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 +1,274 @@
+---
+language: fr
+license: mit
+tags:
+- roberta
+- question-answering
+base_model: almanach/camembertv2-base
+datasets:
+- FQuAD
+metrics:
+- accuracy
+pipeline_tag: text-classification
+library_name: transformers
+model-index:
+- name: almanach/camembertv2-base-fquad
+  results:
+  - task:
+      type: text-classification
+      name: Natural Language Inference
+    dataset:
+      type: FQuAD
+      name: FQuAD
+    metrics:
+    - name: accuracy
+      type: accuracy
+      value: 
+      verified: false
+---
+
+# Model Card for almanach/camembertv2-base-fquad
+
+almanach/camembertv2-base-fquad is a roberta model for question answering. It is trained on the FQuAD dataset for the task of Extractive Question Answering. The model achieves an f1-score of 83.03359 on the FQuAD dataset.
+
+The model is part of the almanach/camembertv2-base family of model finetunes.
+
+## Model Details
+
+### Model Description
+
+- **Developed by:** Wissam Antoun (Phd Student at Almanach, Inria-Paris)
+- **Model type:** roberta
+- **Language(s) (NLP):** French
+- **License:** MIT
+- **Finetuned from model [optional]:** almanach/camembertv2-base
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/WissamAntoun/camemberta
+- **Paper:** https://arxiv.org/abs/2411.08868
+
+## Uses
+
+The model can be used for question answering tasks in French for Extractive Question Answering.
+
+## Bias, Risks, and Limitations
+
+The model may exhibit biases based on the training data. The model may not generalize well to other datasets or tasks. The model may also have limitations in terms of the data it was trained on.
+
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+```python
+from transformers import AutoTokenizer, AutoModelForQuestionAnswering, pipeline
+
+model = AutoModelForQuestionAnswering.from_pretrained("almanach/camembertv2-base-fquad")
+tokenizer = AutoTokenizer.from_pretrained("almanach/camembertv2-base-fquad")
+
+classifier = pipeline("question-answering", model=model, tokenizer=tokenizer)
+
+classifier(question="Quelle est la capitale de la France ?", context="La capitale de la France est Paris.")
+```
+
+
+## Training Details
+
+### Training Data
+
+The model is trained on the FQuAD dataset.
+
+- Dataset Name: FQuAD
+- Dataset Size:
+    - Train: 20731
+    - Dev: 3188
+
+
+### Training Procedure
+
+Model trained with the run_qa.py script from the huggingface repository.
+
+
+
+#### Training Hyperparameters
+
+```yml
+'Unnamed: 0': /scratch/camembertv2/runs/results/fquad/camembertv2-base-bf16-p2-17000/max_seq_length-896-doc_stride-128-max_answer_length-30-gradient_accumulation_steps-4-precision-fp32-learning_rate-5e-06-epochs-6-lr_scheduler-cosine-warmup_steps-0/SEED-25/all_results.json
+accelerator_config: '{''split_batches'': False, ''dispatch_batches'': None, ''even_batches'':
+  True, ''use_seedable_sampler'': True, ''non_blocking'': False, ''gradient_accumulation_kwargs'':
+  None}'
+adafactor: false
+adam_beta1: 0.9
+adam_beta2: 0.999
+adam_epsilon: 1.0e-08
+auto_find_batch_size: false
+base_model: camembertv2
+base_model_name: camembertv2-base-bf16-p2-17000
+batch_eval_metrics: false
+bf16: false
+bf16_full_eval: false
+data_seed: 25.0
+dataloader_drop_last: false
+dataloader_num_workers: 0
+dataloader_persistent_workers: false
+dataloader_pin_memory: true
+dataloader_prefetch_factor: .nan
+ddp_backend: .nan
+ddp_broadcast_buffers: .nan
+ddp_bucket_cap_mb: .nan
+ddp_find_unused_parameters: .nan
+ddp_timeout: 1800
+debug: '[]'
+deepspeed: .nan
+disable_tqdm: false
+dispatch_batches: .nan
+do_eval: true
+do_predict: false
+do_train: true
+epoch: 6.0
+eval_accumulation_steps: 1
+eval_delay: 0
+eval_do_concat_batches: true
