rusheeliyer commited on
Commit
7cae52c
1 Parent(s): 344b354

Initial Commit

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "configs/sled_mt5_config.json",
3
+ "architectures": [
4
+ "SledForConditionalGeneration"
5
+ ],
6
+ "context_size": 256,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 768,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.1,
13
+ "encode_prefix": true,
14
+ "eos_token_id": 1,
15
+ "feed_forward_proj": "gated-gelu",
16
+ "initializer_factor": 1.0,
17
+ "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "max_target_length": 2048,
21
+ "model_type": "tau/sled",
22
+ "num_decoder_layers": 12,
23
+ "num_heads": 12,
24
+ "num_layers": 12,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "prepend_prefix": true,
28
+ "relative_attention_max_distance": 128,
29
+ "relative_attention_num_buckets": 32,
30
+ "sliding_method": "dynamic",
31
+ "tie_word_embeddings": false,
32
+ "tokenizer_class": "T5Tokenizer",
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.28.1",
35
+ "underlying_config": "google/mt5-base",
36
+ "use_cache": false,
37
+ "vocab_size": 250100,
38
+ "window_fraction": 0.5
39
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.28.1",
7
+ "use_cache": false
8
+ }
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbe76e9511b2cb41ba8e536699ff9fa250d4362abc3014900366a25bb493acd0
3
+ size 4659230729
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fbfb6fd4002dc8ce3f2290d34c248f6526dd018048b7b790146b48931583346
3
+ size 2329719897
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e27e0cfaef18cd1501c0ba1d057c3ae19af3842b9a27cd45f1cce4d19e0359
3
+ size 2329636441
pytorch_model.bin.index.json ADDED
The diff for this file is too large to render. See raw diff
 
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:510693a49229ca40bd940d3f84fa8c089339f9d7ae109aeca2a4b32cf7df2885
3
+ size 14575
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6c005afc655ce7691df546cf22ee6ed1ec1eb107a0fde4825e9140cfe2c083b
3
+ size 627
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "eos_token": "</s>",
3
+ "pad_token": "<pad>",
4
+ "unk_token": "<unk>"
5
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
3
+ size 16330369
tokenizer_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": null,
3
+ "clean_up_tokenization_spaces": true,
4
+ "eos_token": "</s>",
5
+ "extra_ids": 0,
6
+ "model_max_length": 1000000000000000019884624838656,
7
+ "pad_token": "<pad>",
8
+ "sp_model_kwargs": {},
9
+ "tokenizer_class": "T5Tokenizer",
10
+ "unk_token": "<unk>"
11
+ }
trainer_state.json ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 14.0723,
3
+ "best_model_checkpoint": "models/sled/output_sled_mt5_base2/checkpoint-2397",
4
+ "epoch": 1.0,
5
+ "global_step": 2397,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.21,
12
+ "learning_rate": 1.3904338153503894e-05,
13
+ "loss": 18.6448,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.42,
18
+ "learning_rate": 2.7808676307007788e-05,
19
+ "loss": 3.8147,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.63,
24
+ "learning_rate": 4.171301446051168e-05,
25
+ "loss": 2.6096,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.83,
30
+ "learning_rate": 5.5617352614015575e-05,
31
+ "loss": 2.3758,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "eval_mean_prediction_length_characters": 7800.0,
37
+ "eval_mean_prediction_length_tokens": 2047.0,
38
+ "eval_num_predicted": 1,
39
+ "eval_rouge/geometric_mean": 14.0723,
40
+ "eval_rouge/rouge1": 24.3546,
41
+ "eval_rouge/rouge2": 7.1185,
42
+ "eval_rouge/rougeL": 16.074,
43
+ "eval_rouge/rougeLsum": 21.4321,
44
+ "eval_runtime": 358.1416,
45
+ "eval_samples_per_second": 0.003,
46
+ "eval_steps_per_second": 0.003,
47
+ "step": 2397
48
+ }
49
+ ],
50
+ "max_steps": 35955,
51
+ "num_train_epochs": 15,
52
+ "total_flos": 8.078322612436992e+16,
53
+ "trial_name": null,
54
+ "trial_params": null
55
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d833e225c6c771d368bc0449bf4aea5850f23cb875e9c6eab4cdd87a206e3f4
3
+ size 3899