Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-348/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,59 @@
----
-license: apache-2.0
----
+---
+library_name: peft
+license: other
+base_model: unsloth/mistral-nemo-instruct-2407-bnb-4bit
+tags:
+- llama-factory
+- lora
+- unsloth
+- generated_from_trainer
+model-index:
+- name: mistral-nemo-finetuned
+  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-nemo-finetuned
+
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) 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-nemo-instruct-2407-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": [
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_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 sha256:4e58d1ff27b7e65906c64608ee0e5adbf7ad2d7c579a7bf589b65ebb87e06602
+size 114106856

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9935483870967743,
+    "total_flos": 2.344956384116736e+17,
+    "train_loss": 0.045667905531737996,
+    "train_runtime": 1808.5239,
+    "train_samples_per_second": 6.164,
+    "train_steps_per_second": 0.192
+}

checkpoint-348/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-nemo-instruct-2407-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-nemo-instruct-2407-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": [
+    "k_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "down_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 sha256:4e58d1ff27b7e65906c64608ee0e5adbf7ad2d7c579a7bf589b65ebb87e06602
+size 114106856

checkpoint-348/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6fb5bd96032490e1389fa6fd2592f69eb47acac4a0714203f8afad04265fa4
+size 228536930

checkpoint-348/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1ad24288d3c9b7105fb709c041f6a2fbf6db40df845dc703a2cba4b782106e4
+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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

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": 0.4689747393131256,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.0829,
+      "step": 10
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 0.31903743743896484,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.073,
+      "step": 20
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.3387955129146576,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.068,
+      "step": 30
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 0.33919498324394226,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.0603,
+      "step": 40
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.33728891611099243,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.0617,
+      "step": 50
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.30449143052101135,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.0617,
+      "step": 60
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 0.3293665945529938,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.0587,
+      "step": 70
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 0.4717239737510681,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.0555,
+      "step": 80
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.4681776463985443,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.0538,
+      "step": 90
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.33837395906448364,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0466,
+      "step": 100
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 0.3245820999145508,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.0457,
+      "step": 110
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.34947386384010315,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0491,
+      "step": 120
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 0.359684020280838,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.0421,
+      "step": 130
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 0.3907443583011627,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.0429,
+      "step": 140
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.40398046374320984,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0448,
+      "step": 150
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.40687504410743713,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0439,
+      "step": 160
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 0.7241388559341431,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0432,
+      "step": 170
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.3367048501968384,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0384,
+      "step": 180
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.27823126316070557,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0415,
+      "step": 190
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.3167360723018646,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0419,
+      "step": 200
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 0.3927469849586487,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.0431,
+      "step": 210
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 0.3293432891368866,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0389,
+      "step": 220
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 0.4683464765548706,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.0422,
+      "step": 230
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.33360326290130615,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0337,
+      "step": 240
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 0.4784548878669739,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.0354,
+      "step": 250
+    },
+    {
+      "epoch": 2.236559139784946,
+      "grad_norm": 0.442839652299881,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0375,
+      "step": 260
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.3498876690864563,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0296,
+      "step": 270
+    },
+    {
+      "epoch": 2.4086021505376345,
+      "grad_norm": 0.6078402400016785,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.0326,
+      "step": 280
+    },
+    {
+      "epoch": 2.4946236559139785,
+      "grad_norm": 0.5483068227767944,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.037,
+      "step": 290
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.29595789313316345,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0344,
+      "step": 300
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.3882715702056885,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0382,
+      "step": 310
+    },
+    {
+      "epoch": 2.752688172043011,
+      "grad_norm": 0.3592262864112854,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0332,
+      "step": 320
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.42720264196395874,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0369,
+      "step": 330
+    },
+    {
+      "epoch": 2.924731182795699,
+      "grad_norm": 0.34159648418426514,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0361,
+      "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": 2.344956384116736e+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 sha256:581e11ecdf29838856a4d9fd37fef831aae8f22c808c0cf81d6fced7208a6071
+size 5432

llamaboard_config.yaml

@@ -0,0 +1,66 @@
+top.booster: unsloth
+top.checkpoint_path: []
+top.finetuning_type: lora
+top.model_name: Mistral-Nemo-Instruct-2407
+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 +1,1228 @@
+[WARNING|2025-02-04 08:13:37] logging.py:162 >> We recommend enable `upcast_layernorm` in quantized training.
