Davlan commited on
Commit
c0a588b
1 Parent(s): 31b0363

add MT model

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "predict_bleu": 8.4667,
4
+ "predict_gen_len": 57.1002,
5
+ "predict_loss": 2.38679838180542,
6
+ "predict_runtime": 1007.4993,
7
+ "predict_samples": 998,
8
+ "predict_samples_per_second": 0.991,
9
+ "predict_steps_per_second": 0.099,
10
+ "train_loss": 3.811387486049107,
11
+ "train_runtime": 1379.0446,
12
+ "train_samples": 3500,
13
+ "train_samples_per_second": 25.38,
14
+ "train_steps_per_second": 2.538
15
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/mt5-base",
3
+ "architectures": [
4
+ "MT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "mt5",
17
+ "num_decoder_layers": 12,
18
+ "num_heads": 12,
19
+ "num_layers": 12,
20
+ "output_past": true,
21
+ "pad_token_id": 0,
22
+ "relative_attention_num_buckets": 32,
23
+ "tie_word_embeddings": false,
24
+ "tokenizer_class": "T5Tokenizer",
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.12.0",
27
+ "use_cache": true,
28
+ "vocab_size": 250100
29
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_bleu": 7.177,
4
+ "eval_gen_len": 52.5722,
5
+ "eval_loss": 2.59366512298584,
6
+ "eval_runtime": 1018.2616,
7
+ "eval_samples": 1239,
8
+ "eval_samples_per_second": 1.217,
9
+ "eval_steps_per_second": 0.122
10
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
predict_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_bleu": 8.4667,
3
+ "predict_gen_len": 57.1002,
4
+ "predict_loss": 2.38679838180542,
5
+ "predict_runtime": 1007.4993,
6
+ "predict_samples": 998,
7
+ "predict_samples_per_second": 0.991,
8
+ "predict_steps_per_second": 0.099
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aaa7b7f0175c3a158a24c11b3706634954d9f49ca5aa707ac106dcb368eb30ea
3
+ size 2329633625
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 3.811387486049107,
4
+ "train_runtime": 1379.0446,
5
+ "train_samples": 3500,
6
+ "train_samples_per_second": 25.38,
7
+ "train_steps_per_second": 2.538
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 3500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.43,
12
+ "learning_rate": 4.2857142857142856e-05,
13
+ "loss": 7.442,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 2.86,
18
+ "learning_rate": 3.571428571428572e-05,
19
+ "loss": 3.7534,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 4.29,
24
+ "learning_rate": 2.857142857142857e-05,
25
+ "loss": 3.359,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 5.71,
30
+ "learning_rate": 2.1428571428571428e-05,
31
+ "loss": 3.1736,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 7.14,
36
+ "learning_rate": 1.4285714285714285e-05,
37
+ "loss": 3.055,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 8.57,
42
+ "learning_rate": 7.142857142857143e-06,
43
+ "loss": 2.9657,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 10.0,
48
+ "learning_rate": 0.0,
49
+ "loss": 2.931,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 10.0,
54
+ "step": 3500,
55
+ "total_flos": 1.62543492527616e+16,
56
+ "train_loss": 3.811387486049107,
57
+ "train_runtime": 1379.0446,
58
+ "train_samples_per_second": 25.38,
59
+ "train_steps_per_second": 2.538
60
+ }
61
+ ],
62
+ "max_steps": 3500,
63
+ "num_train_epochs": 10,
64
+ "total_flos": 1.62543492527616e+16,
65
+ "trial_name": null,
66
+ "trial_params": null
67
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06542304d990e9e30dbe54c46b4128e5780efcd25baae598a7f7b0e614eb6ddd
3
+ size 2927