pszemraj commited on
Commit
95c446c
1 Parent(s): 860e453
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5",
3
+ "architectures": [
4
+ "LongT5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2816,
7
+ "d_kv": 64,
8
+ "d_model": 1024,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "gelu_new",
11
+ "dropout_rate": 0.1,
12
+ "early_stopping": true,
13
+ "encoder_attention_type": "transient-global",
14
+ "encoder_no_repeat_ngram_size": 4,
15
+ "eos_token_id": 1,
16
+ "feed_forward_proj": "gated-gelu",
17
+ "global_block_size": 16,
18
+ "initializer_factor": 1.0,
19
+ "is_encoder_decoder": true,
20
+ "is_gated_act": true,
21
+ "layer_norm_epsilon": 1e-06,
22
+ "length_penalty": 0.8,
23
+ "local_radius": 127,
24
+ "max_length": 512,
25
+ "min_length": 8,
26
+ "model_type": "longt5",
27
+ "n_positions": 4096,
28
+ "no_repeat_ngram_size": 3,
29
+ "num_beams": 2,
30
+ "num_decoder_layers": 24,
31
+ "num_heads": 16,
32
+ "num_layers": 24,
33
+ "output_past": true,
34
+ "pad_token_id": 0,
35
+ "relative_attention_max_distance": 128,
36
+ "relative_attention_num_buckets": 32,
37
+ "repetition_penalty": 3.5,
38
+ "tie_word_embeddings": false,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.23.0.dev0",
41
+ "use_cache": false,
42
+ "vocab_size": 32100
43
+ }
long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5-ft3-booksum_training_metadata.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"output_dir": "/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5-ft3-booksum", "overwrite_output_dir": true, "do_train": false, "do_eval": false, "do_predict": false, "evaluation_strategy": "no", "prediction_loss_only": false, "per_device_train_batch_size": 1, "per_device_eval_batch_size": 1, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 64, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 0.0004, "weight_decay": 0.02, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1, "num_train_epochs": 3, "max_steps": -1, "lr_scheduler_type": "cosine", "warmup_ratio": 0.01, "warmup_steps": 0, "log_level": -1, "log_level_replica": -1, "log_on_each_node": true, "logging_dir": "/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5-ft3-booksum/logs", "logging_strategy": "steps", "logging_first_step": false, "logging_steps": 2, "logging_nan_inf_filter": true, "save_strategy": "steps", "save_steps": 25, "save_total_limit": 1, "save_on_each_node": false, "no_cuda": false, "use_mps_device": false, "seed": 42, "data_seed": "None", "jit_mode_eval": false, "use_ipex": false, "bf16": true, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "cuda_amp", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": "None", "local_rank": 0, "xpu_backend": "None", "tpu_num_cores": "None", "tpu_metrics_debug": false, "debug": "[]", "dataloader_drop_last": false, "eval_steps": "None", "dataloader_num_workers": 0, "past_index": -1, "run_name": "/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5-ft3-booksum", "disable_tqdm": false, "remove_unused_columns": true, "label_names": "None", "load_best_model_at_end": false, "metric_for_best_model": "None", "greater_is_better": "None", "ignore_data_skip": false, "sharded_ddp": "[]", "fsdp": "[]", "fsdp_min_num_params": 