vishnun commited on
Commit
15c7e98
1 Parent(s): ae174dc

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "_name_or_path": "patrickvonplaten/t5-tiny-random",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
- "d_ff": 256,
7
- "d_kv": 8,
8
- "d_model": 64,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
@@ -15,12 +15,11 @@
15
  "is_encoder_decoder": true,
16
  "is_gated_act": false,
17
  "layer_norm_epsilon": 1e-06,
18
- "max_length": 10,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 2,
22
- "num_heads": 2,
23
- "num_layers": 2,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
@@ -55,7 +54,7 @@
55
  }
56
  },
57
  "torch_dtype": "float32",
58
- "transformers_version": "4.28.1",
59
  "use_cache": true,
60
  "vocab_size": 32128
61
  }
 
1
  {
2
+ "_name_or_path": "t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
  "decoder_start_token_id": 0,
10
  "dense_act_fn": "relu",
11
  "dropout_rate": 0.1,
 
15
  "is_encoder_decoder": true,
16
  "is_gated_act": false,
17
  "layer_norm_epsilon": 1e-06,
 
18
  "model_type": "t5",
19
  "n_positions": 512,
20
+ "num_decoder_layers": 6,
21
+ "num_heads": 8,
22
+ "num_layers": 6,
23
  "output_past": true,
24
  "pad_token_id": 0,
25
  "relative_attention_max_distance": 128,
 
54
  }
55
  },
56
  "torch_dtype": "float32",
57
+ "transformers_version": "4.30.0",
58
  "use_cache": true,
59
  "vocab_size": 32128
60
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:947556cec23e3bf599d9bf13310da617633e839e6f4e3ee91ba184d0a8792e0c
3
- size 8867006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9f9186fabf54f6c3241c9794d9ae510df27088ee4a4f59a6c8273da17867a3e
3
+ size 242071641
runs/Jun09_08-10-22_b816c7661e3c/events.out.tfevents.1686298326.b816c7661e3c.5867.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6698c11c55f4fd08348e49dcb99e7d977ba1703144f9f364dc94a10de5ce8845
3
+ size 5413
tokenizer.json CHANGED
@@ -2,7 +2,7 @@
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
- "max_length": 32,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
 
2
  "version": "1.0",
3
  "truncation": {
4
  "direction": "Right",
5
+ "max_length": 16,
6
  "strategy": "LongestFirst",
7
  "stride": 0
8
  },
tokenizer_config.json CHANGED
@@ -104,7 +104,6 @@
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
107
- "max_len": 512,
108
  "model_max_length": 512,
109
  "pad_token": "<pad>",
110
  "tokenizer_class": "T5Tokenizer",
 
104
  "clean_up_tokenization_spaces": true,
105
  "eos_token": "</s>",
106
  "extra_ids": 100,
 
107
  "model_max_length": 512,
108
  "pad_token": "<pad>",
109
  "tokenizer_class": "T5Tokenizer",
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02d1c82301248d00ca6c692631313aaf0cd7e769a2b25558b22c6279870f4745
3
- size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1fd57f1483a07452e0dd499a7b043a10dbec428f82aa07fa3395e91b825e17
3
+ size 4091