+
+[INFO|2025-02-04 08:13:37] parser.py:355 >> Process rank: 0, device: cuda:0, n_gpu: 1, distributed training: False, compute dtype: torch.bfloat16
+
+[INFO|2025-02-04 08:13:38] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/config.json
+
+[INFO|2025-02-04 08:13:38] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "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": 131072
+}
+
+
+[INFO|2025-02-04 08:13:38] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/tokenizer.json
+
+[INFO|2025-02-04 08:13:38] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-02-04 08:13:38] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-02-04 08:13:38] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/special_tokens_map.json
+
+[INFO|2025-02-04 08:13:38] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/tokenizer_config.json
+
+[INFO|2025-02-04 08:13:39] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/config.json
+
+[INFO|2025-02-04 08:13:39] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "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": 131072
+}
+
+
+[INFO|2025-02-04 08:13:39] tokenization_utils_base.py:2211 >> loading file tokenizer.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/tokenizer.json
+
+[INFO|2025-02-04 08:13:39] tokenization_utils_base.py:2211 >> loading file tokenizer.model from cache at None
+
+[INFO|2025-02-04 08:13:39] tokenization_utils_base.py:2211 >> loading file added_tokens.json from cache at None
+
+[INFO|2025-02-04 08:13:39] tokenization_utils_base.py:2211 >> loading file special_tokens_map.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/special_tokens_map.json
+
+[INFO|2025-02-04 08:13:39] tokenization_utils_base.py:2211 >> loading file tokenizer_config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/tokenizer_config.json
+
+[INFO|2025-02-04 08:13:39] logging.py:157 >> Add pad token: </s>
+
+[INFO|2025-02-04 08:13:39] logging.py:157 >> Loading dataset train_new.json...
+
+[INFO|2025-02-04 08:13:44] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--mistralai--Mistral-Nemo-Instruct-2407/snapshots/8aedd450f2583e9c67fae1929f6936b8fc5aef9c/config.json
+
+[INFO|2025-02-04 08:13:44] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "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": 131072
+}
+
+
+[INFO|2025-02-04 08:13:44] logging.py:157 >> Quantizing model to 4 bit with bitsandbytes.
+
+[INFO|2025-02-04 08:13:45] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-nemo-instruct-2407-bnb-4bit/snapshots/a8e82a934394c6858f5ee545fa55e1e8cc67065f/config.json
+
+[INFO|2025-02-04 08:13:45] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-nemo-instruct-2407-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "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": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "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_fixed": true,
+  "use_cache": true,
+  "vocab_size": 131072
+}
+
+
+[INFO|2025-02-04 08:13:46] 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 08:13:46] 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 08:13:46] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unslothai--vram-48/snapshots/3aea312d98ea327daeb5dbf7374b1d7cf8c65bc0/config.json
+
+[INFO|2025-02-04 08:13:46] 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 08:13:46] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-nemo-instruct-2407-bnb-4bit/snapshots/a8e82a934394c6858f5ee545fa55e1e8cc67065f/config.json
+
+[INFO|2025-02-04 08:13:46] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-nemo-instruct-2407-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "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": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "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_fixed": true,
+  "use_cache": true,
+  "vocab_size": 131072
+}
+
+
+[INFO|2025-02-04 08:13:46] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-nemo-instruct-2407-bnb-4bit/snapshots/a8e82a934394c6858f5ee545fa55e1e8cc67065f/config.json
+
+[INFO|2025-02-04 08:13:46] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "unsloth/mistral-nemo-instruct-2407-bnb-4bit",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "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": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "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_fixed": true,
+  "use_cache": true,
+  "vocab_size": 131072
+}
+
+
+[INFO|2025-02-04 08:13:46] modeling_utils.py:3937 >> loading weights file model.safetensors from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-nemo-instruct-2407-bnb-4bit/snapshots/a8e82a934394c6858f5ee545fa55e1e8cc67065f/model.safetensors.index.json
+
+[INFO|2025-02-04 08:27:06] modeling_utils.py:1670 >> Instantiating MistralForCausalLM model under default dtype torch.bfloat16.
+
+[INFO|2025-02-04 08:27:06] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 10
+}
+
+
+[INFO|2025-02-04 08:27:11] modeling_utils.py:4800 >> All model checkpoint weights were used when initializing MistralForCausalLM.
+
+
+[INFO|2025-02-04 08:27:11] modeling_utils.py:4808 >> All the weights of MistralForCausalLM were initialized from the model checkpoint at unsloth/mistral-nemo-instruct-2407-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 08:27:12] configuration_utils.py:1051 >> loading configuration file generation_config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-nemo-instruct-2407-bnb-4bit/snapshots/a8e82a934394c6858f5ee545fa55e1e8cc67065f/generation_config.json
+
+[INFO|2025-02-04 08:27:12] configuration_utils.py:1096 >> Generate config GenerationConfig {
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 131072,
+  "pad_token_id": 10
+}
+
+
+[INFO|2025-02-04 08:27:15] logging.py:157 >> Gradient checkpointing enabled.