0, "fsdp_transformer_layer_cls_to_wrap": "None", "deepspeed": "None", "label_smoothing_factor": 0.0, "optim": "adamw_hf", "adafactor": false, "group_by_length": false, "length_column_name": "length", "report_to": "['tensorboard']", "ddp_find_unused_parameters": "None", "ddp_bucket_cap_mb": "None", "dataloader_pin_memory": true, "skip_memory_metrics": false, "use_legacy_prediction_loop": false, "push_to_hub": true, "resume_from_checkpoint": "None", "hub_model_id": "long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5-ft3-booksum", "hub_strategy": "end", "hub_token": "<HUB_TOKEN>", "hub_private_repo": true, "gradient_checkpointing": true, "include_inputs_for_metrics": false, "fp16_backend": "auto", "push_to_hub_model_id": "None", "push_to_hub_organization": "None", "push_to_hub_token": "<PUSH_TO_HUB_TOKEN>", "_n_gpu": 1, "mp_parameters": "", "auto_find_batch_size": false, "full_determinism": false, "torchdynamo": "None", "ray_scope": "last", "ddp_timeout": 1800, "sortish_sampler": false, "predict_with_generate": false, "generation_max_length": "None", "generation_num_beams": "None", "train_batch_size": 1, "eval_batch_size": 1, "configs_src": "long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5-ft3-booksum", "use_adam8bit": false, "use_adan_optim": true, "optim_params": "(None, None)", "decay_rate_ada": -0.5}
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5c220de7a2ffd094a692bffdf1d82da7fe1c0f88cdee923dbd425d1fcedb658
3
+ size 3132671411
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
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13.5",
107
+ "pad_token": "<pad>",
108
+ "special_tokens_map_file": null,
109
+ "tokenizer_class": "T5Tokenizer",
110
+ "unk_token": "<unk>"
111
+ }
trainer_state.json ADDED
@@ -0,0 +1,700 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.3807365439093484,
5
+ "global_step": 228,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 0.00016,
13
+ "loss": 2.092,
14
+ "step": 2
15
+ },
16
+ {
17
+ "epoch": 0.02,
18
+ "learning_rate": 0.00032,
19
+ "loss": 2.0773,
20
+ "step": 4
21
+ },
22
+ {
23
+ "epoch": 0.04,
24
+ "learning_rate": 0.0003999958893916732,
25
+ "loss": 1.9915,
26
+ "step": 6
27
+ },
28
+ {
29
+ "epoch": 0.05,
30
+ "learning_rate": 0.00039996300553887804,
31
+ "loss": 2.1242,
32
+ "step": 8
33
+ },
34
+ {
35
+ "epoch": 0.06,
36
+ "learning_rate": 0.0003998972432401376,
37
+ "loss": 2.0798,
38
+ "step": 10
39
+ },
40
+ {
41
+ "epoch": 0.07,
42
+ "learning_rate": 0.00039979861330826294,
43
+ "loss": 2.099,
44
+ "step": 12
45
+ },
46
+ {
47
+ "epoch": 0.08,
48
+ "learning_rate": 0.0003996671319602482,
49
+ "loss": 2.0562,
50
+ "step": 14
51
+ },
52
+ {
53
+ "epoch": 0.1,
54
+ "learning_rate": 0.00039950282081460415,
55
+ "loss": 2.0909,
56
+ "step": 16
57
+ },
58
+ {
59
+ "epoch": 0.11,
60
+ "learning_rate": 0.0003993057068878037,
61
+ "loss": 2.0784,
62
+ "step": 18
63
+ },
64
+ {
65
+ "epoch": 0.12,
66
+ "learning_rate": 0.00039907582258983965,
67
+ "loss": 2.0465,
68
+ "step": 20
69
+ },
70
+ {
71
+ "epoch": 0.13,
72
+ "learning_rate": 0.00039881320571889605,
73
+ "loss": 2.173,
74
+ "step": 22
75
+ },
76
+ {
77
+ "epoch": 0.15,
78
+ "learning_rate": 0.000398517899455133,
79
+ "loss": 2.0897,
80
+ "step": 24
81
