Upload folder using huggingface_hub

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+tags:
+- llama-factory
+- lora
+- unsloth
+- generated_from_trainer
+model-index:
+- name: mistral_7b_trained
+  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. -->
+
+# mistral_7b_trained
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3) on the train_new 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: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.12.0
+- Transformers 4.46.1
+- Pytorch 2.2.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "gate_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 sha256:6c784d7b6c55899ce2038e1f6c4c52afaadd535a5493675ef5d4cb95a17bf983
+size 83945296

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9935483870967743,
+    "total_flos": 1.633496428047237e+17,
+    "train_loss": 0.0405226307439393,
+    "train_runtime": 3560.4547,
+    "train_samples_per_second": 3.131,
+    "train_steps_per_second": 0.098
+}

checkpoint-348/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-instruct-v0.3-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

checkpoint-348/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "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,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-348/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c784d7b6c55899ce2038e1f6c4c52afaadd535a5493675ef5d4cb95a17bf983
+size 83945296

checkpoint-348/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ea5c7f3cad4a94311921daf2b0a09583311da8e2e28ab3ed481ce22175dc313
+size 168149074

checkpoint-348/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86ef4c763639d21047bcb7d901fd5b4abdce0307ce9eb5c188e5b519d8067631
+size 14244

checkpoint-348/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0282d00eed9fe2ab27061734672e5936a63ea9e59fda708608ae904fc55aa57
+size 1064

checkpoint-348/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
+  }
+}

checkpoint-348/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-348/trainer_state.json

@@ -0,0 +1,271 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9935483870967743,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 0.815339207649231,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.2134,
+      "step": 10
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 0.7794559597969055,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.0692,
+      "step": 20
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.6546903848648071,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.0594,
+      "step": 30
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 0.6819568872451782,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.0546,
+      "step": 40
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.6973971128463745,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.0511,
+      "step": 50
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.661968469619751,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.0516,
+      "step": 60
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 0.6463760137557983,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.0464,
+      "step": 70
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 0.982441246509552,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.045,
+      "step": 80
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.8698186874389648,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.0478,
+      "step": 90
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.5412614345550537,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0397,
+      "step": 100
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 0.6799947619438171,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.0362,
+      "step": 110
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.7903907895088196,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0428,
+      "step": 120
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 0.811478316783905,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.0334,
+      "step": 130
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 0.6911829710006714,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.035,
+      "step": 140
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.6067230105400085,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0352,
+      "step": 150
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.6847725510597229,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0364,
+      "step": 160
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 0.9747119545936584,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0332,
+      "step": 170
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.48447030782699585,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0315,
+      "step": 180
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.5664235949516296,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0312,
+      "step": 190
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.5801066160202026,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0324,
+      "step": 200
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 0.7894909977912903,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.0326,
+      "step": 210
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 0.4664723575115204,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0319,
+      "step": 220
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 1.0112488269805908,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.0319,
+      "step": 230
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.37232428789138794,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0247,
+      "step": 240
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 0.7465298771858215,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.0276,
+      "step": 250
+    },
+    {
+      "epoch": 2.236559139784946,
+      "grad_norm": 0.7070090174674988,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0259,
+      "step": 260
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.48493513464927673,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0213,
+      "step": 270
+    },
+    {
+      "epoch": 2.4086021505376345,
+      "grad_norm": 1.0859829187393188,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.0224,
+      "step": 280
+    },
+    {
+      "epoch": 2.4946236559139785,
+      "grad_norm": 1.0049951076507568,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.0253,
+      "step": 290
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.5058858394622803,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0241,
+      "step": 300
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.7774279117584229,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0268,
+      "step": 310
+    },
+    {
+      "epoch": 2.752688172043011,
+      "grad_norm": 0.5623956918716431,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0222,
+      "step": 320
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.6706695556640625,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0265,
+      "step": 330
+    },
+    {
+      "epoch": 2.924731182795699,
+      "grad_norm": 0.5286621451377869,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0242,
+      "step": 340
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 348,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.633496428047237e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-348/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf0143af9bc2792ceb14b386eaae0e747e0a02357f934b8190f9fc64e598254f
+size 5432