+eval_exact_match: 64.77415307402761
+eval_f1: 83.03359134454834
+eval_on_start: false
+eval_runtime: 6.4215
+eval_samples: 3188.0
+eval_samples_per_second: 496.455
+eval_steps: .nan
+eval_steps_per_second: 7.786
+eval_strategy: epoch
+eval_use_gather_object: false
+evaluation_strategy: epoch
+fp16: false
+fp16_backend: auto
+fp16_full_eval: false
+fp16_opt_level: O1
+fsdp: '[]'
+fsdp_config: '{''min_num_params'': 0, ''xla'': False, ''xla_fsdp_v2'': False, ''xla_fsdp_grad_ckpt'':
+  False}'
+fsdp_min_num_params: 0
+fsdp_transformer_layer_cls_to_wrap: .nan
+full_determinism: false
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+gradient_checkpointing_kwargs: .nan
+greater_is_better: true
+group_by_length: false
+half_precision_backend: auto
+hub_always_push: false
+hub_model_id: .nan
+hub_private_repo: false
+hub_strategy: every_save
+hub_token: <HUB_TOKEN>
+ignore_data_skip: false
+include_inputs_for_metrics: false
+include_num_input_tokens_seen: false
+include_tokens_per_second: false
+jit_mode_eval: false
+label_names: .nan
+label_smoothing_factor: 0.0
+learning_rate: 5.0e-06
+length_column_name: length
+load_best_model_at_end: true
+local_rank: 0
+log_level: debug
+log_level_replica: warning
+log_on_each_node: true
+logging_dir: /scratch/camembertv2/runs/results/fquad/camembertv2-base-bf16-p2-17000/max_seq_length-896-doc_stride-128-max_answer_length-30-gradient_accumulation_steps-4-precision-fp32-learning_rate-5e-06-epochs-6-lr_scheduler-cosine-warmup_steps-0/SEED-25/logs
+logging_first_step: false
+logging_nan_inf_filter: true
+logging_steps: 100
+logging_strategy: steps
+lr_scheduler_kwargs: '{}'
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_steps: -1
+metric_for_best_model: exact_match
+mp_parameters: .nan
+name: camembertv2/runs/results/fquad/camembertv2-base-bf16-p2-17000/max_seq_length-896-doc_stride-128-max_answer_length-30-gradient_accumulation_steps-4-precision-fp32-learning_rate-5e-06-epochs-6-lr_scheduler-cosine-warmup_steps-0
+neftune_noise_alpha: .nan
+no_cuda: false
+num_train_epochs: 6.0
+optim: adamw_torch
+optim_args: .nan
+optim_target_modules: .nan
+output_dir: /scratch/camembertv2/runs/results/fquad/camembertv2-base-bf16-p2-17000/max_seq_length-896-doc_stride-128-max_answer_length-30-gradient_accumulation_steps-4-precision-fp32-learning_rate-5e-06-epochs-6-lr_scheduler-cosine-warmup_steps-0/SEED-25
+overwrite_output_dir: false
+past_index: -1
+per_device_eval_batch_size: 64
+per_device_train_batch_size: 8
+per_gpu_eval_batch_size: .nan
+per_gpu_train_batch_size: .nan
+prediction_loss_only: false
+push_to_hub: false
+push_to_hub_model_id: .nan
+push_to_hub_organization: .nan
+push_to_hub_token: <PUSH_TO_HUB_TOKEN>
+ray_scope: last
+remove_unused_columns: true
+report_to: '[''tensorboard'']'
+restore_callback_states_from_checkpoint: false
+resume_from_checkpoint: .nan
+run_name: camembertv2-base-bf16-p2-17000
+save_on_each_node: false
+save_only_model: false
+save_safetensors: true
+save_steps: 500
+save_strategy: epoch
+save_total_limit: .nan
+seed: 25
+skip_memory_metrics: true
+split_batches: .nan
+tf32: .nan
+torch_compile: true
+torch_compile_backend: inductor
+torch_compile_mode: .nan
+torch_empty_cache_steps: .nan
+torchdynamo: .nan
+total_flos: 2.0387348740618656e+16
+tpu_metrics_debug: false
+tpu_num_cores: .nan
+train_loss: 1.9457146935011624
+train_runtime: 824.1497
+train_samples: 20731
+train_samples_per_second: 150.926
+train_steps_per_second: 4.718
+use_cpu: false
+use_ipex: false
+use_legacy_prediction_loop: false
+use_mps_device: false
+warmup_ratio: 0.0
+warmup_steps: 0
+weight_decay: 0.0
+
+```
+
+#### Results
+
+**F1-Score:** 83.03359
+
+## Technical Specifications
+
+### Model Architecture and Objective
+
+roberta for extractive question answering in French.