+ },
82
+ {
83
+ "epoch": 0.16,
84
+ "learning_rate": 0.00039818995235358696,
85
+ "loss": 2.057,
86
+ "step": 26
87
+ },
88
+ {
89
+ "epoch": 0.17,
90
+ "learning_rate": 0.00039782941833618724,
91
+ "loss": 2.0833,
92
+ "step": 28
93
+ },
94
+ {
95
+ "epoch": 0.18,
96
+ "learning_rate": 0.00039743635668289007,
97
+ "loss": 2.0256,
98
+ "step": 30
99
+ },
100
+ {
101
+ "epoch": 0.19,
102
+ "learning_rate": 0.0003970108320219314,
103
+ "loss": 2.0925,
104
+ "step": 32
105
+ },
106
+ {
107
+ "epoch": 0.21,
108
+ "learning_rate": 0.0003965529143192008,
109
+ "loss": 2.0337,
110
+ "step": 34
111
+ },
112
+ {
113
+ "epoch": 0.22,
114
+ "learning_rate": 0.0003960626788667375,
115
+ "loss": 2.0865,
116
+ "step": 36
117
+ },
118
+ {
119
+ "epoch": 0.23,
120
+ "learning_rate": 0.00039554020627035035,
121
+ "loss": 2.164,
122
+ "step": 38
123
+ },
124
+ {
125
+ "epoch": 0.24,
126
+ "learning_rate": 0.0003949855824363647,
127
+ "loss": 2.1327,
128
+ "step": 40
129
+ },
130
+ {
131
+ "epoch": 0.25,
132
+ "learning_rate": 0.00039439889855749763,
133
+ "loss": 2.171,
134
+ "step": 42
135
+ },
136
+ {
137
+ "epoch": 0.27,
138
+ "learning_rate": 0.0003937802510978631,
139
+ "loss": 2.0629,
140
+ "step": 44
141
+ },
142
+ {
143
+ "epoch": 0.28,
144
+ "learning_rate": 0.00039312974177711183,
145
+ "loss": 2.0344,
146
+ "step": 46
147
+ },
148
+ {
149
+ "epoch": 0.29,
150
+ "learning_rate": 0.0003924474775537058,
151
+ "loss": 2.071,
152
+ "step": 48
153
+ },
154
+ {
155
+ "epoch": 0.3,
156
+ "learning_rate": 0.0003917335706073321,
157
+ "loss": 2.11,
158
+ "step": 50
159
+ },
160
+ {
161
+ "epoch": 0.31,
162
+ "learning_rate": 0.0003909881383204581,
163
+ "loss": 2.1477,
164
+ "step": 52
165
+ },
166
+ {
167
+ "epoch": 0.33,
168
+ "learning_rate": 0.00039021130325903074,
169
+ "loss": 2.087,
170
+ "step": 54
171
+ },
172
+ {
173
+ "epoch": 0.34,
174
+ "learning_rate": 0.0003894031931523243,
175
+ "loss": 2.0943,
176
+ "step": 56
177
+ },
178
+ {
179
+ "epoch": 0.35,
180
+ "learning_rate": 0.0003885639408719386,
181
+ "loss": 2.0061,
182
+ "step": 58
183
+ },
184
+ {
185
+ "epoch": 0.36,
186
+ "learning_rate": 0.0003876936844099521,
187
+ "loss": 2.0888,
188
+ "step": 60
189
+ },
190
+ {
191
+ "epoch": 0.37,
192
+ "learning_rate": 0.00038679256685623264,
193
+ "loss": 2.1795,
194
+ "step": 62
195
+ },
196
+ {
197
+ "epoch": 0.39,
198
+ "learning_rate": 0.0003858607363749104,
199
+ "loss": 2.1248,
200
+ "step": 64
201
+ },
202
+ {
203
+ "epoch": 0.4,
204
+ "learning_rate": 0.00038489834618001635,
205
+ "loss": 2.0761,
206
+ "step": 66
207
+ },
208
+ {
209
+ "epoch": 0.41,
210
+ "learning_rate": 0.0003839055545102902,
211
+ "loss": 2.1293,
212
+ "step": 68
213
+ },
214
+ {
215
+ "epoch": 0.42,
216
+ "learning_rate": 0.00038288252460316253,
217
+ "loss": 2.0532,
218
+ "step": 70
219
+ },
220
+ {
221
+ "epoch": 0.44,
222
+ "learning_rate": 0.000381829424667915,
223
+ "loss": 2.1937,
224
+ "step": 72
225
+ },
226
+ {
227
+ "epoch": 0.45,
228
+ "learning_rate": 0.0003807464278580227,
229
+ "loss": 2.1357,
230
+ "step": 74
231
+ },
232
+ {
233
+ "epoch": 0.46,
234
+ "learning_rate": 0.0003796337122426838,
235
+ "loss": 2.132,
236
+ "step": 76
237
+ },
238
+ {
239
+ "epoch": 0.47,
240