+
+[INFO|2025-02-04 08:27:15] logging.py:157 >> Upcasting trainable params to float32.
+
+[INFO|2025-02-04 08:27:15] logging.py:157 >> Fine-tuning method: LoRA
+
+[INFO|2025-02-04 08:27:15] logging.py:157 >> Found linear modules: k_proj,gate_proj,q_proj,up_proj,o_proj,v_proj,down_proj
+
+[WARNING|2025-02-04 08:27:16] logging.py:168 >> Unsloth 2025.1.8 patched 40 layers with 40 QKV layers, 40 O layers and 40 MLP layers.
+
+[INFO|2025-02-04 08:27:18] logging.py:157 >> trainable params: 28,508,160 || all params: 12,276,290,560 || trainable%: 0.2322
+
+[INFO|2025-02-04 08:27:18] trainer.py:698 >> Using auto half precision backend
+
+[WARNING|2025-02-04 08:27:18] <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 = 28,508,160
+
+[WARNING|2025-02-04 08:27:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:27:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:27:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:27:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:27:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:27:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:27:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:27:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:28:12] logging.py:157 >> {'loss': 0.0829, 'learning_rate': 2.9939e-05, 'epoch': 0.09}
+
+[WARNING|2025-02-04 08:28:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:28:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:29:03] logging.py:157 >> {'loss': 0.0730, 'learning_rate': 2.9756e-05, 'epoch': 0.17}
+
+[WARNING|2025-02-04 08:29:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:46] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:29:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:29:56] logging.py:157 >> {'loss': 0.0680, 'learning_rate': 2.9453e-05, 'epoch': 0.26}
+
+[WARNING|2025-02-04 08:29:56] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:30:48] logging.py:157 >> {'loss': 0.0603, 'learning_rate': 2.9033e-05, 'epoch': 0.34}
+
+[WARNING|2025-02-04 08:30:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:30:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:31:41] logging.py:157 >> {'loss': 0.0617, 'learning_rate': 2.8498e-05, 'epoch': 0.43}
+
+[WARNING|2025-02-04 08:31:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:46] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:31:56] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:32:31] logging.py:157 >> {'loss': 0.0617, 'learning_rate': 2.7853e-05, 'epoch': 0.52}
+
+[WARNING|2025-02-04 08:32:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:36] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:46] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:32:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:33:22] logging.py:157 >> {'loss': 0.0587, 'learning_rate': 2.7103e-05, 'epoch': 0.60}
+
+[WARNING|2025-02-04 08:33:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:33:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:34:14] logging.py:157 >> {'loss': 0.0555, 'learning_rate': 2.6255e-05, 'epoch': 0.69}
+
+[WARNING|2025-02-04 08:34:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:46] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:34:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:35:07] logging.py:157 >> {'loss': 0.0538, 'learning_rate': 2.5315e-05, 'epoch': 0.77}
+
+[WARNING|2025-02-04 08:35:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:44] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:35:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:35:59] logging.py:157 >> {'loss': 0.0466, 'learning_rate': 2.4292e-05, 'epoch': 0.86}
+
+[WARNING|2025-02-04 08:35:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:15] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:36:50] logging.py:157 >> {'loss': 0.0457, 'learning_rate': 2.3192e-05, 'epoch': 0.95}
+
+[WARNING|2025-02-04 08:36:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:36:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:05] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:15] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:37:40] logging.py:157 >> {'loss': 0.0491, 'learning_rate': 2.2026e-05, 'epoch': 1.03}
+
+[WARNING|2025-02-04 08:37:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:37:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:38:32] logging.py:157 >> {'loss': 0.0421, 'learning_rate': 2.0803e-05, 'epoch': 1.12}
+
+[WARNING|2025-02-04 08:38:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:39] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:44] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:38:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:05] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:39:25] logging.py:157 >> {'loss': 0.0429, 'learning_rate': 1.9532e-05, 'epoch': 1.20}
