leonvanbokhorst commited on
Commit
62c3d08
·
verified ·
1 Parent(s): 7e5fc7e

Training in progress, epoch 1

Browse files
adapter_config.json CHANGED
@@ -1,28 +1,28 @@
1
- {
2
- "alpha_pattern": {},
3
- "auto_mapping": null,
4
- "base_model_name_or_path": "gpt2",
5
- "bias": "none",
6
- "fan_in_fan_out": true,
7
- "inference_mode": true,
8
- "init_lora_weights": true,
9
- "layer_replication": null,
10
- "layers_pattern": null,
11
- "layers_to_transform": null,
12
- "loftq_config": {},
13
- "lora_alpha": 32,
14
- "lora_dropout": 0.1,
15
- "megatron_config": null,
16
- "megatron_core": "megatron.core",
17
- "modules_to_save": null,
18
- "peft_type": "LORA",
19
- "r": 8,
20
- "rank_pattern": {},
21
- "revision": null,
22
- "target_modules": [
23
- "c_attn"
24
- ],
25
- "task_type": "SEQ_CLS",
26
- "use_dora": false,
27
- "use_rslora": false
28
  }
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gpt2",
5
+ "bias": "none",
6
+ "fan_in_fan_out": true,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "c_attn"
24
+ ],
25
+ "task_type": "SEQ_CLS",
26
+ "use_dora": false,
27
+ "use_rslora": false
28
  }
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa2e96ba7ed2c150b2edbcc4e113942e97e2803466ff1da67c26e4ed07316e76
3
  size 1201208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8378b21fbea3a8ac128989e2854992d19b8f9dd7758c4f48861c05e74b10139d
3
  size 1201208
tokenizer_config.json CHANGED
@@ -13,12 +13,8 @@
13
  "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
16
- "max_length": 256,
17
  "model_max_length": 1024,
18
  "pad_token": "<|endoftext|>",
19
- "padding": "max_length",
20
- "padding_side": "right",
21
  "tokenizer_class": "GPT2Tokenizer",
22
- "truncation": true,
23
  "unk_token": "<|endoftext|>"
24
  }
 
13
  "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": true,
15
  "eos_token": "<|endoftext|>",
 
16
  "model_max_length": 1024,
17
  "pad_token": "<|endoftext|>",
 
 
18
  "tokenizer_class": "GPT2Tokenizer",
 
19
  "unk_token": "<|endoftext|>"
20
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2b7cbf9dca007c8c5eed3e6c1fee7a601b327656f08ca8f1a916d3618f087fed
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a464a4e3dbc37828b35fb310fb74b793307394a5d7798a75fc6a4dfe39da3c80
3
  size 4984