aa2c6c361c8e48103
3
  size 497774208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b94725bfe1566204e151e7f0a68c6d8f245e564efd51c476821b0e42ee6aa397
3
  size 497774208
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a8be1024915d9580d9be98c81eda66e51670b80f40a6c63430fac51ad14d2f5
3
  size 995642298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d58a2d63fddfe8d8ac69da051cc41641ffbc97c9c0c4ede54cc429e48b9db0a
3
  size 995642298
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7783ce2b510ebff845afe5faa16d30b45d77fba542f3b0068e3d921d737af067
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3006c2e62f2fbd7c9faf809b9b2f9bdfb8379c432374b893703883a883751cd7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a628550ca4465bdd919b150d3c25a5f39f8c2d8ec727e285ab3a8278b2af9fa2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f2c546c6ee20d93648539b1268fb91629fbdbed1298c7ecff35599c084d635f
3
  size 1064
last-checkpoint/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json CHANGED
@@ -19,7 +19,7 @@
19
  }
20
  },
21
  "bos_token": "<|endoftext|>",
22
- "clean_up_tokenization_spaces": true,
23
  "eos_token": "<|endoftext|>",
24
  "model_max_length": 1024,
25
  "pad_token": "[PAD]",
 
19
  }
20
  },
21
  "bos_token": "<|endoftext|>",
22
+ "clean_up_tokenization_spaces": false,
23
  "eos_token": "<|endoftext|>",
24
  "model_max_length": 1024,
25
  "pad_token": "[PAD]",
last-checkpoint/trainer_state.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.46513023646621054,
5
  "eval_steps": 500,
6
- "global_step": 15500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [],
11
- "logging_steps": 33323,
12
- "max_steps": 99972,
13
  "num_input_tokens_seen": 0,
14
  "num_train_epochs": 3,
15
  "save_steps": 500,
@@ -25,7 +25,7 @@
25
  "attributes": {}
26
  }
27
  },
28
- "total_flos": 3.2400211968e+16,
29
  "train_batch_size": 32,
30
  "trial_name": null,
31
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.029865010154103453,
5
  "eval_steps": 500,
6
+ "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [],
11
+ "logging_steps": 16741,
12
+ "max_steps": 50226,
13
  "num_input_tokens_seen": 0,
14
  "num_train_epochs": 3,
15
  "save_steps": 500,
 
25
  "attributes": {}
26
  }
27
  },
28
+ "total_flos": 1045168128000000.0,
29
  "train_batch_size": 32,
30
  "trial_name": null,
31
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:588ed685f39e84528f61e069ba254fd7cef9c5061f838bf59aba9ee692ef1d72
3
  size 5240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c823122689f046e65538558e9b41096b25fc0852caa1598fec53aa2a8a9e23c8
3
  size 5240