+
+[WARNING|2025-02-04 08:39:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:36] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:39:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:40:16] logging.py:157 >> {'loss': 0.0448, 'learning_rate': 1.8225e-05, 'epoch': 1.29}
+
+[WARNING|2025-02-04 08:40:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:40:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:41:08] logging.py:157 >> {'loss': 0.0439, 'learning_rate': 1.6891e-05, 'epoch': 1.38}
+
+[WARNING|2025-02-04 08:41:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:41:56] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:42:00] logging.py:157 >> {'loss': 0.0432, 'learning_rate': 1.5542e-05, 'epoch': 1.46}
+
+[WARNING|2025-02-04 08:42:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:42:53] logging.py:157 >> {'loss': 0.0384, 'learning_rate': 1.4188e-05, 'epoch': 1.55}
+
+[WARNING|2025-02-04 08:42:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:42:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:43:44] logging.py:157 >> {'loss': 0.0415, 'learning_rate': 1.2841e-05, 'epoch': 1.63}
+
+[WARNING|2025-02-04 08:43:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:43:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:44:37] logging.py:157 >> {'loss': 0.0419, 'learning_rate': 1.1511e-05, 'epoch': 1.72}
+
+[WARNING|2025-02-04 08:44:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:49] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:44:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:45:28] logging.py:157 >> {'loss': 0.0431, 'learning_rate': 1.0210e-05, 'epoch': 1.81}
+
+[WARNING|2025-02-04 08:45:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:51] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:45:56] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:46:21] logging.py:157 >> {'loss': 0.0389, 'learning_rate': 8.9485e-06, 'epoch': 1.89}
+
+[WARNING|2025-02-04 08:46:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:46:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:03] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:47:12] logging.py:157 >> {'loss': 0.0422, 'learning_rate': 7.7358e-06, 'epoch': 1.98}
+
+[WARNING|2025-02-04 08:47:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:25] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:47:56] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:48:04] logging.py:157 >> {'loss': 0.0337, 'learning_rate': 6.5822e-06, 'epoch': 2.06}
+
+[WARNING|2025-02-04 08:48:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:48:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:48:56] logging.py:157 >> {'loss': 0.0354, 'learning_rate': 5.4972e-06, 'epoch': 2.15}
+
+[WARNING|2025-02-04 08:48:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:15] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:20] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:36] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:41] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:49:49] logging.py:157 >> {'loss': 0.0375, 'learning_rate': 4.4896e-06, 'epoch': 2.24}
+
+[WARNING|2025-02-04 08:49:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:49:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:28] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:50:40] logging.py:157 >> {'loss': 0.0296, 'learning_rate': 3.5676e-06, 'epoch': 2.32}
+
+[WARNING|2025-02-04 08:50:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:54] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:50:59] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:05] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:10] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:15] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:51:34] logging.py:157 >> {'loss': 0.0326, 'learning_rate': 2.7387e-06, 'epoch': 2.41}
+
+[WARNING|2025-02-04 08:51:36] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:51:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:07] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:12] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:17] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:52:25] logging.py:157 >> {'loss': 0.0370, 'learning_rate': 2.0096e-06, 'epoch': 2.49}
+
+[WARNING|2025-02-04 08:52:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:33] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:38] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:52:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:53:17] logging.py:157 >> {'loss': 0.0344, 'learning_rate': 1.3864e-06, 'epoch': 2.58}
