init push

README.md

@@ -0,0 +1,69 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
+model-index:
+- name: sft_trained_woaqa_mixtral
+  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. -->
+
+# sft_trained_woaqa_mixtral
+
+This model is a fine-tuned version of [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1) on the sft_wo_aqa_mistral dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8062
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 4.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8668        | 0.63  | 100  | 0.8571          |
+| 0.7837        | 1.26  | 200  | 0.8230          |
+| 0.7824        | 1.9   | 300  | 0.8058          |
+| 0.7401        | 2.53  | 400  | 0.8059          |
+| 0.7101        | 3.16  | 500  | 0.8072          |
+| 0.7037        | 3.79  | 600  | 0.8062          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w3",
+    "w1",
+    "w2",
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "gate",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95394e419230e4e32bc7a3243d358ebc852aaf01d6f99d31e9fe116b41372fe9
+size 484722304

all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 3.99,
+    "eval_loss": 0.8061766028404236,
+    "eval_runtime": 867.2475,
+    "eval_samples_per_second": 3.195,
+    "eval_steps_per_second": 0.4,
+    "train_loss": 0.7920433780815028,
+    "train_runtime": 47185.3474,
+    "train_samples_per_second": 0.858,
+    "train_steps_per_second": 0.013
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.99,
+    "eval_loss": 0.8061766028404236,
+    "eval_runtime": 867.2475,
+    "eval_samples_per_second": 3.195,
+    "eval_steps_per_second": 0.4
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": 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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{{ '<s>' + system_message }}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ ' [INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.99,
+    "train_loss": 0.7920433780815028,
+    "train_runtime": 47185.3474,
+    "train_samples_per_second": 0.858,
+    "train_steps_per_second": 0.013
+}

trainer_log.jsonl

@@ -0,0 +1,38 @@
+{"current_steps": 20, "total_steps": 632, "loss": 1.3016, "learning_rate": 4.9876553763060684e-05, "epoch": 0.13, "percentage": 3.16, "elapsed_time": "0:22:10", "remaining_time": "11:18:44"}
+{"current_steps": 40, "total_steps": 632, "loss": 0.9953, "learning_rate": 4.950743417011591e-05, "epoch": 0.25, "percentage": 6.33, "elapsed_time": "0:44:06", "remaining_time": "10:52:50"}
+{"current_steps": 60, "total_steps": 632, "loss": 0.925, "learning_rate": 4.889628653514402e-05, "epoch": 0.38, "percentage": 9.49, "elapsed_time": "1:09:28", "remaining_time": "11:02:22"}
+{"current_steps": 80, "total_steps": 632, "loss": 0.8788, "learning_rate": 4.804914636820517e-05, "epoch": 0.51, "percentage": 12.66, "elapsed_time": "1:31:29", "remaining_time": "10:31:14"}
+{"current_steps": 100, "total_steps": 632, "loss": 0.8668, "learning_rate": 4.6974379770560846e-05, "epoch": 0.63, "percentage": 15.82, "elapsed_time": "1:53:23", "remaining_time": "10:03:12"}
+{"current_steps": 100, "total_steps": 632, "eval_loss": 0.8571113348007202, "epoch": 0.63, "percentage": 15.82, "elapsed_time": "2:07:51", "remaining_time": "11:20:11"}
+{"current_steps": 120, "total_steps": 632, "loss": 0.8488, "learning_rate": 4.5682600813576435e-05, "epoch": 0.76, "percentage": 18.99, "elapsed_time": "2:29:50", "remaining_time": "10:39:21"}
+{"current_steps": 140, "total_steps": 632, "loss": 0.8462, "learning_rate": 4.41865667173477e-05, "epoch": 0.88, "percentage": 22.15, "elapsed_time": "2:51:49", "remaining_time": "10:03:51"}
+{"current_steps": 160, "total_steps": 632, "loss": 0.827, "learning_rate": 4.2501051864235636e-05, "epoch": 1.01, "percentage": 25.32, "elapsed_time": "3:14:53", "remaining_time": "9:34:54"}
+{"current_steps": 180, "total_steps": 632, "loss": 0.7885, "learning_rate": 4.0642701891514e-05, "epoch": 1.14, "percentage": 28.48, "elapsed_time": "3:37:46", "remaining_time": "9:06:50"}