llamaboard_config.yaml

@@ -0,0 +1,66 @@
+top.booster: unsloth
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Mistral-7B-Instruct-v0.3
+top.quantization_bit: '4'
+top.quantization_method: bitsandbytes
+top.rope_scaling: none
+top.template: alpaca
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 8
+train.compute_type: bf16
+train.create_new_adapter: false
+train.cutoff_len: 2048
+train.dataset:
+- train_new
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.extra_args: '{"optim": "adamw_torch"}'
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 4
+train.learning_rate: 3e-5
+train.logging_steps: 10
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.mask_history: false
+train.max_grad_norm: '1.0'
+train.max_samples: '3716'
+train.neat_packing: false
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 1000
+train.shift_attn: false
+train.train_on_prompt: false
+train.training_stage: Supervised Fine-Tuning
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

running_log.txt

@@ -0,0 +1,1203 @@
+[WARNING|2025-02-04 05:46:33] logging.py:162 >> We recommend enable `upcast_layernorm` in quantized training.
+
+[INFO|2025-02-04 05:46:33] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16
+
+[INFO|2025-02-04 05:46:33] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2025-02-04 05:46:33] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-02-04 05:46:33] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2025-02-04 05:46:33] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2025-02-04 05:46:33] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-02-04 05:46:33] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2025-02-04 05:46:33] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2025-02-04 05:46:34] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2025-02-04 05:46:34] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-02-04 05:46:34] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.model
+
+[INFO|2025-02-04 05:46:34] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer.json
+
+[INFO|2025-02-04 05:46:34] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-02-04 05:46:34] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/special_tokens_map.json
+
+[INFO|2025-02-04 05:46:34] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/tokenizer_config.json
+
+[INFO|2025-02-04 05:46:34] logging.py:157 >> Add pad token: </s>
+
+[INFO|2025-02-04 05:46:34] logging.py:157 >> Loading dataset train_new.json...
+
+[INFO|2025-02-04 05:46:36] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-7B-Instruct-v0.3/snapshots/e0bc86c23ce5aae1db576c8cca6f06f1f73af2db/config.json
+
+[INFO|2025-02-04 05:46:36] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-02-04 05:46:36] logging.py:157 >> Quantizing model to 4 bit with bitsandbytes.
+
+[INFO|2025-02-04 05:46:37] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-02-04 05:46:37] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--aws/snapshots/66e4c14a24a0b445779c922eef992a4af0694a88/config.json
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--repeat/snapshots/7c48478c02f84ed89f149b0815cc0216ee831fb0/config.json
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--vram-24/snapshots/61324ceeacd75b2b31f7a789a9c9d82058e6118c/config.json
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--1/snapshots/7ec782b7604cd9ea0781c23a4270f031650f5617/config.json
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-02-04 05:46:38] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-7b-instruct-v0.3-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-02-04 05:46:39] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/model.safetensors
+
+[INFO|2025-02-04 05:46:39] modeling_utils.py:1670 >> Instantiating MistralForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-02-04 05:46:39] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 770
+}
+
+
+[INFO|2025-02-04 05:46:41] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing MistralForCausalLM.
+
+
+[INFO|2025-02-04 05:46:41] modeling_utils.py:4808 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at unsloth/mistral-7b-instruct-v0.3-bnb-4bit.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use MistralForCausalLM for predictions without further training.
+
+[INFO|2025-02-04 05:46:41] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/generation_config.json
+
+[INFO|2025-02-04 05:46:41] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 32768,
+  "pad_token_id": 770
+}
+
+
+[INFO|2025-02-04 05:46:42] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-02-04 05:46:42] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-02-04 05:46:42] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2025-02-04 05:46:42] logging.py:157 >> Found linear modules: v_proj,up_proj,q_proj,down_proj,k_proj,o_proj,gate_proj
+
+[WARNING|2025-02-04 05:46:44] logging.py:168 >> Unsloth 2025.1.8 patched 32 layers with 32 QKV layers, 32 O layers and 32 MLP layers.
+
+[INFO|2025-02-04 05:46:45] logging.py:157 >> trainable params: 20,971,520 || all params: 7,268,995,072 || trainable%: 0.2885
+
+[INFO|2025-02-04 05:46:45] trainer.py:698 >> Using auto half precision backend
+
+[WARNING|2025-02-04 05:46:45] <string>:208 >> ==((====))==  Unsloth - 2x faster free finetuning | Num GPUs = 1
+   \\   /|    Num examples = 3,716 | Num Epochs = 3
+O^O/ \_/ \    Batch size per device = 8 | Gradient Accumulation steps = 4
+\        /    Total batch size = 32 | Total steps = 348
+ "-____-"     Number of trainable parameters = 20,971,520
+
+[WARNING|2025-02-04 05:46:46] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:46:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:47:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:47:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:47:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:47:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:47:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:47:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:48:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:48:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 05:48:29] logging.py:157 >> {'loss': 0.2134, 'learning_rate': 2.9939e-05, 'epoch': 0.09}
+
+[WARNING|2025-02-04 05:48:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:48:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:48:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:49:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:49:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:49:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:49:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:49:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:49:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:50:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 05:50:11] logging.py:157 >> {'loss': 0.0692, 'learning_rate': 2.9756e-05, 'epoch': 0.17}
+
+[WARNING|2025-02-04 05:50:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:50:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:50:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:50:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:50:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:51:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:51:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:51:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:51:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:51:44] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 05:51:54] logging.py:157 >> {'loss': 0.0594, 'learning_rate': 2.9453e-05, 'epoch': 0.26}
+
