Davlan commited on
Commit
2104143
1 Parent(s): 8709fb3

add MT model

Browse files
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "predict_bleu": 4.3708,
4
+ "predict_gen_len": 73.822,
5
+ "predict_loss": 2.8440630435943604,
6
+ "predict_runtime": 1768.2252,
7
+ "predict_samples": 1500,
8
+ "predict_samples_per_second": 0.848,
9
+ "predict_steps_per_second": 0.085,
10
+ "train_loss": 3.5235617083703685,
11
+ "train_runtime": 1078.3402,
12
+ "train_samples": 3337,
13
+ "train_samples_per_second": 30.946,
14
+ "train_steps_per_second": 3.097
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": 3.6353,
4
+ "eval_gen_len": 74.405,
5
+ "eval_loss": 2.9547171592712402,
6
+ "eval_runtime": 1456.5936,
7
+ "eval_samples": 1284,
8
+ "eval_samples_per_second": 0.882,
9
+ "eval_steps_per_second": 0.089
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": 4.3708,
3
+ "predict_gen_len": 73.822,
4
+ "predict_loss": 2.8440630435943604,
5
+ "predict_runtime": 1768.2252,
6
+ "predict_samples": 1500,
7
+ "predict_samples_per_second": 0.848,
8
+ "predict_steps_per_second": 0.085
9
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581bed7ea3f4d6039964479a074aba9747a52ed3fac26a2e6d8c5ac771cd6a70
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": 3.5235617083703685,
4
+ "train_runtime": 1078.3402,
5
+ "train_samples": 3337,
6
+ "train_samples_per_second": 30.946,
7
+ "train_steps_per_second": 3.097
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 3340,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.5,
12
+ "learning_rate": 4.251497005988024e-05,
13
+ "loss": 5.4617,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 2.99,
18
+ "learning_rate": 3.502994011976048e-05,
19
+ "loss": 3.5907,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 4.49,
24
+ "learning_rate": 2.754491017964072e-05,
25
+ "loss": 3.3263,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 5.99,
30
+ "learning_rate": 2.0059880239520957e-05,
31
+ "loss": 3.1748,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 7.49,
36
+ "learning_rate": 1.2574850299401197e-05,
37
+ "loss": 3.0393,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 8.98,
42
+ "learning_rate": 5.0898203592814375e-06,
43
+ "loss": 2.9581,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 10.0,
48
+ "step": 3340,
49
+ "total_flos": 1.444499623466496e+16,
50
+ "train_loss": 3.5235617083703685,
51
+ "train_runtime": 1078.3402,
52
+ "train_samples_per_second": 30.946,
53
+ "train_steps_per_second": 3.097
54
+ }
55
+ ],
56
+ "max_steps": 3340,
57
+ "num_train_epochs": 10,
58
+ "total_flos": 1.444499623466496e+16,
59
+ "trial_name": null,
60
+ "trial_params": null
61
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98177f1f058723670c43064cfdc5a62ad5b3985753983e55e68e10657587b735
3
+ size 2927