load model from drive and convert

README.md

@@ -0,0 +1,51 @@
+---
+license: bsd-3-clause
+tags:
+- generated_from_trainer
+model-index:
+- name: long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16-ft3-booksum
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16-ft3-booksum
+
+This model is a fine-tuned version of [pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16](https://huggingface.co/pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16) on the kmfoda/booksum dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 3
+
+### Framework versions
+
+- Transformers 4.23.0.dev0
+- Pytorch 1.10.0+cu113
+- Datasets 2.5.1
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "early_stopping": true,
+  "encoder_attention_type": "transient-global",
+  "encoder_no_repeat_ngram_size": 4,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.8,
+  "local_radius": 127,
+  "max_length": 512,
+  "min_length": 8,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "repetition_penalty": 3.5,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32100
+}

long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16-ft3-booksum_training_metadata.json

@@ -0,0 +1 @@
+{"output_dir": "/content/drive/MyDrive/Programming/hf-trainer/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16-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": 0.0001, "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-WIP16-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-WIP16-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-WIP16-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-WIP16-ft3-booksum", "use_adam8bit": false, "use_adan_optim": true, "optim_params": "(None, None)", "decay_rate_ada": -0.5}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbd6ba19dec290f0c61c1b657b6739a6070f943342b9658a23be0d8a6666fb7
+size 3132671411