+[WARNING|2025-02-04 05:51:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:52:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:52:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:52:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:52:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:52:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:52:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:53:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:53:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:53:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 05:53:37] logging.py:157 >> {'loss': 0.0546, 'learning_rate': 2.9033e-05, 'epoch': 0.34}
+
+[WARNING|2025-02-04 05:53:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:53:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:53:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:54:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:54:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:54:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:54:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:54:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:54:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:55:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 05:55:19] logging.py:157 >> {'loss': 0.0511, 'learning_rate': 2.8498e-05, 'epoch': 0.43}
+
+[WARNING|2025-02-04 05:55:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:55:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:55:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:55:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:56:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:56:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:56:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:56:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:56:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:56:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 05:57:01] logging.py:157 >> {'loss': 0.0516, 'learning_rate': 2.7853e-05, 'epoch': 0.52}
+
+[WARNING|2025-02-04 05:57:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:57:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:57:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:57:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:57:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:57:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:58:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:58:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:58:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:58:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 05:58:44] logging.py:157 >> {'loss': 0.0464, 'learning_rate': 2.7103e-05, 'epoch': 0.60}
+
+[WARNING|2025-02-04 05:58:44] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:58:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:59:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:59:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:59:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:59:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:59:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 05:59:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:00:05] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:00:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:00:26] logging.py:157 >> {'loss': 0.0450, 'learning_rate': 2.6255e-05, 'epoch': 0.69}
+
+[WARNING|2025-02-04 06:00:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:00:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:00:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:00:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:01:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:01:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:01:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:01:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:01:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:01:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:02:10] logging.py:157 >> {'loss': 0.0478, 'learning_rate': 2.5315e-05, 'epoch': 0.77}
+
+[WARNING|2025-02-04 06:02:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:02:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:02:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:02:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:02:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:03:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:03:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:03:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:03:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:03:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:03:52] logging.py:157 >> {'loss': 0.0397, 'learning_rate': 2.4292e-05, 'epoch': 0.86}
+
+[WARNING|2025-02-04 06:03:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:04:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:04:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:04:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:04:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:04:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:04:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:05:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:05:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:05:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:05:33] logging.py:157 >> {'loss': 0.0362, 'learning_rate': 2.3192e-05, 'epoch': 0.95}
+
+[WARNING|2025-02-04 06:05:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:05:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:05:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:06:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:06:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:06:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:06:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:06:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:06:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:06:56] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:07:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:07:14] logging.py:157 >> {'loss': 0.0428, 'learning_rate': 2.2026e-05, 'epoch': 1.03}
+
+[WARNING|2025-02-04 06:07:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:07:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:07:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:07:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:07:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:08:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:08:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:08:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:08:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:08:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:08:58] logging.py:157 >> {'loss': 0.0334, 'learning_rate': 2.0803e-05, 'epoch': 1.12}
+
+[WARNING|2025-02-04 06:09:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:09:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:09:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:09:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:09:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:09:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:10:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:10:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:10:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:10:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:10:40] logging.py:157 >> {'loss': 0.0350, 'learning_rate': 1.9532e-05, 'epoch': 1.20}
+