+{"current_steps": 200, "total_steps": 632, "loss": 0.7837, "learning_rate": 3.862986930406669e-05, "epoch": 1.26, "percentage": 31.65, "elapsed_time": "3:59:48", "remaining_time": "8:37:58"}
+{"current_steps": 200, "total_steps": 632, "eval_loss": 0.8230095505714417, "epoch": 1.26, "percentage": 31.65, "elapsed_time": "4:14:17", "remaining_time": "9:09:16"}
+{"current_steps": 220, "total_steps": 632, "loss": 0.7938, "learning_rate": 3.6482432230574446e-05, "epoch": 1.39, "percentage": 34.81, "elapsed_time": "4:36:16", "remaining_time": "8:37:23"}
+{"current_steps": 240, "total_steps": 632, "loss": 0.7819, "learning_rate": 3.4221598113100195e-05, "epoch": 1.52, "percentage": 37.97, "elapsed_time": "4:58:13", "remaining_time": "8:07:06"}
+{"current_steps": 260, "total_steps": 632, "loss": 0.7877, "learning_rate": 3.186969426877563e-05, "epoch": 1.64, "percentage": 41.14, "elapsed_time": "5:20:11", "remaining_time": "7:38:07"}
+{"current_steps": 280, "total_steps": 632, "loss": 0.7918, "learning_rate": 2.9449947391938766e-05, "epoch": 1.77, "percentage": 44.3, "elapsed_time": "5:42:00", "remaining_time": "7:09:57"}
+{"current_steps": 300, "total_steps": 632, "loss": 0.7824, "learning_rate": 2.6986254174292862e-05, "epoch": 1.9, "percentage": 47.47, "elapsed_time": "6:04:00", "remaining_time": "6:42:49"}
+{"current_steps": 300, "total_steps": 632, "eval_loss": 0.8058096766471863, "epoch": 1.9, "percentage": 47.47, "elapsed_time": "6:18:27", "remaining_time": "6:58:50"}
+{"current_steps": 320, "total_steps": 632, "loss": 0.7741, "learning_rate": 2.4502945308373246e-05, "epoch": 2.02, "percentage": 50.63, "elapsed_time": "6:40:24", "remaining_time": "6:30:24"}
+{"current_steps": 340, "total_steps": 632, "loss": 0.7369, "learning_rate": 2.2024545204952383e-05, "epoch": 2.15, "percentage": 53.8, "elapsed_time": "7:02:25", "remaining_time": "6:02:47"}
+{"current_steps": 360, "total_steps": 632, "loss": 0.7365, "learning_rate": 1.957552979734205e-05, "epoch": 2.27, "percentage": 56.96, "elapsed_time": "7:24:19", "remaining_time": "5:35:42"}
+{"current_steps": 380, "total_steps": 632, "loss": 0.7463, "learning_rate": 1.7180084824444325e-05, "epoch": 2.4, "percentage": 60.13, "elapsed_time": "7:46:14", "remaining_time": "5:09:11"}
+{"current_steps": 400, "total_steps": 632, "loss": 0.7401, "learning_rate": 1.4861866979675154e-05, "epoch": 2.53, "percentage": 63.29, "elapsed_time": "8:08:15", "remaining_time": "4:43:11"}
+{"current_steps": 400, "total_steps": 632, "eval_loss": 0.8059037923812866, "epoch": 2.53, "percentage": 63.29, "elapsed_time": "8:22:49", "remaining_time": "4:51:38"}
+{"current_steps": 420, "total_steps": 632, "loss": 0.7332, "learning_rate": 1.2643770284581929e-05, "epoch": 2.65, "percentage": 66.46, "elapsed_time": "8:44:49", "remaining_time": "4:24:54"}
+{"current_steps": 440, "total_steps": 632, "loss": 0.7364, "learning_rate": 1.0547699994378787e-05, "epoch": 2.78, "percentage": 69.62, "elapsed_time": "9:06:48", "remaining_time": "3:58:36"}
+{"current_steps": 460, "total_steps": 632, "loss": 0.7318, "learning_rate": 8.594356268240616e-06, "epoch": 2.91, "percentage": 72.78, "elapsed_time": "9:28:46", "remaining_time": "3:32:40"}
+{"current_steps": 480, "total_steps": 632, "loss": 0.7222, "learning_rate": 6.803029740762648e-06, "epoch": 3.03, "percentage": 75.95, "elapsed_time": "9:50:39", "remaining_time": "3:07:02"}
+{"current_steps": 500, "total_steps": 632, "loss": 0.7101, "learning_rate": 5.191411013460645e-06, "epoch": 3.16, "percentage": 79.11, "elapsed_time": "10:12:38", "remaining_time": "2:41:44"}
+{"current_steps": 500, "total_steps": 632, "eval_loss": 0.807178795337677, "epoch": 3.16, "percentage": 79.11, "elapsed_time": "10:27:05", "remaining_time": "2:45:33"}
+{"current_steps": 520, "total_steps": 632, "loss": 0.7135, "learning_rate": 3.775415947715899e-06, "epoch": 3.29, "percentage": 82.28, "elapsed_time": "10:49:03", "remaining_time": "2:19:47"}
