pushing from VM

README.md

@@ -0,0 +1,51 @@
+---
+license: bsd-3-clause
+tags:
+- generated_from_trainer
+model-index:
+- name: model-checkpoints
+  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. -->
+
+# model-checkpoints
+
+This model is a fine-tuned version of [pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13](https://huggingface.co/pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13) 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: 0.0006
+- train_batch_size: 4
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 16
+- 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: 0.02
+- num_epochs: 2
+
+### Framework versions
+
+- Transformers 4.22.0
+- Pytorch 1.12.1
+- Datasets 2.4.0
+- Tokenizers 0.12.1

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13",
+  "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": "4.22.0",
+  "use_cache": false,
+  "vocab_size": 32100
+}

long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13-ft1-booksum-VM_training_metadata.json

@@ -0,0 +1 @@
+{"output_dir": "/workspace/model-checkpoints", "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": 4, "per_device_eval_batch_size": 1, "per_gpu_train_batch_size": "None", "per_gpu_eval_batch_size": "None", "gradient_accumulation_steps": 16, "eval_accumulation_steps": "None", "eval_delay": 0, "learning_rate": 0.0006, "weight_decay": 0.01, "adam_beta1": 0.9, "adam_beta2": 0.999, "adam_epsilon": 1e-08, "max_grad_norm": 1, "num_train_epochs": 2, "max_steps": -1, "lr_scheduler_type": "cosine", "warmup_ratio": 0.02, "warmup_steps": 0, "log_level": -1, "log_level_replica": -1, "log_on_each_node": true, "logging_dir": "/workspace/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": false, "fp16": false, "fp16_opt_level": "O1", "half_precision_backend": "auto", "bf16_full_eval": false, "fp16_full_eval": false, "tf32": true, "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": "/workspace/model-checkpoints", "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', 'wandb']", "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": false, "resume_from_checkpoint": "None", "hub_model_id": "long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13-ft1-booksum-VM", "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": 4, "eval_batch_size": 1, "configs_src": "long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13-ft1-booksum-VM", "use_adam8bit": false, "use_adan_optim": false, "dataset_input_length": 16384, "optim_params": "(None, None)", "decay_rate_ada": -0.8}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f66fc5e25ca844cd44f50606b398a1ce349b29744d90c1e5e2a12e192382418
+size 3132671411

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 1024
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<pad>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -103,7 +103,7 @@
   ],
   "eos_token": "</s>",
   "extra_ids": 100,
-  "name_or_path": "google/long-t5-tglobal-base",
+  "name_or_path": "pszemraj/long-t5-tglobal-large-pubmed-3k-booksum-16384-WIP13",
   "pad_token": "<pad>",
   "special_tokens_map_file": null,
   "tokenizer_class": "T5Tokenizer",

