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-310m
+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-310m](https://huggingface.co/sbintuitions/modernbert-ja-310m) 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: 3e-05
+- train_batch_size: 12
+- 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: linear
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### 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": 79.71634398919406,
+    "eval_f1": 79.68257541647907,
+    "eval_runtime": 26.8594,
+    "eval_samples": 4442,
+    "eval_samples_per_second": 165.38,
+    "eval_steps_per_second": 20.7,
+    "total_flos": 4.56805831292375e+16,
+    "train_loss": 0.49690309092388235,
+    "train_runtime": 1658.9592,
+    "train_samples": 62859,
+    "train_samples_per_second": 37.891,
+    "train_steps_per_second": 3.158
+}

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": 768,
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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": 12,
+  "num_hidden_layers": 25,
+  "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:acd81724120a080136278ec6c73d2394ffa089dcbe04d428ea1f32a3ebee839d
+size 23487293

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_exact_match": 79.71634398919406,
+    "eval_f1": 79.68257541647907,
+    "eval_runtime": 26.8594,
+    "eval_samples": 4442,
+    "eval_samples_per_second": 165.38,
+    "eval_steps_per_second": 20.7
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef718ea626b20d83139eb0a16adc6d732cca83edaf855c838e0c9fb973a594e
+size 1260832512

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": 4.56805831292375e+16,
+    "train_loss": 0.49690309092388235,
+    "train_runtime": 1658.9592,
+    "train_samples": 62859,
+    "train_samples_per_second": 37.891,
+    "train_steps_per_second": 3.158
+}

trainer_state.json

@@ -0,0 +1,497 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5239,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01908761213972132,
+      "grad_norm": 24.85356330871582,
+      "learning_rate": 2.9484634472227524e-05,
+      "loss": 2.8924,
+      "step": 100
+    },
+    {
+      "epoch": 0.03817522427944264,
+      "grad_norm": 11.6854829788208,
+      "learning_rate": 2.8912006108035885e-05,
+      "loss": 0.7288,
+      "step": 200
+    },
+    {
+      "epoch": 0.057262836419163965,
+      "grad_norm": 14.07279109954834,
+      "learning_rate": 2.8339377743844245e-05,
+      "loss": 0.6985,
+      "step": 300
+    },
+    {
+      "epoch": 0.07635044855888529,
+      "grad_norm": 12.763427734375,
+      "learning_rate": 2.7766749379652605e-05,
+      "loss": 0.6016,
+      "step": 400
+    },
+    {
+      "epoch": 0.09543806069860661,
+      "grad_norm": 10.65344524383545,
+      "learning_rate": 2.7194121015460965e-05,
+      "loss": 0.5952,
+      "step": 500
+    },
+    {
+      "epoch": 0.09543806069860661,
+      "eval_exact_match": 74.24583520936515,
+      "eval_f1": 74.39195128749384,
+      "eval_runtime": 27.1246,
+      "eval_samples_per_second": 163.763,
+      "eval_steps_per_second": 20.498,
+      "step": 500
+    },
+    {
+      "epoch": 0.11452567283832793,
+      "grad_norm": 24.665790557861328,
+      "learning_rate": 2.6621492651269326e-05,
+      "loss": 0.5502,
+      "step": 600
+    },
+    {
+      "epoch": 0.13361328497804925,
+      "grad_norm": 5.523789405822754,
+      "learning_rate": 2.6048864287077686e-05,
+      "loss": 0.6028,
+      "step": 700
+    },
+    {
+      "epoch": 0.15270089711777057,
+      "grad_norm": 21.62483787536621,
+      "learning_rate": 2.5476235922886046e-05,