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP16",
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,916 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8158640226628895,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4e-05,
+      "loss": 1.9088,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 8e-05,
+      "loss": 1.9287,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.99989723479183e-05,
+      "loss": 1.7736,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.999075138471951e-05,
+      "loss": 1.9095,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.99743108100344e-05,
+      "loss": 1.918,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.994965332706573e-05,
+      "loss": 1.8706,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 9.991678299006205e-05,
+      "loss": 1.9351,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.987570520365104e-05,
+      "loss": 1.8793,
+      "step": 16
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.982642672195092e-05,
+      "loss": 1.8827,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.976895564745991e-05,
+      "loss": 1.8303,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.970330142972401e-05,
+      "loss": 1.8379,
+      "step": 22
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 9.962947486378326e-05,
+      "loss": 1.8987,
+      "step": 24
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.954748808839674e-05,
+      "loss": 1.9518,
+      "step": 26
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 9.945735458404681e-05,
+      "loss": 1.8511,
+      "step": 28
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.935908917072252e-05,
+      "loss": 1.9064,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.925270800548285e-05,
+      "loss": 1.8882,
+      "step": 32
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.91382285798002e-05,
+      "loss": 1.9368,
+      "step": 34
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 9.901566971668437e-05,
+      "loss": 1.8747,
+      "step": 36
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.888505156758759e-05,
+      "loss": 1.9426,
+      "step": 38
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 9.874639560909117e-05,
+      "loss": 1.9316,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.859972463937441e-05,
+      "loss": 1.867,
+      "step": 42
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.844506277446577e-05,
+      "loss": 1.8927,
+      "step": 44
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.828243544427796e-05,
+      "loss": 1.9449,
+      "step": 46
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.811186938842645e-05,
+      "loss": 1.8571,
+      "step": 48
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.793339265183303e-05,
+      "loss": 1.8346,
+      "step": 50
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.774703458011453e-05,
+      "loss": 1.9036,
+      "step": 52
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.8838,
+      "step": 54
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.735079828808107e-05,
+      "loss": 1.959,
+      "step": 56
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.714098521798465e-05,
+      "loss": 1.9376,
+      "step": 58
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 9.692342110248802e-05,
+      "loss": 1.9326,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.669814171405816e-05,
+      "loss": 1.9344,
+      "step": 62
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.64651840937276e-05,
+      "loss": 1.9038,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 9.622458654500409e-05,
+      "loss": 1.9294,
+      "step": 66
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.597638862757255e-05,
+      "loss": 1.847,
+      "step": 68
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 9.572063115079063e-05,
+      "loss": 1.9167,
+      "step": 70
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.545735616697875e-05,
+      "loss": 1.8309,
+      "step": 72
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.518660696450568e-05,
+      "loss": 1.8982,
+      "step": 74
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.490842806067095e-05,
+      "loss": 1.8734,
+      "step": 76
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.46228651943853e-05,
+      "loss": 1.8738,
+      "step": 78
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.432996531865002e-05,
+      "loss": 1.9731,
+      "step": 80
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.40297765928369e-05,
+      "loss": 1.9105,
+      "step": 82
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.372234837476978e-05,
+      "loss": 1.8629,
+      "step": 84
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.340773121260893e-05,
+      "loss": 1.8565,
+      "step": 86
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.308597683653975e-05,
+      "loss": 1.9962,
+      "step": 88
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.275713815026731e-05,
+      "loss": 1.8981,
+      "step": 90
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.242126922231763e-05,
+      "loss": 1.9132,
+      "step": 92
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.207842527714767e-05,
+      "loss": 1.9159,
+      "step": 94
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.172866268606513e-05,
+      "loss": 1.9617,
+      "step": 96
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 9.137203895795983e-05,
+      "loss": 1.8794,
+      "step": 98
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.10086127298478e-05,
+      "loss": 2.0122,
+      "step": 100
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.063844375723014e-05,
+      "loss": 1.8813,
+      "step": 102
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.02615929042678e-05,
+      "loss": 1.9717,
+      "step": 104
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.987812213377424e-05,
+      "loss": 1.9022,
+      "step": 106
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 8.948809449702711e-05,
+      "loss": 1.9205,
+      "step": 108
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.90915741234015e-05,
+      "loss": 1.8173,
+      "step": 110
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 8.868862620982534e-05,
+      "loss": 2.0031,
+      "step": 112
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 8.827931701005974e-05,
+      "loss": 1.9448,
+      "step": 114
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 8.786371382380528e-05,
+      "loss": 1.9093,
+      "step": 116
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 8.744188498563641e-05,
+      "loss": 1.9093,
+      "step": 118
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.701389985376578e-05,
+      "loss": 1.8793,
+      "step": 120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.657982879864007e-05,
+      "loss": 1.9477,
+      "step": 122
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 8.613974319136958e-05,
+      "loss": 1.8808,
+      "step": 124
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 8.569371539199316e-05,
+      "loss": 1.9425,
+      "step": 126
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 8.524181873758059e-05,
+      "loss": 1.8945,
+      "step": 128
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.478412753017433e-05,
+      "loss": 1.9579,
+      "step": 130
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 8.432071702457252e-05,
+      "loss": 1.9224,
+      "step": 132
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 8.385166341595548e-05,
+      "loss": 1.9117,
+      "step": 134
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 8.33770438273574e-05,
+      "loss": 1.9455,
+      "step": 136
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.289693629698564e-05,
+      "loss": 1.8856,
+      "step": 138
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.241141976538943e-05,
+      "loss": 1.915,
+      "step": 140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 8.192057406248028e-05,
+      "loss": 1.9302,
+      "step": 142
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.142447989440618e-05,
+      "loss": 1.8647,
+      "step": 144
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.092321883028158e-05,
+      "loss": 1.8653,
+      "step": 146
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.041687328877567e-05,
+      "loss": 1.9183,
+      "step": 148
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 7.990552652456081e-05,
+      "loss": 1.852,
+      "step": 150
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.9445,
+      "step": 152
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.886816644444098e-05,
+      "loss": 1.8727,
+      "step": 154