trainer_state.json

@@ -0,0 +1,988 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9667673716012084,
+  "global_step": 325,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001714285714285714,
+      "loss": 2.3426,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0003428571428571428,
+      "loss": 2.3022,
+      "step": 4
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0005142857142857142,
+      "loss": 2.2919,
+      "step": 6
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0005999858099954059,
+      "loss": 2.254,
+      "step": 8
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0005998722980127753,
+      "loss": 2.3186,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0005996453169994465,
+      "loss": 2.3878,
+      "step": 12
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0005993049528430316,
+      "loss": 2.3118,
+      "step": 14
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005988513343343228,
+      "loss": 2.3463,
+      "step": 16
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00059828463311856,
+      "loss": 2.3265,
+      "step": 18
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005976050636304812,
+      "loss": 2.3153,
+      "step": 20
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0005968128830131823,
+      "loss": 2.2885,
+      "step": 22
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005959083910208167,
+      "loss": 2.3109,
+      "step": 24
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0005948919299051705,
+      "loss": 2.3845,
+      "step": 26
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.000593763884286158,
+      "loss": 2.193,
+      "step": 28
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005925246810062845,
+      "loss": 2.3119,
+      "step": 30
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005911747889691333,
+      "loss": 2.2861,
+      "step": 32
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.000589714718961936,
+      "loss": 2.3374,
+      "step": 34
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005881450234622957,
+      "loss": 2.2921,
+      "step": 36
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005864662964291346,
+      "loss": 2.3176,
+      "step": 38
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005846791730779443,
+      "loss": 2.3021,
+      "step": 40
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005827843296404265,
+      "loss": 2.401,
+      "step": 42
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0005807824831086132,
+      "loss": 2.3131,
+      "step": 44
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.000578674390963562,
+      "loss": 2.3135,
+      "step": 46
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0005764608508887334,
+      "loss": 2.3548,
+      "step": 48
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0005741427004681535,
+      "loss": 2.2768,
+      "step": 50
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0005717208168694799,
+      "loss": 2.3406,
+      "step": 52
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0005691961165120892,
+      "loss": 2.2956,
+      "step": 54
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0005665695547203121,
+      "loss": 2.3519,
+      "step": 56
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0005638421253619467,
+      "loss": 2.2872,
+      "step": 58
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0005610148604721882,
+      "loss": 2.3266,
+      "step": 60
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0005580888298631155,
+      "loss": 2.28,
+      "step": 62
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0005550651407188842,
+      "loss": 2.3256,
+      "step": 64
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0005519449371767772,
+      "loss": 2.261,
+      "step": 66
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.000548729399894274,
+      "loss": 2.3369,
+      "step": 68
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0005454197456022998,
+      "loss": 2.2836,
+      "step": 70
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0005420172266448255,
+      "loss": 2.3457,
+      "step": 72
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0005385231305049919,
+      "loss": 2.3171,
+      "step": 74
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0005349387793179368,
+      "loss": 2.3302,
+      "step": 76
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0005312655293705118,
+      "loss": 2.2234,
+      "step": 78
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0005275047705880744,
+      "loss": 2.3212,
+      "step": 80
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.000523657926008553,
+      "loss": 2.3651,
+      "step": 82
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0005197264512439815,
+      "loss": 2.3028,
+      "step": 84
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0005157118339297094,
+      "loss": 2.3303,
+      "step": 86
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0005116155931614926,
+      "loss": 2.3035,
+      "step": 88
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0005074392789206815,
+      "loss": 2.2973,
+      "step": 90
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0005031844714877223,
+      "loss": 2.333,
+      "step": 92
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0004988527808441915,
+      "loss": 2.318,
+      "step": 94
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0004944458460635947,
+      "loss": 2.3368,
+      "step": 96
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.000489965334691154,
+      "loss": 2.2936,
+      "step": 98
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00048541294211282504,
+      "loss": 2.3529,
+      "step": 100
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0004807903909137769,
+      "loss": 2.3239,
+      "step": 102
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0004760994302265817,
+      "loss": 2.3217,
+      "step": 104
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00047134183506935797,
+      "loss": 2.3422,
+      "step": 106
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0004665194056741195,
+      "loss": 2.2571,
+      "step": 108
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00046163396680558354,
+      "loss": 2.3643,
+      "step": 110
