Hugging Face's logo

irisaparina
/
t5-3b-spider-nlvariation

Text2Text Generation
Transformers
PyTorch
t5
Inference Endpoints
text-generation-inference
Model card Files Community
irisaparina commited on
Commit
1915004
•
1 Parent(s): 56ff067

Upload 14 files

Browse files
Files changed (14) hide show
  1. all_results.json +13 -0
  2. combined_args.json +156 -0
  3. config.json +62 -0
  4. eval_results.json +8 -0
  5. predictions_eval_31.989635573386828.json +0 -0
  6. pytorch_model-00001-of-00002.bin +3 -0
  7. pytorch_model-00002-of-00002.bin +3 -0
  8. pytorch_model.bin.index.json +519 -0
  9. special_tokens_map.json +107 -0
  10. tokenizer.json +0 -0
  11. tokenizer_config.json +112 -0
  12. train_results.json +8 -0
  13. trainer_state.json +0 -0
  14. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 99.99,
3
+ "eval_exec": 0.753384912959381,
4
+ "eval_loss": 0.2954598069190979,
5
+ "eval_runtime": 294.9299,
6
+ "eval_samples": 1034,
7
+ "eval_samples_per_second": 3.506,
8
+ "train_loss": 0.00013556757536748224,
9
+ "train_runtime": 24498.5901,
10
+ "train_samples": 14954,
11
+ "train_samples_per_second": 61.04,
12
+ "train_steps_per_second": 0.302
13
+ }
combined_args.json ADDED
@@ -0,0 +1,156 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "use_picard": false,
3
+ "launch_picard": false,
4
+ "picard_host": "localhost",
5
+ "picard_port": 9090,
6
+ "picard_mode": "parse_with_guards",
7
+ "picard_schedule": "incremental",
8
+ "picard_max_tokens_to_check": 2,
9
+ "model_name_or_path": "t5-3b",
10
+ "config_name": null,
11
+ "tokenizer_name": null,
12
+ "cache_dir": "/rds/user/hpcsapa1/hpc-work/transformers_cache",
13
+ "use_fast_tokenizer": true,
14
+ "model_revision": "main",
15
+ "use_auth_token": false,
16
+ "dataset": "spider",
17
+ "dataset_paths": {
18
+ "spider": "./seq2seq/datasets/spider",
19
+ "cosql": "./seq2seq/datasets/cosql"
20
+ },
21
+ "predict_and_eval": true,
22
+ "metric_config": "test_suite",
23
+ "metric_paths": {
24
+ "spider": "./seq2seq/metrics/spider",
25
+ "cosql": "./seq2seq/metrics/cosql"
26
+ },
27
+ "test_suite_db_dir": "./third_party/test_suite/database",
28
+ "data_config_file": null,
29
+ "test_sections": null,
30
+ "data_dir": "../data/spider_augs",
31
+ "file_prefix": null,
32
+ "overwrite_cache": false,
33
+ "preprocessing_num_workers": null,
34
+ "max_source_length": 512,
35
+ "max_target_length": 512,
36
+ "val_max_target_length": 512,
37
+ "val_max_time": null,
38
+ "max_train_samples": null,
39
+ "max_val_samples": null,
40
+ "num_beams": 1,
41
+ "num_beam_groups": 1,
42
+ "diversity_penalty": null,
43
+ "ignore_pad_token_for_loss": true,
44
+ "source_prefix": "",
45
+ "schema_serialization_type": "peteshaw",
46
+ "schema_serialization_randomized": false,
47
+ "schema_serialization_with_db_id": true,
48
+ "schema_serialization_with_db_content": true,
49
+ "normalize_query": true,
50
+ "target_with_db_id": true,
51
+ "output_dir": "../models/t5-picard",
52
+ "overwrite_output_dir": false,
53
+ "do_train": true,
54
+ "do_eval": true,
55
+ "do_predict": false,
56
+ "evaluation_strategy": "steps",
57
+ "prediction_loss_only": false,
58
+ "per_device_train_batch_size": 5,
59
+ "per_device_eval_batch_size": 5,
60
+ "per_gpu_train_batch_size": "None",
61
+ "per_gpu_eval_batch_size": "None",
62
+ "gradient_accumulation_steps": 40,
63
+ "eval_accumulation_steps": "None",
64
+ "eval_delay": 0,
65
+ "learning_rate": 0.0001,
66
+ "weight_decay": 0.0,
67
+ "adam_beta1": 0.9,
68
+ "adam_beta2": 0.999,
69
+ "adam_epsilon": 1e-08,
70
+ "max_grad_norm": 1.0,
71
+ "num_train_epochs": 100,
72
+ "max_steps": -1,
73
+ "lr_scheduler_type": "constant",
74
+ "warmup_ratio": 0.0,
75
+ "warmup_steps": 0,
76
+ "log_level": -1,
77
+ "log_level_replica": -1,
78
+ "log_on_each_node": true,
79
+ "logging_dir": "../models/t5-picard/runs/Feb12_15-38-39_gpu-q-39",
80
+ "logging_strategy": "steps",
81
+ "logging_first_step": true,
82
+ "logging_steps": 4,
83
+ "logging_nan_inf_filter": true,
84
+ "save_strategy": "steps",
85
+ "save_steps": 64,
86
+ "save_total_limit": 2,
87
+ "save_on_each_node": false,
88
+ "no_cuda": false,
89
+ "seed": 1,
90
+ "data_seed": "None",
91
+ "jit_mode_eval": false,
92
+ "use_ipex": false,
93
+ "bf16": false,
94
+ "fp16": false,
95
+ "fp16_opt_level": "O1",
96
+ "half_precision_backend": "auto",
97
+ "bf16_full_eval": false,
98
+ "fp16_full_eval": false,
99
+ "tf32": "None",
100
+ "xpu_backend": "None",
101
+ "tpu_num_cores": "None",
102
+ "tpu_metrics_debug": false,
103
+ "debug": "[]",
104
+ "dataloader_drop_last": false,
105
+ "eval_steps": 64,
106
+ "dataloader_num_workers": 0,
107
+ "past_index": -1,
108
+ "run_name": "t5-spider-augs",
109
+ "disable_tqdm": false,
110
+ "remove_unused_columns": true,
111
+ "label_names": "None",
112
+ "load_best_model_at_end": true,
113
+ "metric_for_best_model": "exec",
114
+ "greater_is_better": true,
115
+ "ignore_data_skip": false,
116
+ "sharded_ddp": "[]",
117
+ "fsdp": "[]",
118
+ "fsdp_min_num_params": 0,
119
+ "fsdp_transformer_layer_cls_to_wrap": "None",
120
+ "deepspeed": "None",
121
+ "label_smoothing_factor": 0.0,
122
+ "optim": "adafactor",
123
+ "adafactor": true,
124
+ "group_by_length": true,
125
+ "length_column_name": "length",
126
+ "report_to": "['wandb']",
127
+ "ddp_find_unused_parameters": "None",
128
+ "ddp_bucket_cap_mb": "None",
129
+ "dataloader_pin_memory": true,
130
+ "skip_memory_metrics": true,
131
+ "use_legacy_prediction_loop": false,
132
+ "push_to_hub": false,
133
+ "resume_from_checkpoint": "None",
134
+ "hub_model_id": "None",
135
+ "hub_strategy": "every_save",
136
+ "hub_token": "<HUB_TOKEN>",
137
+ "hub_private_repo": false,
138
+ "gradient_checkpointing": false,
139
+ "include_inputs_for_metrics": false,
140
+ "fp16_backend": "auto",
141
+ "push_to_hub_model_id": "None",
142
+ "push_to_hub_organization": "None",
143
+ "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>",
144
+ "_n_gpu": 1,
145
+ "mp_parameters": "",
146
+ "auto_find_batch_size": false,
147
+ "full_determinism": false,
148
+ "torchdynamo": "None",
149
+ "ray_scope": "last",
150
+ "sortish_sampler": false,
151
+ "predict_with_generate": true,
152
+ "generation_max_length": "None",
153
+ "generation_num_beams": "None",
154
+ "train_batch_size": 5,
155
+ "eval_batch_size": 5
156
+ }
config.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-3b",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 16384,
7
+ "d_kv": 128,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "diversity_penalty": null,
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
+ "max_length": 512,
20
+ "model_type": "t5",
21
+ "n_positions": 512,
22
+ "num_decoder_layers": 24,
23
+ "num_heads": 32,
24
+ "num_layers": 24,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "relative_attention_max_distance": 128,
28
+ "relative_attention_num_buckets": 32,
29
+ "task_specific_params": {
30
+ "summarization": {
31
+ "early_stopping": true,
32
+ "length_penalty": 2.0,
33
+ "max_length": 200,
34
+ "min_length": 30,
35
+ "no_repeat_ngram_size": 3,
36
+ "num_beams": 4,
37
+ "prefix": "summarize: "
38
+ },
39
+ "translation_en_to_de": {
40
+ "early_stopping": true,
41
+ "max_length": 300,
42
+ "num_beams": 4,
43
+ "prefix": "translate English to German: "
44
+ },
45
+ "translation_en_to_fr": {
46
+ "early_stopping": true,
47
+ "max_length": 300,
48
+ "num_beams": 4,
49
+ "prefix": "translate English to French: "
50
+ },
51
+ "translation_en_to_ro": {
52
+ "early_stopping": true,
53
+ "max_length": 300,
54
+ "num_beams": 4,
55
+ "prefix": "translate English to Romanian: "
56
+ }
57
+ },
58
+ "torch_dtype": "float32",
59
+ "transformers_version": "4.21.3",
60
+ "use_cache": true,
61
+ "vocab_size": 32102
62
+ }
eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 99.99,
3
+ "eval_exec": 0.753384912959381,
4
+ "eval_loss": 0.2954598069190979,
5
+ "eval_runtime": 294.9299,
6
+ "eval_samples": 1034,
7
+ "eval_samples_per_second": 3.506
8
+ }
predictions_eval_31.989635573386828.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model-00001-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d856785d5bef8ad834762fc88aafc28596a82e7ed16d547596a2923d381991dd
3
+ size 9728631517