+      "loss": 0.5487,
+      "step": 800
+    },
+    {
+      "epoch": 0.1717885092574919,
+      "grad_norm": 3.459503412246704,
+      "learning_rate": 2.4903607558694406e-05,
+      "loss": 0.5442,
+      "step": 900
+    },
+    {
+      "epoch": 0.19087612139721322,
+      "grad_norm": 6.397250652313232,
+      "learning_rate": 2.4330979194502767e-05,
+      "loss": 0.4708,
+      "step": 1000
+    },
+    {
+      "epoch": 0.19087612139721322,
+      "eval_exact_match": 75.73165240882486,
+      "eval_f1": 75.78096524517056,
+      "eval_runtime": 27.0858,
+      "eval_samples_per_second": 163.997,
+      "eval_steps_per_second": 20.527,
+      "step": 1000
+    },
+    {
+      "epoch": 0.20996373353693454,
+      "grad_norm": 5.82578182220459,
+      "learning_rate": 2.3758350830311127e-05,
+      "loss": 0.4403,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22905134567665586,
+      "grad_norm": 55.54654312133789,
+      "learning_rate": 2.3185722466119487e-05,
+      "loss": 0.5175,
+      "step": 1200
+    },
+    {
+      "epoch": 0.24813895781637718,
+      "grad_norm": 3.4721755981445312,
+      "learning_rate": 2.2613094101927848e-05,
+      "loss": 0.4986,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2672265699560985,
+      "grad_norm": 10.456282615661621,
+      "learning_rate": 2.2040465737736208e-05,
+      "loss": 0.5227,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2863141820958198,
+      "grad_norm": 26.73484992980957,
+      "learning_rate": 2.1467837373544568e-05,
+      "loss": 0.4404,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2863141820958198,
+      "eval_exact_match": 75.73165240882486,
+      "eval_f1": 75.79168542698483,
+      "eval_runtime": 27.0984,
+      "eval_samples_per_second": 163.921,
+      "eval_steps_per_second": 20.518,
+      "step": 1500
+    },
+    {
+      "epoch": 0.30540179423554115,
+      "grad_norm": 13.284788131713867,
+      "learning_rate": 2.089520900935293e-05,
+      "loss": 0.4939,
+      "step": 1600
+    },
+    {
+      "epoch": 0.32448940637526247,
+      "grad_norm": 1.5096017122268677,
+      "learning_rate": 2.032258064516129e-05,
+      "loss": 0.4657,
+      "step": 1700
+    },
+    {
+      "epoch": 0.3435770185149838,
+      "grad_norm": 10.362142562866211,
+      "learning_rate": 1.974995228096965e-05,
+      "loss": 0.4559,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3626646306547051,
+      "grad_norm": 12.559228897094727,
+      "learning_rate": 1.917732391677801e-05,
+      "loss": 0.4998,
+      "step": 1900
+    },
+    {
+      "epoch": 0.38175224279442643,
+      "grad_norm": 8.283560752868652,
+      "learning_rate": 1.860469555258637e-05,
+      "loss": 0.4603,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38175224279442643,
+      "eval_exact_match": 77.73525438991446,
+      "eval_f1": 77.81083167170515,
+      "eval_runtime": 27.123,
+      "eval_samples_per_second": 163.772,
+      "eval_steps_per_second": 20.499,
+      "step": 2000
+    },
+    {
+      "epoch": 0.40083985493414775,
+      "grad_norm": 5.818004131317139,
+      "learning_rate": 1.803206718839473e-05,
+      "loss": 0.4361,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4199274670738691,
+      "grad_norm": 14.656002044677734,
+      "learning_rate": 1.745943882420309e-05,
+      "loss": 0.467,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4390150792135904,
+      "grad_norm": 8.953429222106934,
+      "learning_rate": 1.688681046001145e-05,
+      "loss": 0.3691,
+      "step": 2300
+    },
+    {
+      "epoch": 0.4581026913533117,
+      "grad_norm": 9.16756820678711,