+{"current_steps": 540, "total_steps": 632, "loss": 0.7045, "learning_rate": 2.5690284845196923e-06, "epoch": 3.41, "percentage": 85.44, "elapsed_time": "11:10:58", "remaining_time": "1:54:18"}
+{"current_steps": 560, "total_steps": 632, "loss": 0.7057, "learning_rate": 1.5841625432818057e-06, "epoch": 3.54, "percentage": 88.61, "elapsed_time": "11:32:56", "remaining_time": "1:29:05"}
+{"current_steps": 580, "total_steps": 632, "loss": 0.7044, "learning_rate": 8.305443635490711e-07, "epoch": 3.67, "percentage": 91.77, "elapsed_time": "11:54:45", "remaining_time": "1:04:04"}
+{"current_steps": 600, "total_steps": 632, "loss": 0.7037, "learning_rate": 3.1561645159166597e-07, "epoch": 3.79, "percentage": 94.94, "elapsed_time": "12:16:39", "remaining_time": "0:39:17"}
+{"current_steps": 600, "total_steps": 632, "eval_loss": 0.8061766028404236, "epoch": 3.79, "percentage": 94.94, "elapsed_time": "12:31:07", "remaining_time": "0:40:03"}
+{"current_steps": 620, "total_steps": 632, "loss": 0.7027, "learning_rate": 4.4464080451675494e-08, "epoch": 3.92, "percentage": 98.1, "elapsed_time": "12:53:10", "remaining_time": "0:14:57"}
+{"current_steps": 632, "total_steps": 632, "epoch": 3.99, "percentage": 100.0, "elapsed_time": "13:06:25", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,295 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.993680884676145,
+  "eval_steps": 100,
+  "global_step": 632,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.37133172154426575,
+      "learning_rate": 4.9876553763060684e-05,
+      "loss": 1.3016,
+      "step": 20
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.3215538263320923,
+      "learning_rate": 4.950743417011591e-05,
+      "loss": 0.9953,
+      "step": 40
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.33872345089912415,
+      "learning_rate": 4.889628653514402e-05,
+      "loss": 0.925,
+      "step": 60
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.3175918459892273,
+      "learning_rate": 4.804914636820517e-05,
+      "loss": 0.8788,
+      "step": 80
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.3202904164791107,
+      "learning_rate": 4.6974379770560846e-05,
+      "loss": 0.8668,
+      "step": 100
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.8571113348007202,
+      "eval_runtime": 868.2347,
+      "eval_samples_per_second": 3.192,
+      "eval_steps_per_second": 0.4,
+      "step": 100
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.33093100786209106,
+      "learning_rate": 4.5682600813576435e-05,
+      "loss": 0.8488,
+      "step": 120
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3297623097896576,
+      "learning_rate": 4.41865667173477e-05,
+      "loss": 0.8462,
+      "step": 140
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.3524036705493927,
+      "learning_rate": 4.2501051864235636e-05,
+      "loss": 0.827,
+      "step": 160
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.3592537045478821,
+      "learning_rate": 4.0642701891514e-05,
+      "loss": 0.7885,
+      "step": 180
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.3888987600803375,
+      "learning_rate": 3.862986930406669e-05,
+      "loss": 0.7837,
+      "step": 200
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.8230095505714417,
+      "eval_runtime": 869.2538,
+      "eval_samples_per_second": 3.188,
+      "eval_steps_per_second": 0.399,
+      "step": 200
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.380818247795105,
+      "learning_rate": 3.6482432230574446e-05,
+      "loss": 0.7938,
+      "step": 220
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.3564074635505676,
+      "learning_rate": 3.4221598113100195e-05,
+      "loss": 0.7819,
+      "step": 240
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.3780010938644409,
+      "learning_rate": 3.186969426877563e-05,
+      "loss": 0.7877,
+      "step": 260
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 0.36975908279418945,
+      "learning_rate": 2.9449947391938766e-05,
+      "loss": 0.7918,
+      "step": 280
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.39148128032684326,