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.000456687367070696,
+      "loss": 2.4112,
+      "step": 112
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00045168147821913443,
+      "loss": 2.4067,
+      "step": 114
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.000446618194435055,
+      "loss": 2.2525,
+      "step": 116
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0004414994316203498,
+      "loss": 2.3874,
+      "step": 118
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00043632712666968643,
+      "loss": 2.3131,
+      "step": 120
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.000431103236737604,
+      "loss": 2.3785,
+      "step": 122
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0004258297384979432,
+      "loss": 2.2967,
+      "step": 124
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0004205086273958908,
+      "loss": 2.2922,
+      "step": 126
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00041514191689292,
+      "loss": 2.2529,
+      "step": 128
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00040973163770491517,
+      "loss": 2.3434,
+      "step": 130
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00040427983703376615,
+      "loss": 2.2736,
+      "step": 132
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.000398788577792726,
+      "loss": 2.3327,
+      "step": 134
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.0003932599378258218,
+      "loss": 2.3188,
+      "step": 136
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.0003876960091216179,
+      "loss": 2.3499,
+      "step": 138
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0003820988970216249,
+      "loss": 2.3068,
+      "step": 140
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 0.0003764707194236576,
+      "loss": 2.3397,
+      "step": 142
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00037081360598044123,
+      "loss": 2.3231,
+      "step": 144
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0003651296972937693,
+      "loss": 2.3411,
+      "step": 146
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.0003594211441045188,
+      "loss": 2.2935,
+      "step": 148
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.0003536901064788292,
+      "loss": 2.3536,
+      "step": 150
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 0.0003479387529907521,
+      "loss": 2.3074,
+      "step": 152
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00034216925990168234,
+      "loss": 2.3337,
+      "step": 154
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00033638381033687924,
+      "loss": 2.2681,
+      "step": 156
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0003305845934593921,
+      "loss": 2.412,
+      "step": 158
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.0003247738036416997,
+      "loss": 2.2969,
+      "step": 160
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.0003189536396353791,
+      "loss": 2.2902,
+      "step": 162
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 0.0003131263037391177,
+      "loss": 2.3273,
+      "step": 164
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0003072940009653828,
+      "loss": 2.8654,
+      "step": 166
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0003014589382060642,
+      "loss": 2.194,
+      "step": 168
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0002956233233974061,
+      "loss": 2.2423,
+      "step": 170
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0002897893646845429,
+      "loss": 2.3222,
+      "step": 172
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00028395926958595737,
+      "loss": 2.1401,
+      "step": 174
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0002781352441581744,
+      "loss": 2.2044,
+      "step": 176
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0002723194921610094,
+      "loss": 2.1597,
+      "step": 178
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00026651421422368434,
+      "loss": 2.2658,
+      "step": 180
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0002607216070121293,
+      "loss": 2.1676,
+      "step": 182
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00025494386239778414,
+      "loss": 2.2419,
+      "step": 184
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0002491831666282127,
+      "loss": 2.1281,
+      "step": 186
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.0002434416994998462,
+      "loss": 2.2088,
+      "step": 188
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00023772163353316837,
+      "loss": 2.2267,
+      "step": 190
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.00023202513315065184,
+      "loss": 2.2146,
+      "step": 192
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.00022635435385776024,
+      "loss": 2.2714,
+      "step": 194
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.0002207114414273241,
+      "loss": 2.2393,
+      "step": 196
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.00021509853108759883,
+      "loss": 2.1523,
+      "step": 198
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.00020951774671431413,
+      "loss": 2.1741,
+      "step": 200
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.00020397120002701684,
+      "loss": 2.1682,
+      "step": 202
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.000198460989790016,
+      "loss": 2.3001,
+      "step": 204
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00019298920101822875,
+      "loss": 2.29,
+      "step": 206
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 0.0001875579041882286,
+      "loss": 2.2567,
+      "step": 208
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.0001821691544547958,
+      "loss": 2.2445,
+      "step": 210
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.000176824990873265,
+      "loss": 2.1725,
+      "step": 212
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 0.00017152743562796427,
+      "loss": 2.2335,
+      "step": 214
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00016627849326703853,
+      "loss": 2.2806,
+      "step": 216
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.00016108014994394682,
+      "loss": 2.241,
+      "step": 218
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00015593437266591854,