pytorch_model-00002-of-00002.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:666f4f28c0f2e40d88abf79b1f28e68bb62ae18d769ab2af196d65e7424b39f5
3
+ size 1809320175
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,519 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 11800756224
4
+ },
5
+ "weight_map": {
6
+ "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
7
+ "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
8
+ "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
9
+ "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
10
+ "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
11
+ "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
12
+ "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
13
+ "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
14
+ "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
15
+ "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
16
+ "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
17
+ "decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
18
+ "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
19
+ "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
20
+ "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
21
+ "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
22
+ "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
23
+ "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
24
+ "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
25
+ "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
26
+ "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
27
+ "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
28
+ "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
29
+ "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
30
+ "decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
31
+ "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
32
+ "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
33
+ "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
34
+ "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
35
+ "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
36
+ "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
37
+ "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
38
+ "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
39
+ "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
40
+ "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
41
+ "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
42
+ "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
43
+ "decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
44
+ "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
45
+ "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
46
+ "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
47
+ "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
48
+ "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
49
+ "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
50
+ "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
51
+ "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
52
+ "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
53
+ "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
54
+ "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
55
+ "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
56
+ "decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
57
+ "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
58
+ "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
59
+ "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
60
+ "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
61
+ "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
62
+ "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
63
+ "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
64
+ "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
65
+ "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
66
+ "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
67
+ "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
68
+ "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
69
+ "decoder.block.12.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
70
+ "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
71
+ "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
72
+ "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
73
+ "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
74
+ "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
75
+ "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
76
+ "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
77
+ "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
78
+ "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
79
+ "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
80
+ "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
81
+ "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
82
+ "decoder.block.13.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
83
+ "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
84
+ "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
85
+ "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
86
+ "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
87
+ "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
88
+ "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
89
+ "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
90
+ "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
91
+ "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
92
+ "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
93
+ "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
94
+ "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
95
+ "decoder.block.14.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
96
+ "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
97
+ "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
98
+ "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
99
+ "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
100
+ "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
101
+ "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
102
+ "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
103
+ "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
104
+ "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
105
+ "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
106
+ "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
107
+ "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
108
+ "decoder.block.15.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
109
+ "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
110
+ "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
111
+ "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
112
+ "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
113
+ "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
114
+ "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
115
+ "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
116
+ "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
117
+ "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
118
+ "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
119
+ "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
120
+ "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
121
+ "decoder.block.16.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
122
+ "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
123
+ "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
124
+ "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
125
+ "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
126
+ "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
127
+ "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
128
+ "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
129
+ "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
130
+ "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
131
+ "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
132
+ "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
133
+ "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
134
+ "decoder.block.17.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