+[WARNING|2025-02-04 06:10:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:10:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:11:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:11:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:11:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:11:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:11:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:11:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:12:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:12:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:12:21] logging.py:157 >> {'loss': 0.0352, 'learning_rate': 1.8225e-05, 'epoch': 1.29}
+
+[WARNING|2025-02-04 06:12:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:12:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:12:44] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:12:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:13:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:13:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:13:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:13:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:13:44] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:13:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:14:02] logging.py:157 >> {'loss': 0.0364, 'learning_rate': 1.6891e-05, 'epoch': 1.38}
+
+[WARNING|2025-02-04 06:14:05] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:14:15] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:14:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:14:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:14:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:14:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:15:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:15:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:15:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:15:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:15:45] logging.py:157 >> {'loss': 0.0332, 'learning_rate': 1.5542e-05, 'epoch': 1.46}
+
+[WARNING|2025-02-04 06:15:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:15:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:16:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:16:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:16:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:16:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:16:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:16:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:17:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:17:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:17:27] logging.py:157 >> {'loss': 0.0315, 'learning_rate': 1.4188e-05, 'epoch': 1.55}
+
+[WARNING|2025-02-04 06:17:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:17:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:17:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:17:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:18:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:18:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:18:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:18:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:18:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:19:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:19:08] logging.py:157 >> {'loss': 0.0312, 'learning_rate': 1.2841e-05, 'epoch': 1.63}
+
+[WARNING|2025-02-04 06:19:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:19:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:19:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:19:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:19:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:20:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:20:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:20:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:20:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:20:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:20:51] logging.py:157 >> {'loss': 0.0324, 'learning_rate': 1.1511e-05, 'epoch': 1.72}
+
+[WARNING|2025-02-04 06:20:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:21:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:21:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:21:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:21:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:21:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:21:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:22:05] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:22:15] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:22:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:22:34] logging.py:157 >> {'loss': 0.0326, 'learning_rate': 1.0210e-05, 'epoch': 1.81}
+
+[WARNING|2025-02-04 06:22:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:22:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:22:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:23:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:23:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:23:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:23:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:23:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:23:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:24:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:24:16] logging.py:157 >> {'loss': 0.0319, 'learning_rate': 8.9485e-06, 'epoch': 1.89}
+
+[WARNING|2025-02-04 06:24:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:24:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:24:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:24:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:24:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:25:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:25:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:25:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:25:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:25:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:25:58] logging.py:157 >> {'loss': 0.0319, 'learning_rate': 7.7358e-06, 'epoch': 1.98}
+
+[WARNING|2025-02-04 06:26:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:26:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:26:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:26:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:26:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:26:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:26:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:27:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:27:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:27:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:27:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:27:39] logging.py:157 >> {'loss': 0.0247, 'learning_rate': 6.5822e-06, 'epoch': 2.06}
+
+[WARNING|2025-02-04 06:27:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:27:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:28:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:28:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:28:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:28:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:28:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:28:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:29:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:29:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:29:22] logging.py:157 >> {'loss': 0.0276, 'learning_rate': 5.4972e-06, 'epoch': 2.15}
+