+      "loss": 2.235,
+      "step": 220
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00015084310854965552,
+      "loss": 2.1917,
+      "step": 222
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00014580828408456074,
+      "loss": 2.2387,
+      "step": 224
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00014083180440377106,
+      "loss": 2.2408,
+      "step": 226
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00013591555256327198,
+      "loss": 2.2359,
+      "step": 228
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 0.0001310613888293659,
+      "loss": 2.1735,
+      "step": 230
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.00012627114997476352,
+      "loss": 2.2335,
+      "step": 232
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00012154664858356591,
+      "loss": 2.2986,
+      "step": 234
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 0.00011688967236539785,
+      "loss": 2.2063,
+      "step": 236
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011230198347895463,
+      "loss": 2.2019,
+      "step": 238
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001077853178652171,
+      "loss": 2.2321,
+      "step": 240
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00010334138459058639,
+      "loss": 2.2161,
+      "step": 242
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 9.897186520018855e-05,
+      "loss": 2.2123,
+      "step": 244
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 9.46784130815926e-05,
+      "loss": 2.2248,
+      "step": 246
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 9.046265283918349e-05,
+      "loss": 2.2312,
+      "step": 248
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 8.632617967942566e-05,
+      "loss": 2.2357,
+      "step": 250
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 8.227055880725182e-05,
+      "loss": 2.1949,
+      "step": 252
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 7.82973248338023e-05,
+      "loss": 2.1943,
+      "step": 254
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 7.440798119574219e-05,
+      "loss": 2.1259,
+      "step": 256
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 7.060399958637441e-05,
+      "loss": 2.1426,
+      "step": 258
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.688681939876344e-05,
+      "loss": 2.2838,
+      "step": 260
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 6.325784718108195e-05,
+      "loss": 2.1821,
+      "step": 262
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 5.971845610438546e-05,
+      "loss": 2.2078,
+      "step": 264
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 5.626998544301631e-05,
+      "loss": 2.2778,
+      "step": 266
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 5.2913740067834434e-05,
+      "loss": 2.2872,
+      "step": 268
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 4.9650989952465326e-05,
+      "loss": 2.1835,
+      "step": 270
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 4.6482969692753415e-05,
+      "loss": 2.1698,
+      "step": 272
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 4.341087803960204e-05,
+      "loss": 2.256,
+      "step": 274
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 4.0435877445376396e-05,
+      "loss": 2.1821,
+      "step": 276
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 3.7559093624042036e-05,
+      "loss": 2.182,
+      "step": 278
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.4781615125204575e-05,
+      "loss": 2.1865,
+      "step": 280
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 3.210449292221213e-05,
+      "loss": 2.256,
+      "step": 282
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.9528740014476193e-05,
+      "loss": 2.2292,
+      "step": 284
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.7055331044161933e-05,
+      "loss": 2.1894,
+      "step": 286
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.468520192739162e-05,
+      "loss": 2.2869,
+      "step": 288
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.2419249500102832e-05,
+      "loss": 2.2185,
+      "step": 290
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2.0258331178693286e-05,
+      "loss": 2.2471,
+      "step": 292
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.8203264635581994e-05,
+      "loss": 2.1422,
+      "step": 294
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.625482748980961e-05,
+      "loss": 2.1964,
+      "step": 296
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 1.441375701279388e-05,
+      "loss": 2.2073,
+      "step": 298
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.2680749849352745e-05,
+      "loss": 2.2215,
+      "step": 300
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.1056461754100309e-05,
+      "loss": 2.2439,
+      "step": 302
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 9.541507343314714e-06,
+      "loss": 2.1537,
+      "step": 304
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 8.136459862373056e-06,
+      "loss": 2.1494,
+      "step": 306
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 6.841850968840212e-06,
+      "loss": 2.1858,
+      "step": 308
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 5.6581705312944145e-06,
+      "loss": 2.1937,
+      "step": 310
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.585866443965302e-06,
+      "loss": 2.1877,
+      "step": 312
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.62534445725472e-06,
+      "loss": 2.2081,
+      "step": 314
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.7769680242041624e-06,
+      "loss": 2.2323,
+      "step": 316
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2.0410581629676236e-06,
+      "loss": 2.2301,
+      "step": 318
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.417893335340925e-06,
+      "loss": 2.1788,
+      "step": 320
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 9.077093413944358e-07,
+      "loss": 2.166,
+      "step": 322
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.106992302482127e-07,
+      "loss": 2.1464,
+      "step": 324
+    }
+  ],
+  "max_steps": 330,
+  "num_train_epochs": 2,
+  "total_flos": 1.536257738185638e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48738bb2a785f7ae2751245455c22ffc81b78d6b8e5ba427269e73150bca9fb
+size 3567