+      "learning_rate": 1.631418209581981e-05,
+      "loss": 0.4318,
+      "step": 2400
+    },
+    {
+      "epoch": 0.47719030349303304,
+      "grad_norm": 12.255992889404297,
+      "learning_rate": 1.574155373162817e-05,
+      "loss": 0.4323,
+      "step": 2500
+    },
+    {
+      "epoch": 0.47719030349303304,
+      "eval_exact_match": 78.09545249887438,
+      "eval_f1": 78.14723097703737,
+      "eval_runtime": 27.2895,
+      "eval_samples_per_second": 162.773,
+      "eval_steps_per_second": 20.374,
+      "step": 2500
+    },
+    {
+      "epoch": 0.49627791563275436,
+      "grad_norm": 15.877165794372559,
+      "learning_rate": 1.5168925367436533e-05,
+      "loss": 0.392,
+      "step": 2600
+    },
+    {
+      "epoch": 0.5153655277724757,
+      "grad_norm": 18.496259689331055,
+      "learning_rate": 1.4596297003244895e-05,
+      "loss": 0.4044,
+      "step": 2700
+    },
+    {
+      "epoch": 0.534453139912197,
+      "grad_norm": 12.297314643859863,
+      "learning_rate": 1.4023668639053255e-05,
+      "loss": 0.4233,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5535407520519183,
+      "grad_norm": 4.0507049560546875,
+      "learning_rate": 1.3451040274861615e-05,
+      "loss": 0.4213,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5726283641916396,
+      "grad_norm": 6.028878211975098,
+      "learning_rate": 1.2878411910669976e-05,
+      "loss": 0.4129,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5726283641916396,
+      "eval_exact_match": 78.77082395317424,
+      "eval_f1": 78.77832808044424,
+      "eval_runtime": 27.3136,
+      "eval_samples_per_second": 162.629,
+      "eval_steps_per_second": 20.356,
+      "step": 3000
+    },
+    {
+      "epoch": 0.591715976331361,
+      "grad_norm": 2.101097583770752,
+      "learning_rate": 1.2305783546478336e-05,
+      "loss": 0.386,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6108035884710823,
+      "grad_norm": 26.336244583129883,
+      "learning_rate": 1.1733155182286696e-05,
+      "loss": 0.4582,
+      "step": 3200
+    },
+    {
+      "epoch": 0.6298912006108036,
+      "grad_norm": 1.0698107481002808,
+      "learning_rate": 1.1160526818095056e-05,
+      "loss": 0.3729,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6489788127505249,
+      "grad_norm": 24.801355361938477,
+      "learning_rate": 1.0587898453903417e-05,
+      "loss": 0.3804,
+      "step": 3400
+    },
+    {
+      "epoch": 0.6680664248902463,
+      "grad_norm": 27.99701690673828,
+      "learning_rate": 1.0015270089711777e-05,
+      "loss": 0.4083,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6680664248902463,
+      "eval_exact_match": 78.18550202611436,
+      "eval_f1": 78.18325078793336,
+      "eval_runtime": 26.9164,
+      "eval_samples_per_second": 165.03,
+      "eval_steps_per_second": 20.657,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6871540370299676,
+      "grad_norm": 1.1666632890701294,
+      "learning_rate": 9.442641725520137e-06,
+      "loss": 0.3877,
+      "step": 3600
+    },
+    {
+      "epoch": 0.7062416491696889,
+      "grad_norm": 15.128180503845215,
+      "learning_rate": 8.870013361328497e-06,
+      "loss": 0.4168,
+      "step": 3700
+    },
+    {
+      "epoch": 0.7253292613094102,
+      "grad_norm": 22.817325592041016,
+      "learning_rate": 8.297384997136858e-06,
+      "loss": 0.4292,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7444168734491315,
+      "grad_norm": 11.064777374267578,
+      "learning_rate": 7.724756632945218e-06,
+      "loss": 0.4225,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7635044855888529,