+
+## Citation
+
+**BibTeX:**
+
+```bibtex
+@misc{antoun2024camembert20smarterfrench,
+      title={CamemBERT 2.0: A Smarter French Language Model Aged to Perfection},
+      author={Wissam Antoun and Francis Kulumba and Rian Touchent and Éric de la Clergerie and Benoît Sagot and Djamé Seddah},
+      year={2024},
+      eprint={2411.08868},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2411.08868},
+}
+```

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 64.77415307402761,
+    "eval_f1": 83.03359134454834,
+    "eval_runtime": 6.4215,
+    "eval_samples": 3188,
+    "eval_samples_per_second": 496.455,
+    "eval_steps_per_second": 7.786,
+    "total_flos": 2.0387348740618656e+16,
+    "train_loss": 1.9457146935011624,
+    "train_runtime": 824.1497,
+    "train_samples": 20731,
+    "train_samples_per_second": 150.926,
+    "train_steps_per_second": 4.718
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/scratch/camembertv2/runs/models/camembertv2-base-bf16/post/ckpt-p2-17000/pt/",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 1025,
+  "model_name": "camembertv2-base-bf16",
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_biased_input": true,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32768
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b6cde6759e30442525bb591dbc94a2b94f99410c2853778d17574cbe2315623
+size 14796790

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "eval_exact_match": 64.77415307402761,
+    "eval_f1": 83.03359134454834,
+    "eval_runtime": 6.4215,
+    "eval_samples": 3188,
+    "eval_samples_per_second": 496.455,
+    "eval_steps_per_second": 7.786
+}

logs/events.out.tfevents.1724462857.nefgpu58.62368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2efbaac8e471dd36b6ed8192a202a71ae7cee547d127889a17c1b6bb3db19f16
+size 15806

logs/events.out.tfevents.1724463694.nefgpu58.62368.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f43fd2d2b012a03545542eb1359bd162af5aa3d8066fbc758172f96d2972ca0
+size 364

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb311090a5188bbd306d56d693e051458e3c510373cd3d3fce17a17a53b4d567
+size 444069240

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "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_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "errors": "replace",
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 6.0,
+    "total_flos": 2.0387348740618656e+16,
+    "train_loss": 1.9457146935011624,
+    "train_runtime": 824.1497,
+    "train_samples": 20731,
+    "train_samples_per_second": 150.926,
+    "train_steps_per_second": 4.718
+}

trainer_state.json

@@ -0,0 +1,362 @@
+{
+  "best_metric": 53.324968632371395,
+  "best_model_checkpoint": "/scratch/camembertv2/runs/results/fquad/camembertv2-base-bf16-p2-17000/max_seq_length-896-doc_stride-128-max_answer_length-30-gradient_accumulation_steps-4-precision-fp32-learning_rate-5e-06-epochs-6-lr_scheduler-cosine-warmup_steps-0/SEED-25/checkpoint-3888",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 3888,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15432098765432098,
+      "grad_norm": 4.547507286071777,
+      "learning_rate": 4.99184317884152e-06,
+      "loss": 5.1604,
+      "step": 100
+    },
+    {
+      "epoch": 0.30864197530864196,
+      "grad_norm": 12.684767723083496,
+      "learning_rate": 4.967425942351207e-06,
+      "loss": 4.0839,
+      "step": 200
+    },
+    {
+      "epoch": 0.46296296296296297,
+      "grad_norm": 14.742673873901367,
+      "learning_rate": 4.926907624154051e-06,
+      "loss": 3.3159,
+      "step": 300
+    },
+    {
+      "epoch": 0.6172839506172839,
+      "grad_norm": 12.705907821655273,
+      "learning_rate": 4.870552624790192e-06,
+      "loss": 2.9494,
+      "step": 400
+    },
+    {
+      "epoch": 0.7716049382716049,
+      "grad_norm": 14.801329612731934,
+      "learning_rate": 4.798728686380588e-06,
+      "loss": 2.7635,
+      "step": 500