+ "learning_rate": 0.0003784914607775412,
241
+ "loss": 2.0785,
242
+ "step": 78
243
+ },
244
+ {
245
+ "epoch": 0.48,
246
+ "learning_rate": 0.00037731986127460007,
247
+ "loss": 2.1671,
248
+ "step": 80
249
+ },
250
+ {
251
+ "epoch": 0.5,
252
+ "learning_rate": 0.0003761191063713476,
253
+ "loss": 2.1016,
254
+ "step": 82
255
+ },
256
+ {
257
+ "epoch": 0.51,
258
+ "learning_rate": 0.00037488939349907913,
259
+ "loss": 2.1284,
260
+ "step": 84
261
+ },
262
+ {
263
+ "epoch": 0.52,
264
+ "learning_rate": 0.0003736309248504357,
265
+ "loss": 2.1275,
266
+ "step": 86
267
+ },
268
+ {
269
+ "epoch": 0.53,
270
+ "learning_rate": 0.000372343907346159,
271
+ "loss": 2.0667,
272
+ "step": 88
273
+ },
274
+ {
275
+ "epoch": 0.54,
276
+ "learning_rate": 0.00037102855260106926,
277
+ "loss": 2.1596,
278
+ "step": 90
279
+ },
280
+ {
281
+ "epoch": 0.56,
282
+ "learning_rate": 0.0003696850768892705,
283
+ "loss": 2.1802,
284
+ "step": 92
285
+ },
286
+ {
287
+ "epoch": 0.57,
288
+ "learning_rate": 0.00036831370110859067,
289
+ "loss": 2.0789,
290
+ "step": 94
291
+ },
292
+ {
293
+ "epoch": 0.58,
294
+ "learning_rate": 0.00036691465074426054,
295
+ "loss": 2.1284,
296
+ "step": 96
297
+ },
298
+ {
299
+ "epoch": 0.59,
300
+ "learning_rate": 0.0003654881558318393,
301
+ "loss": 2.1499,
302
+ "step": 98
303
+ },
304
+ {
305
+ "epoch": 0.6,
306
+ "learning_rate": 0.0003640344509193912,
307
+ "loss": 2.063,
308
+ "step": 100
309
+ },
310
+ {
311
+ "epoch": 0.62,
312
+ "learning_rate": 0.00036255377502892054,
313
+ "loss": 2.0843,
314
+ "step": 102
315
+ },
316
+ {
317
+ "epoch": 0.63,
318
+ "learning_rate": 0.0003610463716170712,
319
+ "loss": 2.0807,
320
+ "step": 104
321
+ },
322
+ {
323
+ "epoch": 0.64,
324
+ "learning_rate": 0.00035951248853509696,
325
+ "loss": 2.0838,
326
+ "step": 106
327
+ },
328
+ {
329
+ "epoch": 0.65,
330
+ "learning_rate": 0.00035795237798810846,
331
+ "loss": 2.1357,
332
+ "step": 108
333
+ },
334
+ {
335
+ "epoch": 0.66,
336
+ "learning_rate": 0.000356366296493606,
337
+ "loss": 2.1482,
338
+ "step": 110
339
+ },
340
+ {
341
+ "epoch": 0.68,
342
+ "learning_rate": 0.00035475450483930137,
343
+ "loss": 2.0468,
344
+ "step": 112
345
+ },
346
+ {
347
+ "epoch": 0.69,
348
+ "learning_rate": 0.00035311726804023894,
349
+ "loss": 2.0996,
350
+ "step": 114
351
+ },
352
+ {
353
+ "epoch": 0.7,
354
+ "learning_rate": 0.0003514548552952211,
355
+ "loss": 2.1049,
356
+ "step": 116
357
+ },
358
+ {
359
+ "epoch": 0.71,
360
+ "learning_rate": 0.00034976753994254566,
361
+ "loss": 2.07,
362
+ "step": 118
363
+ },
364
+ {
365
+ "epoch": 0.73,
366
+ "learning_rate": 0.0003480555994150631,
367
+ "loss": 2.1217,
368
+ "step": 120
369
+ },
370
+ {
371
+ "epoch": 0.74,
372
+ "learning_rate": 0.0003463193151945603,
373
+ "loss": 2.0953,
374
+ "step": 122
375
+ },
376
+ {
377
+ "epoch": 0.75,
378
+ "learning_rate": 0.0003445589727654783,
379
+ "loss": 2.1044,
380
+ "step": 124
381
+ },
382
+ {
383
+ "epoch": 0.76,
384
+ "learning_rate": 0.0003427748615679726,
385
+ "loss": 2.0992,
386
+ "step": 126
387
+ },
388
+ {
389
+ "epoch": 0.77,
390
+ "learning_rate": 0.00034096727495032235,
391
+ "loss": 2.1416,
392
+ "step": 128
393
+ },
394
+ {
395
+ "epoch": 0.79,
396