+      "grad_norm": 6.2987060546875,
+      "learning_rate": 7.152128268753579e-06,
+      "loss": 0.39,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7635044855888529,
+      "eval_exact_match": 78.95092300765421,
+      "eval_f1": 78.91715443493922,
+      "eval_runtime": 26.9864,
+      "eval_samples_per_second": 164.602,
+      "eval_steps_per_second": 20.603,
+      "step": 4000
+    },
+    {
+      "epoch": 0.7825920977285742,
+      "grad_norm": 13.171396255493164,
+      "learning_rate": 6.579499904561939e-06,
+      "loss": 0.4579,
+      "step": 4100
+    },
+    {
+      "epoch": 0.8016797098682955,
+      "grad_norm": 5.967886924743652,
+      "learning_rate": 6.0068715403703e-06,
+      "loss": 0.3918,
+      "step": 4200
+    },
+    {
+      "epoch": 0.8207673220080168,
+      "grad_norm": 15.37869930267334,
+      "learning_rate": 5.43424317617866e-06,
+      "loss": 0.3938,
+      "step": 4300
+    },
+    {
+      "epoch": 0.8398549341477382,
+      "grad_norm": 14.545265197753906,
+      "learning_rate": 4.86161481198702e-06,
+      "loss": 0.3823,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8589425462874595,
+      "grad_norm": 22.79754638671875,
+      "learning_rate": 4.2889864477953805e-06,
+      "loss": 0.3429,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8589425462874595,
+      "eval_exact_match": 79.19855920756416,
+      "eval_f1": 79.16479063484917,
+      "eval_runtime": 26.9798,
+      "eval_samples_per_second": 164.642,
+      "eval_steps_per_second": 20.608,
+      "step": 4500
+    },
+    {
+      "epoch": 0.8780301584271808,
+      "grad_norm": 19.819913864135742,
+      "learning_rate": 3.716358083603741e-06,
+      "loss": 0.3482,
+      "step": 4600
+    },
+    {
+      "epoch": 0.8971177705669021,
+      "grad_norm": 14.867344856262207,
+      "learning_rate": 3.1437297194121014e-06,
+      "loss": 0.3886,
+      "step": 4700
+    },
+    {
+      "epoch": 0.9162053827066234,
+      "grad_norm": 5.279645919799805,
+      "learning_rate": 2.571101355220462e-06,
+      "loss": 0.3932,
+      "step": 4800
+    },
+    {
+      "epoch": 0.9352929948463448,
+      "grad_norm": 17.6607666015625,
+      "learning_rate": 1.9984729910288224e-06,
+      "loss": 0.369,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9543806069860661,
+      "grad_norm": 29.288660049438477,
+      "learning_rate": 1.4258446268371827e-06,
+      "loss": 0.3289,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9543806069860661,
+      "eval_exact_match": 79.73885637100405,
+      "eval_f1": 79.70508779828906,
+      "eval_runtime": 26.9148,
+      "eval_samples_per_second": 165.039,
+      "eval_steps_per_second": 20.658,
+      "step": 5000
+    },
+    {
+      "epoch": 0.9734682191257874,
+      "grad_norm": 18.447587966918945,
+      "learning_rate": 8.53216262645543e-07,
+      "loss": 0.4057,
+      "step": 5100
+    },
+    {
+      "epoch": 0.9925558312655087,
+      "grad_norm": 4.9967122077941895,
+      "learning_rate": 2.8058789845390346e-07,
+      "loss": 0.3995,
+      "step": 5200
+    },
+    {
+      "epoch": 1.0,
+      "step": 5239,
+      "total_flos": 4.56805831292375e+16,
+      "train_loss": 0.49690309092388235,
+      "train_runtime": 1658.9592,
+      "train_samples_per_second": 37.891,
+      "train_steps_per_second": 3.158
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5239,
+  "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": 4.56805831292375e+16,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc5128ecc3140315ba84032188042b886b7fc23bff7da40e11d81da4073f02fe
+size 5713