+
+[WARNING|2025-02-04 08:53:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:29] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:34] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:53:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:01] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:54:09] logging.py:157 >> {'loss': 0.0382, 'learning_rate': 8.7399e-07, 'epoch': 2.67}
+
+[WARNING|2025-02-04 08:54:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:22] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:27] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:32] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:43] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:48] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:53] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:54:58] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:55:01] logging.py:157 >> {'loss': 0.0332, 'learning_rate': 4.7666e-07, 'epoch': 2.75}
+
+[WARNING|2025-02-04 08:55:04] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:09] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:14] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:19] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:24] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:30] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:35] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:40] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:45] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:55:50] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:55:53] logging.py:157 >> {'loss': 0.0369, 'learning_rate': 1.9760e-07, 'epoch': 2.84}
+
+[WARNING|2025-02-04 08:55:55] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:00] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:06] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:11] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:16] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:21] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:26] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:31] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:37] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:42] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:56:44] logging.py:157 >> {'loss': 0.0361, 'learning_rate': 3.9102e-08, 'epoch': 2.92}
+
+[WARNING|2025-02-04 08:56:47] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:52] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:56:57] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:57:02] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:57:08] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:57:13] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:57:18] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[WARNING|2025-02-04 08:57:23] logging.py:168 >> 'Seq2SeqTrainingArguments' object has no attribute 'average_tokens_across_devices'
+
+[INFO|2025-02-04 08:57:26] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-Nemo-Instruct-2407/lora/mistral-nemo-finetuned/checkpoint-348
+
+[INFO|2025-02-04 08:57:26] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-nemo-instruct-2407-bnb-4bit/snapshots/a8e82a934394c6858f5ee545fa55e1e8cc67065f/config.json
+
+[INFO|2025-02-04 08:57:26] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "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": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "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_fixed": true,
+  "use_cache": true,
+  "vocab_size": 131072
+}
+
+
+[INFO|2025-02-04 08:57:27] <string>:484 >> 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+[INFO|2025-02-04 08:57:27] trainer.py:3801 >> Saving model checkpoint to saves/Mistral-Nemo-Instruct-2407/lora/mistral-nemo-finetuned
+
+[INFO|2025-02-04 08:57:27] configuration_utils.py:679 >> loading configuration file config.json from cache at /home/zeus/.cache/huggingface/hub/models--unsloth--mistral-nemo-instruct-2407-bnb-4bit/snapshots/a8e82a934394c6858f5ee545fa55e1e8cc67065f/config.json
+
+[INFO|2025-02-04 08:57:27] configuration_utils.py:746 >> Model config MistralConfig {
+  "_name_or_path": "mistralai/Mistral-Nemo-Instruct-2407",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "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": [
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection"
+    ],
+    "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_fixed": true,
+  "use_cache": true,
+  "vocab_size": 131072
+}
+
+