+[WARNING|2025-02-04 06:29:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:29:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:29:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:29:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:30:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:30:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:30:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:30:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:30:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:31:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:31:07] logging.py:157 >> {'loss': 0.0259, 'learning_rate': 4.4896e-06, 'epoch': 2.24}
+
+[WARNING|2025-02-04 06:31:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:31:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:31:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:31:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:31:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:32:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:32:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:32:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:32:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:32:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:32:47] logging.py:157 >> {'loss': 0.0213, 'learning_rate': 3.5676e-06, 'epoch': 2.32}
+
+[WARNING|2025-02-04 06:32:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:33:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:33:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:33:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:33:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:33:44] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:33:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:34:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:34:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:34:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:34:32] logging.py:157 >> {'loss': 0.0224, 'learning_rate': 2.7387e-06, 'epoch': 2.41}
+
+[WARNING|2025-02-04 06:34:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:34:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:34:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:35:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:35:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:35:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:35:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:35:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:35:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:36:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:36:13] logging.py:157 >> {'loss': 0.0253, 'learning_rate': 2.0096e-06, 'epoch': 2.49}
+
+[WARNING|2025-02-04 06:36:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:36:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:36:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:36:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:36:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:37:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:37:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:37:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:37:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:37:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:37:56] logging.py:157 >> {'loss': 0.0241, 'learning_rate': 1.3864e-06, 'epoch': 2.58}
+
+[WARNING|2025-02-04 06:38:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:38:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:38:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:38:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:38:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:38:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:39:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:39:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:39:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:39:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:39:38] logging.py:157 >> {'loss': 0.0268, 'learning_rate': 8.7399e-07, 'epoch': 2.67}
+
+[WARNING|2025-02-04 06:39:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:39:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:40:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:40:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:40:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:40:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:40:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:40:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:41:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:41:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:41:20] logging.py:157 >> {'loss': 0.0222, 'learning_rate': 4.7666e-07, 'epoch': 2.75}
+
+[WARNING|2025-02-04 06:41:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:41:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:41:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:41:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:42:05] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:42:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:42:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:42:36] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:42:46] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:42:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:43:02] logging.py:157 >> {'loss': 0.0265, 'learning_rate': 1.9760e-07, 'epoch': 2.84}
+
+[WARNING|2025-02-04 06:43:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:43:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:43:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:43:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:43:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:43:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:44:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:44:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:44:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:44:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:44:43] logging.py:157 >> {'loss': 0.0242, 'learning_rate': 3.9102e-08, 'epoch': 2.92}
+
+[WARNING|2025-02-04 06:44:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:44:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:45:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:45:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:45:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:45:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:45:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 06:46:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 06:46:06] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/mistral_7b_trained/checkpoint-348
+
+[INFO|2025-02-04 06:46:06] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-02-04 06:46:06] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[INFO|2025-02-04 06:46:06] <string>:484 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-02-04 06:46:06] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-7B-Instruct-v0.3/lora/mistral_7b_trained
+
+[INFO|2025-02-04 06:46:06] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-7b-instruct-v0.3-bnb-4bit/snapshots/d5f623888f1415cf89b5c208d09cb620694618ee/config.json
+
+[INFO|2025-02-04 06:46:06] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/Mistral-7B-Instruct-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 770,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "unsloth_version": "2024.9",
+  "use_cache": true,
+  "vocab_size": 32768
+}
+
+
+[WARNING|2025-02-04 06:46:07] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-02-04 06:46:07] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-02-04 06:46:07] modelcard.py:449 >> Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9935483870967743,
+    "total_flos": 1.633496428047237e+17,
+    "train_loss": 0.0405226307439393,
+    "train_runtime": 3560.4547,
+    "train_samples_per_second": 3.131,
+    "train_steps_per_second": 0.098
+}