+ "learning_rate": 0.00033913651012069734,
397
+ "loss": 2.1709,
398
+ "step": 130
399
+ },
400
+ {
401
+ "epoch": 0.8,
402
+ "learning_rate": 0.0003372828680982901,
403
+ "loss": 2.1202,
404
+ "step": 132
405
+ },
406
+ {
407
+ "epoch": 0.81,
408
+ "learning_rate": 0.0003354066536638219,
409
+ "loss": 2.145,
410
+ "step": 134
411
+ },
412
+ {
413
+ "epoch": 0.82,
414
+ "learning_rate": 0.0003335081753094296,
415
+ "loss": 2.1667,
416
+ "step": 136
417
+ },
418
+ {
419
+ "epoch": 0.83,
420
+ "learning_rate": 0.00033158774518794254,
421
+ "loss": 2.0619,
422
+ "step": 138
423
+ },
424
+ {
425
+ "epoch": 0.85,
426
+ "learning_rate": 0.00032964567906155774,
427
+ "loss": 2.0791,
428
+ "step": 140
429
+ },
430
+ {
431
+ "epoch": 0.86,
432
+ "learning_rate": 0.0003276822962499211,
433
+ "loss": 2.1484,
434
+ "step": 142
435
+ },
436
+ {
437
+ "epoch": 0.87,
438
+ "learning_rate": 0.0003256979195776247,
439
+ "loss": 2.1358,
440
+ "step": 144
441
+ },
442
+ {
443
+ "epoch": 0.88,
444
+ "learning_rate": 0.00032369287532112634,
445
+ "loss": 2.0854,
446
+ "step": 146
447
+ },
448
+ {
449
+ "epoch": 0.89,
450
+ "learning_rate": 0.0003216674931551027,
451
+ "loss": 2.1297,
452
+ "step": 148
453
+ },
454
+ {
455
+ "epoch": 0.91,
456
+ "learning_rate": 0.00031962210609824324,
457
+ "loss": 2.0643,
458
+ "step": 150
459
+ },
460
+ {
461
+ "epoch": 0.92,
462
+ "learning_rate": 0.00031755705045849464,
463
+ "loss": 2.1189,
464
+ "step": 152
465
+ },
466
+ {
467
+ "epoch": 0.93,
468
+ "learning_rate": 0.00031547266577776394,
469
+ "loss": 2.1361,
470
+ "step": 154
471
+ },
472
+ {
473
+ "epoch": 0.94,
474
+ "learning_rate": 0.00031336929477609,
475
+ "loss": 2.0426,
476
+ "step": 156
477
+ },
478
+ {
479
+ "epoch": 0.95,
480
+ "learning_rate": 0.000311247283295293,
481
+ "loss": 2.0954,
482
+ "step": 158
483
+ },
484
+ {
485
+ "epoch": 0.97,
486
+ "learning_rate": 0.0003091069802421097,
487
+ "loss": 2.1072,
488
+ "step": 160
489
+ },
490
+ {
491
+ "epoch": 0.98,
492
+ "learning_rate": 0.00030694873753082594,
493
+ "loss": 2.1506,
494
+ "step": 162
495
+ },
496
+ {
497
+ "epoch": 0.99,
498
+ "learning_rate": 0.0003047729100254131,
499
+ "loss": 2.1293,
500
+ "step": 164
501
+ },
502
+ {
503
+ "epoch": 1.01,
504
+ "learning_rate": 0.00030257985548118126,
505
+ "loss": 2.5226,
506
+ "step": 166
507
+ },
508
+ {
509
+ "epoch": 1.02,
510
+ "learning_rate": 0.00030036993448595556,
511
+ "loss": 2.0338,
512
+ "step": 168
513
+ },
514
+ {
515
+ "epoch": 1.03,
516
+ "learning_rate": 0.0002981435104007876,
517
+ "loss": 2.0049,
518
+ "step": 170
519
+ },
520
+ {
521
+ "epoch": 1.04,
522
+ "learning_rate": 0.0002959009493002108,
523
+ "loss": 2.0443,
524
+ "step": 172
525
+ },
526
+ {
527
+ "epoch": 1.05,
528
+ "learning_rate": 0.0002936426199120492,
529
+ "loss": 2.0638,
530
+ "step": 174
531
+ },
532
+ {
533
+ "epoch": 1.07,
534
+ "learning_rate": 0.0002913688935567903,
535
+ "loss": 2.039,
536
+ "step": 176
537
+ },
538
+ {
539
+ "epoch": 1.08,
540
+ "learning_rate": 0.0002890801440865318,
541
+ "loss": 1.9961,
542
+ "step": 178
543
+ },
544
+ {
545
+ "epoch": 1.09,
546
+ "learning_rate": 0.00028677674782351165,
547
+ "loss": 1.9829,
548
+ "step": 180
549
+ },
550
+ {
551
+ "epoch": 1.1,
552