+[WARNING|2025-02-04 08:57:27] logging.py:162 >> No metric eval_loss to plot.
+
+[WARNING|2025-02-04 08:57:27] logging.py:162 >> No metric eval_accuracy to plot.
+
+[INFO|2025-02-04 08:57:27] 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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9935483870967743,
+    "total_flos": 2.344956384116736e+17,
+    "train_loss": 0.045667905531737996,
+    "train_runtime": 1808.5239,
+    "train_samples_per_second": 6.164,
+    "train_steps_per_second": 0.192
+}

trainer_log.jsonl

@@ -0,0 +1,35 @@
+{"current_steps": 10, "total_steps": 348, "loss": 0.0829, "lr": 2.9938918800982563e-05, "epoch": 0.08602150537634409, "percentage": 2.87, "elapsed_time": "0:00:54", "remaining_time": "0:30:25"}
+{"current_steps": 20, "total_steps": 348, "loss": 0.073, "lr": 2.975617265898004e-05, "epoch": 0.17204301075268819, "percentage": 5.75, "elapsed_time": "0:01:44", "remaining_time": "0:28:32"}
+{"current_steps": 30, "total_steps": 348, "loss": 0.068, "lr": 2.9453249887788343e-05, "epoch": 0.25806451612903225, "percentage": 8.62, "elapsed_time": "0:02:37", "remaining_time": "0:27:52"}
+{"current_steps": 40, "total_steps": 348, "loss": 0.0603, "lr": 2.9032617538884018e-05, "epoch": 0.34408602150537637, "percentage": 11.49, "elapsed_time": "0:03:30", "remaining_time": "0:26:57"}
+{"current_steps": 50, "total_steps": 348, "loss": 0.0617, "lr": 2.84977013093626e-05, "epoch": 0.43010752688172044, "percentage": 14.37, "elapsed_time": "0:04:22", "remaining_time": "0:26:02"}
+{"current_steps": 60, "total_steps": 348, "loss": 0.0617, "lr": 2.7852857642513838e-05, "epoch": 0.5161290322580645, "percentage": 17.24, "elapsed_time": "0:05:12", "remaining_time": "0:25:01"}
+{"current_steps": 70, "total_steps": 348, "loss": 0.0587, "lr": 2.7103338248251055e-05, "epoch": 0.6021505376344086, "percentage": 20.11, "elapsed_time": "0:06:03", "remaining_time": "0:24:05"}
+{"current_steps": 80, "total_steps": 348, "loss": 0.0555, "lr": 2.6255247332346036e-05, "epoch": 0.6881720430107527, "percentage": 22.99, "elapsed_time": "0:06:55", "remaining_time": "0:23:12"}
+{"current_steps": 90, "total_steps": 348, "loss": 0.0538, "lr": 2.531549188280135e-05, "epoch": 0.7741935483870968, "percentage": 25.86, "elapsed_time": "0:07:48", "remaining_time": "0:22:23"}
+{"current_steps": 100, "total_steps": 348, "loss": 0.0466, "lr": 2.4291725418235848e-05, "epoch": 0.8602150537634409, "percentage": 28.74, "elapsed_time": "0:08:40", "remaining_time": "0:21:31"}
+{"current_steps": 110, "total_steps": 348, "loss": 0.0457, "lr": 2.3192285656405456e-05, "epoch": 0.946236559139785, "percentage": 31.61, "elapsed_time": "0:09:31", "remaining_time": "0:20:36"}
+{"current_steps": 120, "total_steps": 348, "loss": 0.0491, "lr": 2.2026126610496852e-05, "epoch": 1.032258064516129, "percentage": 34.48, "elapsed_time": "0:10:21", "remaining_time": "0:19:41"}
+{"current_steps": 130, "total_steps": 348, "loss": 0.0421, "lr": 2.0802745666212592e-05, "epoch": 1.118279569892473, "percentage": 37.36, "elapsed_time": "0:11:14", "remaining_time": "0:18:50"}
+{"current_steps": 140, "total_steps": 348, "loss": 0.0429, "lr": 1.953210623354359e-05, "epoch": 1.2043010752688172, "percentage": 40.23, "elapsed_time": "0:12:06", "remaining_time": "0:17:59"}
+{"current_steps": 150, "total_steps": 348, "loss": 0.0448, "lr": 1.8224556603165363e-05, "epoch": 1.2903225806451613, "percentage": 43.1, "elapsed_time": "0:12:57", "remaining_time": "0:17:06"}
+{"current_steps": 160, "total_steps": 348, "loss": 0.0439, "lr": 1.689074566830434e-05, "epoch": 1.3763440860215055, "percentage": 45.98, "elapsed_time": "0:13:49", "remaining_time": "0:16:14"}
+{"current_steps": 170, "total_steps": 348, "loss": 0.0432, "lr": 1.5541536198449044e-05, "epoch": 1.4623655913978495, "percentage": 48.85, "elapsed_time": "0:14:41", "remaining_time": "0:15:23"}
+{"current_steps": 180, "total_steps": 348, "loss": 0.0384, "lr": 1.4187916371218739e-05, "epoch": 1.5483870967741935, "percentage": 51.72, "elapsed_time": "0:15:34", "remaining_time": "0:14:31"}
+{"current_steps": 190, "total_steps": 348, "loss": 0.0415, "lr": 1.2840910282888211e-05, "epoch": 1.6344086021505375, "percentage": 54.6, "elapsed_time": "0:16:25", "remaining_time": "0:13:39"}
+{"current_steps": 200, "total_steps": 348, "loss": 0.0419, "lr": 1.1511488166385349e-05, "epoch": 1.7204301075268817, "percentage": 57.47, "elapsed_time": "0:17:18", "remaining_time": "0:12:48"}
+{"current_steps": 210, "total_steps": 348, "loss": 0.0431, "lr": 1.0210477047960303e-05, "epoch": 1.8064516129032258, "percentage": 60.34, "elapsed_time": "0:18:10", "remaining_time": "0:11:56"}