trainer_log.jsonl

@@ -0,0 +1,35 @@
+{"current_steps": 10, "total_steps": 348, "loss": 0.2134, "lr": 2.9938918800982563e-05, "epoch": 0.08602150537634409, "percentage": 2.87, "elapsed_time": "0:01:43", "remaining_time": "0:58:21"}
+{"current_steps": 20, "total_steps": 348, "loss": 0.0692, "lr": 2.975617265898004e-05, "epoch": 0.17204301075268819, "percentage": 5.75, "elapsed_time": "0:03:24", "remaining_time": "0:56:01"}
+{"current_steps": 30, "total_steps": 348, "loss": 0.0594, "lr": 2.9453249887788343e-05, "epoch": 0.25806451612903225, "percentage": 8.62, "elapsed_time": "0:05:08", "remaining_time": "0:54:24"}
+{"current_steps": 40, "total_steps": 348, "loss": 0.0546, "lr": 2.9032617538884018e-05, "epoch": 0.34408602150537637, "percentage": 11.49, "elapsed_time": "0:06:51", "remaining_time": "0:52:48"}
+{"current_steps": 50, "total_steps": 348, "loss": 0.0511, "lr": 2.84977013093626e-05, "epoch": 0.43010752688172044, "percentage": 14.37, "elapsed_time": "0:08:33", "remaining_time": "0:50:59"}
+{"current_steps": 60, "total_steps": 348, "loss": 0.0516, "lr": 2.7852857642513838e-05, "epoch": 0.5161290322580645, "percentage": 17.24, "elapsed_time": "0:10:15", "remaining_time": "0:49:12"}
+{"current_steps": 70, "total_steps": 348, "loss": 0.0464, "lr": 2.7103338248251055e-05, "epoch": 0.6021505376344086, "percentage": 20.11, "elapsed_time": "0:11:57", "remaining_time": "0:47:31"}
+{"current_steps": 80, "total_steps": 348, "loss": 0.045, "lr": 2.6255247332346036e-05, "epoch": 0.6881720430107527, "percentage": 22.99, "elapsed_time": "0:13:40", "remaining_time": "0:45:49"}
+{"current_steps": 90, "total_steps": 348, "loss": 0.0478, "lr": 2.531549188280135e-05, "epoch": 0.7741935483870968, "percentage": 25.86, "elapsed_time": "0:15:23", "remaining_time": "0:44:08"}
+{"current_steps": 100, "total_steps": 348, "loss": 0.0397, "lr": 2.4291725418235848e-05, "epoch": 0.8602150537634409, "percentage": 28.74, "elapsed_time": "0:17:06", "remaining_time": "0:42:24"}
+{"current_steps": 110, "total_steps": 348, "loss": 0.0362, "lr": 2.3192285656405456e-05, "epoch": 0.946236559139785, "percentage": 31.61, "elapsed_time": "0:18:47", "remaining_time": "0:40:39"}
+{"current_steps": 120, "total_steps": 348, "loss": 0.0428, "lr": 2.2026126610496852e-05, "epoch": 1.032258064516129, "percentage": 34.48, "elapsed_time": "0:20:27", "remaining_time": "0:38:52"}
+{"current_steps": 130, "total_steps": 348, "loss": 0.0334, "lr": 2.0802745666212592e-05, "epoch": 1.118279569892473, "percentage": 37.36, "elapsed_time": "0:22:11", "remaining_time": "0:37:13"}
+{"current_steps": 140, "total_steps": 348, "loss": 0.035, "lr": 1.953210623354359e-05, "epoch": 1.2043010752688172, "percentage": 40.23, "elapsed_time": "0:23:54", "remaining_time": "0:35:30"}
+{"current_steps": 150, "total_steps": 348, "loss": 0.0352, "lr": 1.8224556603165363e-05, "epoch": 1.2903225806451613, "percentage": 43.1, "elapsed_time": "0:25:34", "remaining_time": "0:33:45"}
+{"current_steps": 160, "total_steps": 348, "loss": 0.0364, "lr": 1.689074566830434e-05, "epoch": 1.3763440860215055, "percentage": 45.98, "elapsed_time": "0:27:16", "remaining_time": "0:32:02"}
+{"current_steps": 170, "total_steps": 348, "loss": 0.0332, "lr": 1.5541536198449044e-05, "epoch": 1.4623655913978495, "percentage": 48.85, "elapsed_time": "0:28:59", "remaining_time": "0:30:20"}
+{"current_steps": 180, "total_steps": 348, "loss": 0.0315, "lr": 1.4187916371218739e-05, "epoch": 1.5483870967741935, "percentage": 51.72, "elapsed_time": "0:30:41", "remaining_time": "0:28:38"}
+{"current_steps": 190, "total_steps": 348, "loss": 0.0312, "lr": 1.2840910282888211e-05, "epoch": 1.6344086021505375, "percentage": 54.6, "elapsed_time": "0:32:22", "remaining_time": "0:26:55"}
+{"current_steps": 200, "total_steps": 348, "loss": 0.0324, "lr": 1.1511488166385349e-05, "epoch": 1.7204301075268817, "percentage": 57.47, "elapsed_time": "0:34:04", "remaining_time": "0:25:13"}
+{"current_steps": 210, "total_steps": 348, "loss": 0.0326, "lr": 1.0210477047960303e-05, "epoch": 1.8064516129032258, "percentage": 60.34, "elapsed_time": "0:35:48", "remaining_time": "0:23:31"}
+{"current_steps": 220, "total_steps": 348, "loss": 0.0319, "lr": 8.948472570152874e-06, "epoch": 1.89247311827957, "percentage": 63.22, "elapsed_time": "0:37:30", "remaining_time": "0:21:49"}
+{"current_steps": 230, "total_steps": 348, "loss": 0.0319, "lr": 7.735752699185711e-06, "epoch": 1.978494623655914, "percentage": 66.09, "elapsed_time": "0:39:11", "remaining_time": "0:20:06"}