+ "learning_rate": 0.000284459083498232,
553
+ "loss": 1.9802,
554
+ "step": 182
555
+ },
556
+ {
557
+ "epoch": 1.11,
558
+ "learning_rate": 0.0002821275321871876,
559
+ "loss": 2.012,
560
+ "step": 184
561
+ },
562
+ {
563
+ "epoch": 1.13,
564
+ "learning_rate": 0.0002797824772502084,
565
+ "loss": 1.9602,
566
+ "step": 186
567
+ },
568
+ {
569
+ "epoch": 1.14,
570
+ "learning_rate": 0.00027742430426742567,
571
+ "loss": 2.1046,
572
+ "step": 188
573
+ },
574
+ {
575
+ "epoch": 1.15,
576
+ "learning_rate": 0.0002750534009758749,
577
+ "loss": 2.046,
578
+ "step": 190
579
+ },
580
+ {
581
+ "epoch": 1.16,
582
+ "learning_rate": 0.0002726701572057423,
583
+ "loss": 2.0335,
584
+ "step": 192
585
+ },
586
+ {
587
+ "epoch": 1.18,
588
+ "learning_rate": 0.0002702749648162686,
589
+ "loss": 1.9656,
590
+ "step": 194
591
+ },
592
+ {
593
+ "epoch": 1.19,
594
+ "learning_rate": 0.0002678682176313175,
595
+ "loss": 1.9843,
596
+ "step": 196
597
+ },
598
+ {
599
+ "epoch": 1.2,
600
+ "learning_rate": 0.0002654503113746234,
601
+ "loss": 2.0132,
602
+ "step": 198
603
+ },
604
+ {
605
+ "epoch": 1.21,
606
+ "learning_rate": 0.0002630216436047242,
607
+ "loss": 2.0522,
608
+ "step": 200
609
+ },
610
+ {
611
+ "epoch": 1.22,
612
+ "learning_rate": 0.00026058261364959444,
613
+ "loss": 2.0108,
614
+ "step": 202
615
+ },
616
+ {
617
+ "epoch": 1.24,
618
+ "learning_rate": 0.00025813362254098677,
619
+ "loss": 2.0582,
620
+ "step": 204
621
+ },
622
+ {
623
+ "epoch": 1.25,
624
+ "learning_rate": 0.0002556750729484927,
625
+ "loss": 1.9982,
626
+ "step": 206
627
+ },
628
+ {
629
+ "epoch": 1.26,
630
+ "learning_rate": 0.00025320736911333503,
631
+ "loss": 2.0753,
632
+ "step": 208
633
+ },
634
+ {
635
+ "epoch": 1.27,
636
+ "learning_rate": 0.0002507309167819015,
637
+ "loss": 2.04,
638
+ "step": 210
639
+ },
640
+ {
641
+ "epoch": 1.28,
642
+ "learning_rate": 0.00024824612313903053,
643
+ "loss": 1.9574,
644
+ "step": 212
645
+ },
646
+ {
647
+ "epoch": 1.3,
648
+ "learning_rate": 0.0002457533967410611,
649
+ "loss": 2.06,
650
+ "step": 214
651
+ },
652
+ {
653
+ "epoch": 1.31,
654
+ "learning_rate": 0.00024325314744865672,
655
+ "loss": 2.0338,
656
+ "step": 216
657
+ },
658
+ {
659
+ "epoch": 1.32,
660
+ "learning_rate": 0.00024074578635941514,
661
+ "loss": 2.012,
662
+ "step": 218
663
+ },
664
+ {
665
+ "epoch": 1.33,
666
+ "learning_rate": 0.0002382317257402745,
667
+ "loss": 2.0156,
668
+ "step": 220
669
+ },
670
+ {
671
+ "epoch": 1.34,
672
+ "learning_rate": 0.00023571137895972733,
673
+ "loss": 2.0225,
674
+ "step": 222
675
+ },
676
+ {
677
+ "epoch": 1.36,
678
+ "learning_rate": 0.0002331851604198536,
679
+ "loss": 2.0278,
680
+ "step": 224
681
+ },
682
+ {
683
+ "epoch": 1.37,
684
+ "learning_rate": 0.00023065348548818317,
685
+ "loss": 2.1048,
686
+ "step": 226
687
+ },
688
+ {
689
+ "epoch": 1.38,
690
+ "learning_rate": 0.00022811677042940058,
691
+ "loss": 1.9557,
692
+ "step": 228
693
+ }
694
+ ],
695
+ "max_steps": 495,
696
+ "num_train_epochs": 3,
697
+ "total_flos": 1.0784042558129439e+18,
698
+ "trial_name": null,
699
+ "trial_params": null
700
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:081e07496af6787b5dadb5157a5397bd0124fc9f76aba020e5d31ad74e6c8713
3
+ size 3695