135
+ "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
136
+ "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
137
+ "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
138
+ "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
139
+ "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
140
+ "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
141
+ "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
142
+ "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
143
+ "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
144
+ "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
145
+ "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
146
+ "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
147
+ "decoder.block.18.layer.2.DenseReluDense.wi.weight": "pytorch_model-00002-of-00002.bin",
148
+ "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
149
+ "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
150
+ "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
151
+ "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
152
+ "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
153
+ "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
154
+ "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
155
+ "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
156
+ "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
157
+ "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
158
+ "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
159
+ "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
160
+ "decoder.block.19.layer.2.DenseReluDense.wi.weight": "pytorch_model-00002-of-00002.bin",
161
+ "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
162
+ "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
163
+ "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
164
+ "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
165
+ "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
166
+ "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
167
+ "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
168
+ "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
169
+ "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
170
+ "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
171
+ "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
172
+ "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
173
+ "decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
174
+ "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
175
+ "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
176
+ "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
177
+ "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
178
+ "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
179
+ "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
180
+ "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
181
+ "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
182
+ "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
183
+ "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
184
+ "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
185
+ "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
186
+ "decoder.block.20.layer.2.DenseReluDense.wi.weight": "pytorch_model-00002-of-00002.bin",
187
+ "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
188
+ "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
189
+ "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
190
+ "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
191
+ "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
192
+ "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
193
+ "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
194
+ "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
195
+ "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
196
+ "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
197
+ "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
198
+ "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
199
+ "decoder.block.21.layer.2.DenseReluDense.wi.weight": "pytorch_model-00002-of-00002.bin",
200
+ "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
201
+ "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
202
+ "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
203
+ "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
204
+ "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
205
+ "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
206
+ "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
207
+ "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
208
+ "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
209
+ "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
210
+ "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
211
+ "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
212
+ "decoder.block.22.layer.2.DenseReluDense.wi.weight": "pytorch_model-00002-of-00002.bin",
213
+ "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
214
+ "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
215
+ "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
216
+ "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
217
+ "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
218
+ "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
219
+ "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
220
+ "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
221
+ "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
222
+ "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
223
+ "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
224
+ "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
225
+ "decoder.block.23.layer.2.DenseReluDense.wi.weight": "pytorch_model-00002-of-00002.bin",
226
+ "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
227
+ "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
228
+ "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
229
+ "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
230
+ "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
231
+ "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
232
+ "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
233
+ "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
234
+ "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
235
+ "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
236
+ "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
237
+ "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
238
+ "decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
239
+ "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
240
+ "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
241
+ "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
242
+ "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
243
+ "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
244
+ "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
245
+ "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
246
+ "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
247
+ "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
248
+ "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
249
+ "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
250
+ "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
251
+ "decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
252
+ "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
253
+ "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
254
+ "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
255
+ "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
256
+ "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
257
+ "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
258
+ "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
259
+ "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
260
+ "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
261
+ "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
262
+ "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
263
+ "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
264
+ "decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
265
+ "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