+    },
+    {
+      "epoch": 0.9259259259259259,
+      "grad_norm": 17.233285903930664,
+      "learning_rate": 4.711904492941644e-06,
+      "loss": 2.6393,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 38.86449184441656,
+      "eval_f1": 60.0036086905889,
+      "eval_runtime": 6.9307,
+      "eval_samples_per_second": 459.985,
+      "eval_steps_per_second": 7.214,
+      "step": 648
+    },
+    {
+      "epoch": 1.0802469135802468,
+      "grad_norm": 14.701664924621582,
+      "learning_rate": 4.610646612007849e-06,
+      "loss": 2.4089,
+      "step": 700
+    },
+    {
+      "epoch": 1.2345679012345678,
+      "grad_norm": 17.278104782104492,
+      "learning_rate": 4.495615797519732e-06,
+      "loss": 2.3405,
+      "step": 800
+    },
+    {
+      "epoch": 1.3888888888888888,
+      "grad_norm": 11.50146770477295,
+      "learning_rate": 4.367562678102491e-06,
+      "loss": 2.2084,
+      "step": 900
+    },
+    {
+      "epoch": 1.5432098765432098,
+      "grad_norm": 13.203764915466309,
+      "learning_rate": 4.22732285887122e-06,
+      "loss": 2.1694,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6975308641975309,
+      "grad_norm": 21.71219825744629,
+      "learning_rate": 4.075811468725734e-06,
+      "loss": 2.0862,
+      "step": 1100
+    },
+    {
+      "epoch": 1.8518518518518519,
+      "grad_norm": 12.909610748291016,
+      "learning_rate": 3.914017188716347e-06,
+      "loss": 2.0016,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 48.745294855708906,
+      "eval_f1": 70.05708349304844,
+      "eval_runtime": 6.5382,
+      "eval_samples_per_second": 487.593,
+      "eval_steps_per_second": 7.647,
+      "step": 1296
+    },
+    {
+      "epoch": 2.006172839506173,
+      "grad_norm": 16.666929244995117,
+      "learning_rate": 3.7429958004482575e-06,
+      "loss": 1.9412,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1604938271604937,
+      "grad_norm": 10.462796211242676,
+      "learning_rate": 3.5638632966241686e-06,
+      "loss": 1.8009,
+      "step": 1400
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 13.769060134887695,
+      "learning_rate": 3.3777885986819725e-06,
+      "loss": 1.7928,
+      "step": 1500
+    },
+    {
+      "epoch": 2.4691358024691357,
+      "grad_norm": 15.287083625793457,
+      "learning_rate": 3.1859859290482544e-06,
+      "loss": 1.7865,
+      "step": 1600
+    },
+    {
+      "epoch": 2.623456790123457,
+      "grad_norm": 11.451101303100586,
+      "learning_rate": 2.989706887782151e-06,
+      "loss": 1.7489,
+      "step": 1700
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 17.512975692749023,
+      "learning_rate": 2.7902322853130758e-06,
+      "loss": 1.6978,
+      "step": 1800
+    },
+    {
+      "epoch": 2.932098765432099,
+      "grad_norm": 17.15248680114746,
+      "learning_rate": 2.5888637845674276e-06,
+      "loss": 1.6566,
+      "step": 1900
+    },
+    {
+      "epoch": 3.0,
+      "eval_exact_match": 50.47051442910916,
+      "eval_f1": 72.25048266378954,
+      "eval_runtime": 6.5447,
+      "eval_samples_per_second": 487.112,
+      "eval_steps_per_second": 7.64,
+      "step": 1944
+    },
+    {
+      "epoch": 3.0864197530864197,
+      "grad_norm": 11.384383201599121,
+      "learning_rate": 2.3869154070232346e-06,
+      "loss": 1.6309,
+      "step": 2000
+    },
+    {
+      "epoch": 3.240740740740741,
+      "grad_norm": 14.492201805114746,
+      "learning_rate": 2.185704958119594e-06,
+      "loss": 1.5353,
+      "step": 2100
+    },
+    {
+      "epoch": 3.3950617283950617,
+      "grad_norm": 15.613585472106934,
+      "learning_rate": 1.9865454279740452e-06,
+      "loss": 1.5249,
+      "step": 2200
+    },
+    {
+      "epoch": 3.549382716049383,
+      "grad_norm": 12.233988761901855,
+      "learning_rate": 1.7907364235221128e-06,
+      "loss": 1.5499,
+      "step": 2300
+    },
+    {