+{"current_steps": 220, "total_steps": 348, "loss": 0.0389, "lr": 8.948472570152874e-06, "epoch": 1.89247311827957, "percentage": 63.22, "elapsed_time": "0:19:02", "remaining_time": "0:11:04"}
+{"current_steps": 230, "total_steps": 348, "loss": 0.0422, "lr": 7.735752699185711e-06, "epoch": 1.978494623655914, "percentage": 66.09, "elapsed_time": "0:19:53", "remaining_time": "0:10:12"}
+{"current_steps": 240, "total_steps": 348, "loss": 0.0337, "lr": 6.582194019564266e-06, "epoch": 2.064516129032258, "percentage": 68.97, "elapsed_time": "0:20:45", "remaining_time": "0:09:20"}
+{"current_steps": 250, "total_steps": 348, "loss": 0.0354, "lr": 5.497191297593647e-06, "epoch": 2.150537634408602, "percentage": 71.84, "elapsed_time": "0:21:37", "remaining_time": "0:08:28"}
+{"current_steps": 260, "total_steps": 348, "loss": 0.0375, "lr": 4.4895809688998655e-06, "epoch": 2.236559139784946, "percentage": 74.71, "elapsed_time": "0:22:31", "remaining_time": "0:07:37"}
+{"current_steps": 270, "total_steps": 348, "loss": 0.0296, "lr": 3.567569173085455e-06, "epoch": 2.3225806451612905, "percentage": 77.59, "elapsed_time": "0:23:22", "remaining_time": "0:06:45"}
+{"current_steps": 280, "total_steps": 348, "loss": 0.0326, "lr": 2.7386649216166233e-06, "epoch": 2.4086021505376345, "percentage": 80.46, "elapsed_time": "0:24:15", "remaining_time": "0:05:53"}
+{"current_steps": 290, "total_steps": 348, "loss": 0.037, "lr": 2.0096189432334194e-06, "epoch": 2.4946236559139785, "percentage": 83.33, "elapsed_time": "0:25:06", "remaining_time": "0:05:01"}
+{"current_steps": 300, "total_steps": 348, "loss": 0.0344, "lr": 1.3863687049356465e-06, "epoch": 2.5806451612903225, "percentage": 86.21, "elapsed_time": "0:25:58", "remaining_time": "0:04:09"}
+{"current_steps": 310, "total_steps": 348, "loss": 0.0382, "lr": 8.7399005630238e-07, "epoch": 2.6666666666666665, "percentage": 89.08, "elapsed_time": "0:26:50", "remaining_time": "0:03:17"}
+{"current_steps": 320, "total_steps": 348, "loss": 0.0332, "lr": 4.766558909615504e-07, "epoch": 2.752688172043011, "percentage": 91.95, "elapsed_time": "0:27:42", "remaining_time": "0:02:25"}
+{"current_steps": 330, "total_steps": 348, "loss": 0.0369, "lr": 1.9760216187710788e-07, "epoch": 2.838709677419355, "percentage": 94.83, "elapsed_time": "0:28:34", "remaining_time": "0:01:33"}
+{"current_steps": 340, "total_steps": 348, "loss": 0.0361, "lr": 3.910152723075322e-08, "epoch": 2.924731182795699, "percentage": 97.7, "elapsed_time": "0:29:26", "remaining_time": "0:00:41"}
+{"current_steps": 348, "total_steps": 348, "epoch": 2.9935483870967743, "percentage": 100.0, "elapsed_time": "0:30:08", "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": 0.4689747393131256,
+      "learning_rate": 2.9938918800982563e-05,
+      "loss": 0.0829,
+      "step": 10
+    },
+    {
+      "epoch": 0.17204301075268819,
+      "grad_norm": 0.31903743743896484,
+      "learning_rate": 2.975617265898004e-05,
+      "loss": 0.073,
+      "step": 20
+    },
+    {
+      "epoch": 0.25806451612903225,
+      "grad_norm": 0.3387955129146576,
+      "learning_rate": 2.9453249887788343e-05,
+      "loss": 0.068,
+      "step": 30
+    },
+    {
+      "epoch": 0.34408602150537637,
+      "grad_norm": 0.33919498324394226,
+      "learning_rate": 2.9032617538884018e-05,
+      "loss": 0.0603,
+      "step": 40
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 0.33728891611099243,
+      "learning_rate": 2.84977013093626e-05,
+      "loss": 0.0617,
+      "step": 50
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 0.30449143052101135,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 0.0617,
+      "step": 60
+    },
+    {
+      "epoch": 0.6021505376344086,
+      "grad_norm": 0.3293665945529938,
+      "learning_rate": 2.7103338248251055e-05,
+      "loss": 0.0587,
+      "step": 70
+    },
+    {
+      "epoch": 0.6881720430107527,
+      "grad_norm": 0.4717239737510681,
+      "learning_rate": 2.6255247332346036e-05,
+      "loss": 0.0555,
+      "step": 80
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.4681776463985443,
+      "learning_rate": 2.531549188280135e-05,
+      "loss": 0.0538,
+      "step": 90
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.33837395906448364,
+      "learning_rate": 2.4291725418235848e-05,
+      "loss": 0.0466,
+      "step": 100
+    },
+    {
+      "epoch": 0.946236559139785,
+      "grad_norm": 0.3245820999145508,
+      "learning_rate": 2.3192285656405456e-05,
+      "loss": 0.0457,
+      "step": 110
+    },
+    {
+      "epoch": 1.032258064516129,
+      "grad_norm": 0.34947386384010315,
+      "learning_rate": 2.2026126610496852e-05,