+{"current_steps": 240, "total_steps": 348, "loss": 0.0247, "lr": 6.582194019564266e-06, "epoch": 2.064516129032258, "percentage": 68.97, "elapsed_time": "0:40:52", "remaining_time": "0:18:23"}
+{"current_steps": 250, "total_steps": 348, "loss": 0.0276, "lr": 5.497191297593647e-06, "epoch": 2.150537634408602, "percentage": 71.84, "elapsed_time": "0:42:35", "remaining_time": "0:16:41"}
+{"current_steps": 260, "total_steps": 348, "loss": 0.0259, "lr": 4.4895809688998655e-06, "epoch": 2.236559139784946, "percentage": 74.71, "elapsed_time": "0:44:20", "remaining_time": "0:15:00"}
+{"current_steps": 270, "total_steps": 348, "loss": 0.0213, "lr": 3.567569173085455e-06, "epoch": 2.3225806451612905, "percentage": 77.59, "elapsed_time": "0:46:01", "remaining_time": "0:13:17"}
+{"current_steps": 280, "total_steps": 348, "loss": 0.0224, "lr": 2.7386649216166233e-06, "epoch": 2.4086021505376345, "percentage": 80.46, "elapsed_time": "0:47:46", "remaining_time": "0:11:36"}
+{"current_steps": 290, "total_steps": 348, "loss": 0.0253, "lr": 2.0096189432334194e-06, "epoch": 2.4946236559139785, "percentage": 83.33, "elapsed_time": "0:49:27", "remaining_time": "0:09:53"}
+{"current_steps": 300, "total_steps": 348, "loss": 0.0241, "lr": 1.3863687049356465e-06, "epoch": 2.5806451612903225, "percentage": 86.21, "elapsed_time": "0:51:10", "remaining_time": "0:08:11"}
+{"current_steps": 310, "total_steps": 348, "loss": 0.0268, "lr": 8.7399005630238e-07, "epoch": 2.6666666666666665, "percentage": 89.08, "elapsed_time": "0:52:52", "remaining_time": "0:06:28"}
+{"current_steps": 320, "total_steps": 348, "loss": 0.0222, "lr": 4.766558909615504e-07, "epoch": 2.752688172043011, "percentage": 91.95, "elapsed_time": "0:54:33", "remaining_time": "0:04:46"}
+{"current_steps": 330, "total_steps": 348, "loss": 0.0265, "lr": 1.9760216187710788e-07, "epoch": 2.838709677419355, "percentage": 94.83, "elapsed_time": "0:56:15", "remaining_time": "0:03:04"}
+{"current_steps": 340, "total_steps": 348, "loss": 0.0242, "lr": 3.910152723075322e-08, "epoch": 2.924731182795699, "percentage": 97.7, "elapsed_time": "0:57:57", "remaining_time": "0:01:21"}
+{"current_steps": 348, "total_steps": 348, "epoch": 2.9935483870967743, "percentage": 100.0, "elapsed_time": "0:59:20", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,280 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9935483870967743,
+  "eval_steps": 500,
+  "global_step": 348,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 0.815339207649231,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.2134,
+      "step": 10
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 0.7794559597969055,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.0692,
+      "step": 20
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.6546903848648071,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.0594,
+      "step": 30
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 0.6819568872451782,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.0546,
+      "step": 40
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.6973971128463745,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.0511,
+      "step": 50
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.661968469619751,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.0516,
+      "step": 60
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 0.6463760137557983,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.0464,
+      "step": 70
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 0.982441246509552,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.045,
+      "step": 80
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.8698186874389648,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.0478,
+      "step": 90
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.5412614345550537,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0397,
+      "step": 100
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 0.6799947619438171,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.0362,
+      "step": 110
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.7903907895088196,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0428,
+      "step": 120
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 0.811478316783905,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.0334,
+      "step": 130
