Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+license: mit
+base_model: sbintuitions/modernbert-ja-130m
+tags:
+- generated_from_trainer
+datasets:
+- sbintuitions/JSQuAD
+model-index:
+- name: output
+  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. -->
+
+# output
+
+This model is a fine-tuned version of [sbintuitions/modernbert-ja-130m](https://huggingface.co/sbintuitions/modernbert-ja-130m) on the sbintuitions/JSQuAD 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: 4e-05
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.10.0.dev20251211+cu128
+- Datasets 4.4.1
+- Tokenizers 0.21.4

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_exact_match": 78.18550202611436,
+    "eval_f1": 78.18174996247937,
+    "eval_runtime": 17.0033,
+    "eval_samples": 4442,
+    "eval_samples_per_second": 261.243,
+    "eval_steps_per_second": 32.7,
+    "total_flos": 1.5443482530613248e+16,
+    "train_loss": 0.7458447315335486,
+    "train_runtime": 559.0145,
+    "train_samples": 62859,
+    "train_samples_per_second": 112.446,
+    "train_steps_per_second": 7.028
+}

checkpoint-3929/config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertForQuestionAnswering"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 6,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 2,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 512,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 19,
+  "pad_token_id": 3,
+  "position_embedding_type": "rope",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 4,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "vocab_size": 102400
+}

checkpoint-3929/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1587b8f3ea216ccc36bda5c1d26208fb680c1f1dea9158799c00ab4bbb33ae
+size 529629216

checkpoint-3929/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9273ab4a52df1b6bc1254bd4fae177df32c40e5bceb6f68c421771ba17a6341
+size 1059335371

checkpoint-3929/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dee670dbbb7f9ae79334dd2a96a883c819ee2429d4cad998dcb558b1b2923cb8
+size 14645

checkpoint-3929/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6def77edef7f497c671d8890a07030f546840c8b9df25bc885d9d8e8e54bbda
+size 1465

checkpoint-3929/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<sep>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-3929/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
+size 1831879

checkpoint-3929/tokenizer_config.json

@@ -0,0 +1,171 @@
+{
+  "add_bos_token": true,
+  "add_dummy_prefix_space": false,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<|available_tools|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<|tool_calls|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<|tool_results|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<|code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<|file|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102397": {
+      "content": "<|prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102398": {
+      "content": "<|suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102399": {
+      "content": "<|middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": {},
+  "keep_accents": true,
+  "legacy": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-3929/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3929,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12725884448969205,
+      "grad_norm": 37.20204162597656,
+      "learning_rate": 3.9911373020040744e-05,
+      "loss": 2.3857,
+      "step": 500
+    },
+    {
+      "epoch": 0.2545176889793841,
+      "grad_norm": 39.65735626220703,
+      "learning_rate": 3.717053803934548e-05,
+      "loss": 0.6773,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3817765334690761,
+      "grad_norm": 24.23069953918457,
+      "learning_rate": 3.1096625736016396e-05,
+      "loss": 0.5841,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5090353779587682,
+      "grad_norm": 33.852108001708984,
+      "learning_rate": 2.286868008127341e-05,
+      "loss": 0.5041,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6362942224484601,
+      "grad_norm": 6.397488117218018,
+      "learning_rate": 1.4083877529974594e-05,
+      "loss": 0.4732,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7635530669381522,
+      "grad_norm": 9.303166389465332,
+      "learning_rate": 6.447489407948826e-06,
+      "loss": 0.4418,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8908119114278442,
+      "grad_norm": 11.69579792022705,
+      "learning_rate": 1.4418613480487786e-06,
+      "loss": 0.4325,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 78.18550202611436,
+      "eval_f1": 78.18174996247937,
+      "eval_runtime": 17.1279,
+      "eval_samples_per_second": 259.343,
+      "eval_steps_per_second": 32.462,
+      "step": 3929
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3929,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5443482530613248e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3929/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8dab68bdd4c2a1c4cfe14d5b55fcfc0f2fa782a12fb4f9b0f8bfb657969647
+size 5713

config.json

@@ -0,0 +1,45 @@
+{
+  "architectures": [
+    "ModernBertForQuestionAnswering"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 6,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 2,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 512,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 19,
+  "pad_token_id": 3,
+  "position_embedding_type": "rope",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 4,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.52.4",
+  "vocab_size": 102400
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:617513d0301f4038d28e706a47204cd6ea92cd0e80712b3762296f36d66d08bc
+size 22725399