266
+ "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
267
+ "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
268
+ "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
269
+ "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
270
+ "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
271
+ "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
272
+ "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
273
+ "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
274
+ "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
275
+ "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
276
+ "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
277
+ "decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
278
+ "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
279
+ "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
280
+ "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
281
+ "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
282
+ "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
283
+ "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
284
+ "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
285
+ "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
286
+ "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
287
+ "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
288
+ "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
289
+ "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
290
+ "decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
291
+ "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
292
+ "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
293
+ "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
294
+ "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
295
+ "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
296
+ "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
297
+ "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
298
+ "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
299
+ "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
300
+ "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
301
+ "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
302
+ "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
303
+ "decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
304
+ "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
305
+ "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
306
+ "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
307
+ "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
308
+ "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
309
+ "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
310
+ "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
311
+ "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
312
+ "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
313
+ "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
314
+ "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
315
+ "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
316
+ "decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
317
+ "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
318
+ "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
319
+ "decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
320
+ "decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
321
+ "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
322
+ "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
323
+ "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
324
+ "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
325
+ "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
326
+ "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
327
+ "encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
328
+ "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
329
+ "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
330
+ "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
331
+ "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
332
+ "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
333
+ "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
334
+ "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
335
+ "encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
336
+ "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
337
+ "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
338
+ "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
339
+ "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
340
+ "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
341
+ "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
342
+ "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
343
+ "encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
344
+ "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
345
+ "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
346
+ "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
347
+ "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
348
+ "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
349
+ "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
350
+ "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
351
+ "encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
352
+ "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
353
+ "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
354
+ "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
355
+ "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
356
+ "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
357
+ "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
358
+ "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
359
+ "encoder.block.12.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
360
+ "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
361
+ "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
362
+ "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
363
+ "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
364
+ "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
365
+ "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
366
+ "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
367
+ "encoder.block.13.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
368
+ "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
369
+ "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
370
+ "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
371
+ "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
372
+ "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
373
+ "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
374
+ "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
375
+ "encoder.block.14.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
376
+ "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
377
+ "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
378
+ "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
379
+ "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
380
+ "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
381
+ "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
382
+ "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
383
+ "encoder.block.15.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
384
+ "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
385
+ "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
386
+ "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
387
+ "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
388
+ "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
389
+ "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
390
+ "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
391
+ "encoder.block.16.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
392
+ "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
393
+ "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
394
+ "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
395
+ "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
396
+ "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
397
+ "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
398