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 0.6911829710006714,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.035,
+      "step": 140
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.6067230105400085,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0352,
+      "step": 150
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.6847725510597229,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0364,
+      "step": 160
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 0.9747119545936584,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0332,
+      "step": 170
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.48447030782699585,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0315,
+      "step": 180
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.5664235949516296,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0312,
+      "step": 190
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.5801066160202026,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0324,
+      "step": 200
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 0.7894909977912903,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.0326,
+      "step": 210
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 0.4664723575115204,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0319,
+      "step": 220
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 1.0112488269805908,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.0319,
+      "step": 230
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.37232428789138794,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0247,
+      "step": 240
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 0.7465298771858215,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.0276,
+      "step": 250
+    },
+    {
+      "epoch": 2.236559139784946,
+      "grad_norm": 0.7070090174674988,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0259,
+      "step": 260
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.48493513464927673,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0213,
+      "step": 270
+    },
+    {
+      "epoch": 2.4086021505376345,
+      "grad_norm": 1.0859829187393188,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.0224,
+      "step": 280
+    },
+    {
+      "epoch": 2.4946236559139785,
+      "grad_norm": 1.0049951076507568,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.0253,
+      "step": 290
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.5058858394622803,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0241,
+      "step": 300
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.7774279117584229,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0268,
+      "step": 310
+    },
+    {
+      "epoch": 2.752688172043011,
+      "grad_norm": 0.5623956918716431,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0222,
+      "step": 320
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.6706695556640625,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0265,
+      "step": 330
+    },
+    {
+      "epoch": 2.924731182795699,
+      "grad_norm": 0.5286621451377869,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0242,
+      "step": 340
+    },
+    {
+      "epoch": 2.9935483870967743,
+      "step": 348,
+      "total_flos": 1.633496428047237e+17,
+      "train_loss": 0.0405226307439393,
+      "train_runtime": 3560.4547,
+      "train_samples_per_second": 3.131,
+      "train_steps_per_second": 0.098
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 348,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.633496428047237e+17,
+  "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:bf0143af9bc2792ceb14b386eaae0e747e0a02357f934b8190f9fc64e598254f
+size 5432

training_args.yaml

@@ -0,0 +1,34 @@
+bf16: true
+cutoff_len: 2048
+dataset: train_new
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+gradient_accumulation_steps: 4
+learning_rate: 3.0e-05
+logging_steps: 10
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 3716
+model_name_or_path: mistralai/Mistral-7B-Instruct-v0.3
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Mistral-7B-Instruct-v0.3/lora/mistral_7b_trained
+packing: false
+per_device_train_batch_size: 8
+plot_loss: true
+preprocessing_num_workers: 16
+quantization_bit: 4
+quantization_method: bitsandbytes
+report_to: none
+save_steps: 1000
+stage: sft
+template: alpaca
+use_unsloth: true
+warmup_steps: 0