+      "learning_rate": 2.6986254174292862e-05,
+      "loss": 0.7824,
+      "step": 300
+    },
+    {
+      "epoch": 1.9,
+      "eval_loss": 0.8058096766471863,
+      "eval_runtime": 867.7611,
+      "eval_samples_per_second": 3.193,
+      "eval_steps_per_second": 0.4,
+      "step": 300
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.36495909094810486,
+      "learning_rate": 2.4502945308373246e-05,
+      "loss": 0.7741,
+      "step": 320
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.40916556119918823,
+      "learning_rate": 2.2024545204952383e-05,
+      "loss": 0.7369,
+      "step": 340
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.42436033487319946,
+      "learning_rate": 1.957552979734205e-05,
+      "loss": 0.7365,
+      "step": 360
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.43983975052833557,
+      "learning_rate": 1.7180084824444325e-05,
+      "loss": 0.7463,
+      "step": 380
+    },
+    {
+      "epoch": 2.53,
+      "grad_norm": 0.44617146253585815,
+      "learning_rate": 1.4861866979675154e-05,
+      "loss": 0.7401,
+      "step": 400
+    },
+    {
+      "epoch": 2.53,
+      "eval_loss": 0.8059037923812866,
+      "eval_runtime": 873.5556,
+      "eval_samples_per_second": 3.172,
+      "eval_steps_per_second": 0.397,
+      "step": 400
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.4369719624519348,
+      "learning_rate": 1.2643770284581929e-05,
+      "loss": 0.7332,
+      "step": 420
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.4235495328903198,
+      "learning_rate": 1.0547699994378787e-05,
+      "loss": 0.7364,
+      "step": 440
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.4584214389324188,
+      "learning_rate": 8.594356268240616e-06,
+      "loss": 0.7318,
+      "step": 460
+    },
+    {
+      "epoch": 3.03,
+      "grad_norm": 0.4329874813556671,
+      "learning_rate": 6.803029740762648e-06,
+      "loss": 0.7222,
+      "step": 480
+    },
+    {
+      "epoch": 3.16,
+      "grad_norm": 0.5470691919326782,
+      "learning_rate": 5.191411013460645e-06,
+      "loss": 0.7101,
+      "step": 500
+    },
+    {
+      "epoch": 3.16,
+      "eval_loss": 0.807178795337677,
+      "eval_runtime": 867.2257,
+      "eval_samples_per_second": 3.195,
+      "eval_steps_per_second": 0.4,
+      "step": 500
+    },
+    {
+      "epoch": 3.29,
+      "grad_norm": 0.4557144343852997,
+      "learning_rate": 3.775415947715899e-06,
+      "loss": 0.7135,
+      "step": 520
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 0.46527382731437683,
+      "learning_rate": 2.5690284845196923e-06,
+      "loss": 0.7045,
+      "step": 540
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 0.4702458679676056,
+      "learning_rate": 1.5841625432818057e-06,
+      "loss": 0.7057,
+      "step": 560
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 0.4915095865726471,
+      "learning_rate": 8.305443635490711e-07,
+      "loss": 0.7044,
+      "step": 580
+    },
+    {
+      "epoch": 3.79,
+      "grad_norm": 0.5043957233428955,
+      "learning_rate": 3.1561645159166597e-07,
+      "loss": 0.7037,
+      "step": 600
+    },
+    {
+      "epoch": 3.79,
+      "eval_loss": 0.8061766028404236,
+      "eval_runtime": 867.9324,
+      "eval_samples_per_second": 3.193,
+      "eval_steps_per_second": 0.4,
+      "step": 600
+    },
+    {
+      "epoch": 3.92,
+      "grad_norm": 0.4672119915485382,
+      "learning_rate": 4.4464080451675494e-08,
+      "loss": 0.7027,
+      "step": 620
+    },
+    {
+      "epoch": 3.99,
+      "step": 632,
+      "total_flos": 1.137224723506643e+19,
+      "train_loss": 0.7920433780815028,
+      "train_runtime": 47185.3474,
+      "train_samples_per_second": 0.858,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 632,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 1.137224723506643e+19,
+  "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 sha256:1b573d48fc5f9488e07fd9eb672eddaf1b96a03a8caa287045c162f31893e3fd
+size 5112