+ "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
399
+ "encoder.block.17.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
400
+ "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
401
+ "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
402
+ "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
403
+ "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
404
+ "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
405
+ "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
406
+ "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
407
+ "encoder.block.18.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
408
+ "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
409
+ "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
410
+ "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
411
+ "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
412
+ "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
413
+ "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
414
+ "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
415
+ "encoder.block.19.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
416
+ "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
417
+ "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
418
+ "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
419
+ "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
420
+ "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
421
+ "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
422
+ "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
423
+ "encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
424
+ "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
425
+ "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
426
+ "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
427
+ "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
428
+ "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
429
+ "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
430
+ "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
431
+ "encoder.block.20.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
432
+ "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
433
+ "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
434
+ "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
435
+ "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
436
+ "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
437
+ "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
438
+ "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
439
+ "encoder.block.21.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
440
+ "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
441
+ "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
442
+ "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
443
+ "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
444
+ "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
445
+ "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
446
+ "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
447
+ "encoder.block.22.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
448
+ "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
449
+ "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
450
+ "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
451
+ "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
452
+ "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
453
+ "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
454
+ "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
455
+ "encoder.block.23.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
456
+ "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
457
+ "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
458
+ "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
459
+ "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
460
+ "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
461
+ "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
462
+ "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
463
+ "encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
464
+ "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
465
+ "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
466
+ "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
467
+ "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
468
+ "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
469
+ "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
470
+ "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
471
+ "encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
472
+ "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
473
+ "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
474
+ "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
475
+ "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
476
+ "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
477
+ "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
478
+ "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
479
+ "encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
480
+ "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
481
+ "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
482
+ "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
483
+ "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
484
+ "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
485
+ "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
486
+ "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
487
+ "encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
488
+ "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
489
+ "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
490
+ "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
491
+ "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
492
+ "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
493
+ "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
494
+ "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
495
+ "encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
496
+ "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
497
+ "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
498
+ "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
499
+ "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
500
+ "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
501
+ "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
502
+ "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
503
+ "encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
504
+ "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
505
+ "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
506
+ "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
507
+ "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
508
+ "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
509
+ "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
510
+ "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
511
+ "encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00002.bin",
512
+ "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
513
+ "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
514
+ "encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
515
+ "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
516
+ "lm_head.weight": "pytorch_model-00002-of-00002.bin",
517
+ "shared.weight": "pytorch_model-00001-of-00002.bin"
518
+ }
519
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "pad_token": "<pad>",
106
+ "unk_token": "<unk>"
107
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": "</s>",
105
+ "extra_ids": 100,
106
+ "model_max_length": 512,
107
+ "name_or_path": "t5-3b",
108
+ "pad_token": "<pad>",
109
+ "special_tokens_map_file": null,
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 99.99,
3
+ "train_loss": 0.00013556757536748224,
4
+ "train_runtime": 24498.5901,
5
+ "train_samples": 14954,
6
+ "train_samples_per_second": 61.04,
7
+ "train_steps_per_second": 0.302
8
+ }
trainer_state.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b05808ad213dd3f3dc8c05e73f9f813640286cc25c74ba06647793dd4dae6fa
3
+ size 3439