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_exact_match": 78.18550202611436,
+    "eval_f1": 78.18174996247937,
+    "eval_runtime": 17.0033,
+    "eval_samples": 4442,
+    "eval_samples_per_second": 261.243,
+    "eval_steps_per_second": 32.7
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be1587b8f3ea216ccc36bda5c1d26208fb680c1f1dea9158799c00ab4bbb33ae
+size 529629216

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<cls>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<sep>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008293028e1a9d9a1038d9b63d989a2319797dfeaa03f171093a57b33a3a8277
+size 1831879

tokenizer_config.json

@@ -0,0 +1,171 @@
+{
+  "add_bos_token": true,
+  "add_dummy_prefix_space": false,
+  "add_eos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<|available_tools|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<|tool_calls|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<|tool_results|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<|code|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<|file|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102397": {
+      "content": "<|prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102398": {
+      "content": "<|suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102399": {
+      "content": "<|middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<cls>",
+  "do_lower_case": false,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "extra_special_tokens": {},
+  "keep_accents": true,
+  "legacy": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "<sep>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.5443482530613248e+16,
+    "train_loss": 0.7458447315335486,
+    "train_runtime": 559.0145,
+    "train_samples": 62859,
+    "train_samples_per_second": 112.446,
+    "train_steps_per_second": 7.028
+}

trainer_state.json

@@ -0,0 +1,101 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3929,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12725884448969205,
+      "grad_norm": 37.20204162597656,
+      "learning_rate": 3.9911373020040744e-05,
+      "loss": 2.3857,
+      "step": 500
+    },
+    {
+      "epoch": 0.2545176889793841,
+      "grad_norm": 39.65735626220703,
+      "learning_rate": 3.717053803934548e-05,
+      "loss": 0.6773,
+      "step": 1000
+    },
+    {
+      "epoch": 0.3817765334690761,
+      "grad_norm": 24.23069953918457,
+      "learning_rate": 3.1096625736016396e-05,
+      "loss": 0.5841,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5090353779587682,
+      "grad_norm": 33.852108001708984,
+      "learning_rate": 2.286868008127341e-05,
+      "loss": 0.5041,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6362942224484601,
+      "grad_norm": 6.397488117218018,
+      "learning_rate": 1.4083877529974594e-05,
+      "loss": 0.4732,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7635530669381522,
+      "grad_norm": 9.303166389465332,
+      "learning_rate": 6.447489407948826e-06,
+      "loss": 0.4418,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8908119114278442,
+      "grad_norm": 11.69579792022705,
+      "learning_rate": 1.4418613480487786e-06,
+      "loss": 0.4325,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 78.18550202611436,
+      "eval_f1": 78.18174996247937,
+      "eval_runtime": 17.1279,
+      "eval_samples_per_second": 259.343,
+      "eval_steps_per_second": 32.462,
+      "step": 3929
+    },
+    {
+      "epoch": 1.0,
+      "step": 3929,
+      "total_flos": 1.5443482530613248e+16,
+      "train_loss": 0.7458447315335486,
+      "train_runtime": 559.0145,
+      "train_samples_per_second": 112.446,
+      "train_steps_per_second": 7.028
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3929,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5443482530613248e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b8dab68bdd4c2a1c4cfe14d5b55fcfc0f2fa782a12fb4f9b0f8bfb657969647
+size 5713