+      "loss": 0.0491,
+      "step": 120
+    },
+    {
+      "epoch": 1.118279569892473,
+      "grad_norm": 0.359684020280838,
+      "learning_rate": 2.0802745666212592e-05,
+      "loss": 0.0421,
+      "step": 130
+    },
+    {
+      "epoch": 1.2043010752688172,
+      "grad_norm": 0.3907443583011627,
+      "learning_rate": 1.953210623354359e-05,
+      "loss": 0.0429,
+      "step": 140
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.40398046374320984,
+      "learning_rate": 1.8224556603165363e-05,
+      "loss": 0.0448,
+      "step": 150
+    },
+    {
+      "epoch": 1.3763440860215055,
+      "grad_norm": 0.40687504410743713,
+      "learning_rate": 1.689074566830434e-05,
+      "loss": 0.0439,
+      "step": 160
+    },
+    {
+      "epoch": 1.4623655913978495,
+      "grad_norm": 0.7241388559341431,
+      "learning_rate": 1.5541536198449044e-05,
+      "loss": 0.0432,
+      "step": 170
+    },
+    {
+      "epoch": 1.5483870967741935,
+      "grad_norm": 0.3367048501968384,
+      "learning_rate": 1.4187916371218739e-05,
+      "loss": 0.0384,
+      "step": 180
+    },
+    {
+      "epoch": 1.6344086021505375,
+      "grad_norm": 0.27823126316070557,
+      "learning_rate": 1.2840910282888211e-05,
+      "loss": 0.0415,
+      "step": 190
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.3167360723018646,
+      "learning_rate": 1.1511488166385349e-05,
+      "loss": 0.0419,
+      "step": 200
+    },
+    {
+      "epoch": 1.8064516129032258,
+      "grad_norm": 0.3927469849586487,
+      "learning_rate": 1.0210477047960303e-05,
+      "loss": 0.0431,
+      "step": 210
+    },
+    {
+      "epoch": 1.89247311827957,
+      "grad_norm": 0.3293432891368866,
+      "learning_rate": 8.948472570152874e-06,
+      "loss": 0.0389,
+      "step": 220
+    },
+    {
+      "epoch": 1.978494623655914,
+      "grad_norm": 0.4683464765548706,
+      "learning_rate": 7.735752699185711e-06,
+      "loss": 0.0422,
+      "step": 230
+    },
+    {
+      "epoch": 2.064516129032258,
+      "grad_norm": 0.33360326290130615,
+      "learning_rate": 6.582194019564266e-06,
+      "loss": 0.0337,
+      "step": 240
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 0.4784548878669739,
+      "learning_rate": 5.497191297593647e-06,
+      "loss": 0.0354,
+      "step": 250
+    },
+    {
+      "epoch": 2.236559139784946,
+      "grad_norm": 0.442839652299881,
+      "learning_rate": 4.4895809688998655e-06,
+      "loss": 0.0375,
+      "step": 260
+    },
+    {
+      "epoch": 2.3225806451612905,
+      "grad_norm": 0.3498876690864563,
+      "learning_rate": 3.567569173085455e-06,
+      "loss": 0.0296,
+      "step": 270
+    },
+    {
+      "epoch": 2.4086021505376345,
+      "grad_norm": 0.6078402400016785,
+      "learning_rate": 2.7386649216166233e-06,
+      "loss": 0.0326,
+      "step": 280
+    },
+    {
+      "epoch": 2.4946236559139785,
+      "grad_norm": 0.5483068227767944,
+      "learning_rate": 2.0096189432334194e-06,
+      "loss": 0.037,
+      "step": 290
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.29595789313316345,
+      "learning_rate": 1.3863687049356465e-06,
+      "loss": 0.0344,
+      "step": 300
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.3882715702056885,
+      "learning_rate": 8.7399005630238e-07,
+      "loss": 0.0382,
+      "step": 310
+    },
+    {
+      "epoch": 2.752688172043011,
+      "grad_norm": 0.3592262864112854,
+      "learning_rate": 4.766558909615504e-07,
+      "loss": 0.0332,
+      "step": 320
+    },
+    {
+      "epoch": 2.838709677419355,
+      "grad_norm": 0.42720264196395874,
+      "learning_rate": 1.9760216187710788e-07,
+      "loss": 0.0369,
+      "step": 330
+    },
+    {
+      "epoch": 2.924731182795699,
+      "grad_norm": 0.34159648418426514,
+      "learning_rate": 3.910152723075322e-08,
+      "loss": 0.0361,
+      "step": 340
+    },
+    {
+      "epoch": 2.9935483870967743,
+      "step": 348,
+      "total_flos": 2.344956384116736e+17,
+      "train_loss": 0.045667905531737996,
+      "train_runtime": 1808.5239,
+      "train_samples_per_second": 6.164,
+      "train_steps_per_second": 0.192
+    }
+  ],
+  "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": 2.344956384116736e+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 sha256:581e11ecdf29838856a4d9fd37fef831aae8f22c808c0cf81d6fced7208a6071
+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-Nemo-Instruct-2407
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Mistral-Nemo-Instruct-2407/lora/mistral-nemo-finetuned
+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