xavierbarbier commited on
Commit
1d5ef6f
·
verified ·
1 Parent(s): f3169bf

Training in progress, step 500

Browse files
config.json CHANGED
@@ -1,26 +1,26 @@
1
  {
2
- "_name_or_path": "google/flan-t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
- "d_ff": 1024,
8
  "d_kv": 64,
9
  "d_model": 512,
10
  "decoder_start_token_id": 0,
11
- "dense_act_fn": "gelu_new",
12
  "dropout_rate": 0.1,
13
  "eos_token_id": 1,
14
- "feed_forward_proj": "gated-gelu",
15
  "initializer_factor": 1.0,
16
  "is_encoder_decoder": true,
17
- "is_gated_act": true,
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
- "num_decoder_layers": 8,
22
- "num_heads": 6,
23
- "num_layers": 8,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
@@ -54,7 +54,6 @@
54
  "prefix": "translate English to Romanian: "
55
  }
56
  },
57
- "tie_word_embeddings": false,
58
  "torch_dtype": "float32",
59
  "transformers_version": "4.36.0",
60
  "use_cache": true,
 
1
  {
2
+ "_name_or_path": "google-t5/t5-small",
3
  "architectures": [
4
  "T5ForConditionalGeneration"
5
  ],
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
  "d_kv": 64,
9
  "d_model": 512,
10
  "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
  "dropout_rate": 0.1,
13
  "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
  "initializer_factor": 1.0,
16
  "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
  "layer_norm_epsilon": 1e-06,
19
  "model_type": "t5",
20
  "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
24
  "output_past": true,
25
  "pad_token_id": 0,
26
  "relative_attention_max_distance": 128,
 
54
  "prefix": "translate English to Romanian: "
55
  }
56
  },
 
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.36.0",
59
  "use_cache": true,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:495fa51e204676f1a857a9fc13c4c89f3f5ba9f480b898cebca02add25e6d749
3
- size 307867048
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27335cb5f5796385b952829a9def25fcd745ccf1cceface123f1ee6f94eb50bf
3
+ size 242041896
runs/Jun03_11-20-27_b0cad9bc102b/events.out.tfevents.1717413629.b0cad9bc102b.567.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:294674f051af72c411599d34eb2b37f03585953dac86af531308dbab62169dfe
3
+ size 5361
runs/Jun03_11-20-58_b0cad9bc102b/events.out.tfevents.1717413659.b0cad9bc102b.567.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13dc7a97bd68fe8a8d829f45b3cbe5b703c70943a16ee803abaebe84e80026a0
3
+ size 5518
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -932,7 +932,6 @@
932
  "extra_ids": 100,
933
  "model_max_length": 512,
934
  "pad_token": "<pad>",
935
- "sp_model_kwargs": {},
936
  "tokenizer_class": "T5Tokenizer",
937
  "unk_token": "<unk>"
938
  }
 
932
  "extra_ids": 100,
933
  "model_max_length": 512,
934
  "pad_token": "<pad>",
 
935
  "tokenizer_class": "T5Tokenizer",
936
  "unk_token": "<unk>"
937
  }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11afd9e320362d5802dd7f51216cc0796cc1ab3641c148f40f66c8e920cbbded
3
+ size 4856