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 7.83423236940225e-05,
+      "loss": 1.9182,
+      "step": 156
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.781182082382325e-05,
+      "loss": 1.9708,
+      "step": 158
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.727674506052743e-05,
+      "loss": 1.8826,
+      "step": 160
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.673718438270648e-05,
+      "loss": 1.9755,
+      "step": 162
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 7.619322750635327e-05,
+      "loss": 1.947,
+      "step": 164
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 7.564496387029532e-05,
+      "loss": 2.3347,
+      "step": 166
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 7.509248362148889e-05,
+      "loss": 1.9177,
+      "step": 168
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 7.45358776001969e-05,
+      "loss": 1.8889,
+      "step": 170
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 7.39752373250527e-05,
+      "loss": 1.8581,
+      "step": 172
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 7.34106549780123e-05,
+      "loss": 1.8564,
+      "step": 174
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 7.284222338919758e-05,
+      "loss": 1.8354,
+      "step": 176
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 7.227003602163295e-05,
+      "loss": 1.89,
+      "step": 178
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 7.169418695587791e-05,
+      "loss": 1.9877,
+      "step": 180
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 7.1114770874558e-05,
+      "loss": 1.7948,
+      "step": 182
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 7.05318830467969e-05,
+      "loss": 1.9217,
+      "step": 184
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 6.99456193125521e-05,
+      "loss": 1.7795,
+      "step": 186
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.935607606685642e-05,
+      "loss": 1.9189,
+      "step": 188
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 6.876335024396872e-05,
+      "loss": 1.8445,
+      "step": 190
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 6.816753930143558e-05,
+      "loss": 1.852,
+      "step": 192
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.756874120406714e-05,
+      "loss": 1.8622,
+      "step": 194
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 6.696705440782938e-05,
+      "loss": 1.9092,
+      "step": 196
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 6.636257784365584e-05,
+      "loss": 1.8074,
+      "step": 198
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 6.575541090118105e-05,
+      "loss": 1.8295,
+      "step": 200
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 6.514565341239861e-05,
+      "loss": 1.9595,
+      "step": 202
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 6.453340563524669e-05,
+      "loss": 1.8733,
+      "step": 204
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 6.391876823712317e-05,
+      "loss": 1.8277,
+      "step": 206
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 6.330184227833376e-05,
+      "loss": 1.914,
+      "step": 208
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.268272919547537e-05,
+      "loss": 1.8684,
+      "step": 210
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 6.206153078475763e-05,
+      "loss": 1.9092,
+      "step": 212
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 6.143834918526527e-05,
+      "loss": 1.7996,
+      "step": 214
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 6.081328686216418e-05,
+      "loss": 1.8958,
+      "step": 216
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 6.0186446589853784e-05,
+      "loss": 1.9597,
+      "step": 218
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 5.955793143506863e-05,
+      "loss": 1.9054,
+      "step": 220
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.8927844739931834e-05,
+      "loss": 1.8064,
+      "step": 222
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 5.82962901049634e-05,
+      "loss": 1.9105,
+      "step": 224
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5.766337137204579e-05,
+      "loss": 1.8535,
+      "step": 226
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 5.7029192607350146e-05,
+      "loss": 1.8961,
+      "step": 228
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 5.6393858084225305e-05,
+      "loss": 1.8679,
+      "step": 230
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 5.575747226605298e-05,
+      "loss": 1.8808,
+      "step": 232
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.512013978907157e-05,
+      "loss": 1.8165,
+      "step": 234
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.448196544517168e-05,
+      "loss": 1.849,
+      "step": 236
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 5.384305416466584e-05,
+      "loss": 1.8585,
+      "step": 238
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.320351099903565e-05,
+      "loss": 1.8477,
+      "step": 240
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 5.256344110365896e-05,
+      "loss": 1.84,
+      "step": 242
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 5.192294972051992e-05,
+      "loss": 1.847,
+      "step": 244
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 5.128214216090478e-05,
+      "loss": 1.9149,
+      "step": 246
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 5.064112378808637e-05,
+      "loss": 1.8937,
+      "step": 248
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 5e-05,
+      "loss": 1.8805,
+      "step": 250
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.935887621191364e-05,
+      "loss": 1.862,
+      "step": 252
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.871785783909523e-05,
+      "loss": 1.8958,
+      "step": 254
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 4.807705027948008e-05,
+      "loss": 1.9492,
+      "step": 256
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.743655889634105e-05,
+      "loss": 1.918,
+      "step": 258
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.679648900096436e-05,
+      "loss": 1.9169,
+      "step": 260
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 4.6156945835334184e-05,
+      "loss": 1.8927,
+      "step": 262
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.551803455482833e-05,
+      "loss": 1.9368,
+      "step": 264
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.487986021092844e-05,
+      "loss": 1.9573,
+      "step": 266
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.424252773394704e-05,
+      "loss": 1.9401,
+      "step": 268
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.3606141915774693e-05,
+      "loss": 1.8759,
+      "step": 270
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.297080739264987e-05,
+      "loss": 1.9353,
+      "step": 272
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.23366286279542e-05,
+      "loss": 1.8375,
+      "step": 274
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.1703709895036625e-05,
+      "loss": 1.9202,
+      "step": 276
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.107215526006817e-05,
+      "loss": 1.9248,
+      "step": 278
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 4.04420685649314e-05,
+      "loss": 1.7924,
+      "step": 280
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.981355341014623e-05,
+      "loss": 1.7682,
+      "step": 282
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 3.9186713137835826e-05,
+      "loss": 1.8612,
+      "step": 284
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 3.856165081473474e-05,
+      "loss": 1.8759,
+      "step": 286
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.793846921524237e-05,
+      "loss": 1.875,
+      "step": 288
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.731727080452464e-05,
+      "loss": 1.8429,
+      "step": 290
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.6698157721666246e-05,
+      "loss": 1.907,
+      "step": 292
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 3.608123176287685e-05,
+      "loss": 1.8561,
+      "step": 294
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 3.5466594364753326e-05,
+      "loss": 1.9138,
+      "step": 296
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3.48543465876014e-05,
+      "loss": 1.893,
+      "step": 298
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.424458909881897e-05,
+      "loss": 1.8505,
+      "step": 300
+    }
+  ],
+  "max_steps": 495,
+  "num_train_epochs": 3,
+  "total_flos": 1.4182542633473147e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3ab32065ec72149d7b702b1e4b4f95deadc83116204c2ae6fa43dfadf03d234
+size 3695