+      "epoch": 3.7037037037037037,
+      "grad_norm": 11.811338424682617,
+      "learning_rate": 1.5995556879882246e-06,
+      "loss": 1.5159,
+      "step": 2400
+    },
+    {
+      "epoch": 3.8580246913580245,
+      "grad_norm": 18.379695892333984,
+      "learning_rate": 1.414250763027336e-06,
+      "loss": 1.5072,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_exact_match": 53.01129234629862,
+      "eval_f1": 74.3205610049545,
+      "eval_runtime": 6.5679,
+      "eval_samples_per_second": 485.39,
+      "eval_steps_per_second": 7.613,
+      "step": 2592
+    },
+    {
+      "epoch": 4.012345679012346,
+      "grad_norm": 12.669611930847168,
+      "learning_rate": 1.2360308479456027e-06,
+      "loss": 1.5257,
+      "step": 2600
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 13.753548622131348,
+      "learning_rate": 1.0660589091223854e-06,
+      "loss": 1.4296,
+      "step": 2700
+    },
+    {
+      "epoch": 4.320987654320987,
+      "grad_norm": 10.774425506591797,
+      "learning_rate": 9.054440911232348e-07,
+      "loss": 1.4796,
+      "step": 2800
+    },
+    {
+      "epoch": 4.4753086419753085,
+      "grad_norm": 16.21649742126465,
+      "learning_rate": 7.552344790248104e-07,
+      "loss": 1.426,
+      "step": 2900
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 11.01417064666748,
+      "learning_rate": 6.164102591808482e-07,
+      "loss": 1.4245,
+      "step": 3000
+    },
+    {
+      "epoch": 4.783950617283951,
+      "grad_norm": 10.40230941772461,
+      "learning_rate": 4.898773230583353e-07,
+      "loss": 1.4493,
+      "step": 3100
+    },
+    {
+      "epoch": 4.938271604938271,
+      "grad_norm": 10.953381538391113,
+      "learning_rate": 3.7646135588175676e-07,
+      "loss": 1.404,
+      "step": 3200
+    },
+    {
+      "epoch": 5.0,
+      "eval_exact_match": 53.168130489335006,
+      "eval_f1": 74.39491719320372,
+      "eval_runtime": 6.6406,
+      "eval_samples_per_second": 480.08,
+      "eval_steps_per_second": 7.529,
+      "step": 3240
+    },
+    {
+      "epoch": 5.092592592592593,
+      "grad_norm": 13.173111915588379,
+      "learning_rate": 2.7690244865973494e-07,
+      "loss": 1.43,
+      "step": 3300
+    },
+    {
+      "epoch": 5.246913580246914,
+      "grad_norm": 13.998867988586426,
+      "learning_rate": 1.918502687530241e-07,
+      "loss": 1.3968,
+      "step": 3400
+    },
+    {
+      "epoch": 5.401234567901234,
+      "grad_norm": 12.186470985412598,
+      "learning_rate": 1.2185982049813472e-07,
+      "loss": 1.378,
+      "step": 3500
+    },
+    {
+      "epoch": 5.555555555555555,
+      "grad_norm": 16.22747039794922,
+      "learning_rate": 6.738782355044048e-08,
+      "loss": 1.4347,
+      "step": 3600
+    },
+    {
+      "epoch": 5.709876543209877,
+      "grad_norm": 17.75710105895996,
+      "learning_rate": 2.878973257973955e-08,
+      "loss": 1.422,
+      "step": 3700
+    },
+    {
+      "epoch": 5.864197530864198,
+      "grad_norm": 17.476356506347656,
+      "learning_rate": 6.317417766116829e-09,
+      "loss": 1.3868,
+      "step": 3800
+    },
+    {
+      "epoch": 6.0,
+      "eval_exact_match": 53.324968632371395,
+      "eval_f1": 74.54839090269344,
+      "eval_runtime": 6.5292,
+      "eval_samples_per_second": 488.268,
+      "eval_steps_per_second": 7.658,
+      "step": 3888
+    },
+    {
+      "epoch": 6.0,
+      "step": 3888,
+      "total_flos": 2.0387348740618656e+16,
+      "train_loss": 1.9457146935011624,
+      "train_runtime": 824.1497,
+      "train_samples_per_second": 150.926,
+      "train_steps_per_second": 4.718
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 3888,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "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": 2.0387348740618656e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf43bebeeef721ccd0e0d0f58cdae5570d7c7f63c5cd3695b03168815aa747f0
+size 5688