theojolliffe commited on
Commit
600ff91
1 Parent(s): fa57116

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,19 +1,19 @@
1
  {
2
- "_name_or_path": "theojolliffe/T5-model-1-feedback-1109",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 3072,
7
  "d_kv": 64,
8
  "d_model": 768,
9
  "decoder_start_token_id": 0,
10
- "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
12
  "eos_token_id": 1,
13
- "feed_forward_proj": "relu",
14
  "initializer_factor": 1.0,
15
  "is_encoder_decoder": true,
16
- "is_gated_act": false,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
@@ -53,8 +53,9 @@
53
  "prefix": "translate English to Romanian: "
54
  }
55
  },
 
56
  "torch_dtype": "float32",
57
- "transformers_version": "4.24.0",
58
  "use_cache": true,
59
  "vocab_size": 32128
60
  }
 
1
  {
2
+ "_name_or_path": "google/flan-t5-base",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 2048,
7
  "d_kv": 64,
8
  "d_model": 768,
9
  "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
  "dropout_rate": 0.1,
12
  "eos_token_id": 1,
13
+ "feed_forward_proj": "gated-gelu",
14
  "initializer_factor": 1.0,
15
  "is_encoder_decoder": true,
16
+ "is_gated_act": true,
17
  "layer_norm_epsilon": 1e-06,
18
  "model_type": "t5",
19
  "n_positions": 512,
 
53
  "prefix": "translate English to Romanian: "
54
  }
55
  },
56
+ "tie_word_embeddings": false,
57
  "torch_dtype": "float32",
58
+ "transformers_version": "4.26.1",
59
  "use_cache": true,
60
  "vocab_size": 32128
61
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2645ac0cb4cdaacc3ee6cbc5258fea22339ca296b8b8f6d895bbd2bf7b8db200
3
- size 891700799
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c41f877fe0e15973fabd60eebe3564b42af1d4ff106ce50b28fe6c667b6cb6
3
+ size 990408885
runs/Feb28_23-14-29_5d14e5e5ecd4/1677626320.1970775/events.out.tfevents.1677626320.5d14e5e5ecd4.1155.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b0f99a134a3d6d94d2be52b7b1f8493e6fc80630919f2255ddce69b8db5a34
3
+ size 5933
runs/Feb28_23-14-29_5d14e5e5ecd4/events.out.tfevents.1677626320.5d14e5e5ecd4.1155.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76d290485ae87db696c1a0cd280885b1b42834f25662c789827c59ab6760b80c
3
+ size 5505
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -104,11 +104,10 @@
104
  "eos_token": "</s>",
105
  "extra_ids": 100,
106
  "model_max_length": 512,
107
- "name_or_path": "theojolliffe/T5-model-1-feedback-1109",
108
  "pad_token": "<pad>",
109
  "sp_model_kwargs": {},
110
- "special_tokens_map_file": null,
111
  "tokenizer_class": "T5Tokenizer",
112
- "tokenizer_file": null,
113
  "unk_token": "<unk>"
114
  }
 
104
  "eos_token": "</s>",
105
  "extra_ids": 100,
106
  "model_max_length": 512,
107
+ "name_or_path": "google/flan-t5-base",
108
  "pad_token": "<pad>",
109
  "sp_model_kwargs": {},
110
+ "special_tokens_map_file": "/home/younes_huggingface_co/.cache/huggingface/hub/models--google--t5-v1_1-base/snapshots/650d7745bf1e502d6949b22cc19155cd656d3d4e/special_tokens_map.json",
111
  "tokenizer_class": "T5Tokenizer",
 
112
  "unk_token": "<unk>"
113
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da20caf121ffcdb7830c09ebc1252503fcf682bbe39fb501404f77e6db654352
3
- size 3503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cbb44cbbba7056ee120e6ef4ee00e1a6988eb8d5b0fe49ae87c448277eca53
3
+ size 3643