End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,166 @@
+---
+library_name: peft
+license: mit
+base_model: fxmarty/tiny-random-GemmaForCausalLM
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 922da73d-0a26-4f27-a883-0f02b8fbbb93
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+accelerate_config:
+  dynamo_backend: inductor
+  mixed_precision: bf16
+  num_machines: 1
+  num_processes: auto
+  use_cpu: false
+adapter: lora
+base_model: fxmarty/tiny-random-GemmaForCausalLM
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 9845ef35490c4ed8_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/9845ef35490c4ed8_train_data.json
+  type:
+    field_instruction: option_0
+    field_output: text
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+early_stopping_patience: null
+eval_max_new_tokens: 128
+eval_table_size: null
+evals_per_epoch: 4
+flash_attention: false
+fp16: null
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 16
+gradient_checkpointing: true
+group_by_length: false
+hub_model_id: null
+hub_repo: null
+hub_strategy: checkpoint
+hub_token: null
+learning_rate: 0.0001
+local_rank: null
+logging_steps: 1
+lora_alpha: 16
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 8
+lora_target_linear: true
+lora_target_modules:
+- q_proj
+- v_proj
+lr_scheduler: cosine
+max_memory:
+  0: 70GiB
+max_steps: 100
+micro_batch_size: 2
+mlflow_experiment_name: /tmp/9845ef35490c4ed8_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 1
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+quantization_config:
+  llm_int8_enable_fp32_cpu_offload: true
+  load_in_8bit: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+saves_per_epoch: 4
+sequence_len: 512
+strict: false
+tf32: false
+tokenizer_type: AutoTokenizer
+torch_compile: true
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 922da73d-0a26-4f27-a883-0f02b8fbbb93
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: 922da73d-0a26-4f27-a883-0f02b8fbbb93
+warmup_steps: 10
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 922da73d-0a26-4f27-a883-0f02b8fbbb93
+
+This model is a fine-tuned version of [fxmarty/tiny-random-GemmaForCausalLM](https://huggingface.co/fxmarty/tiny-random-GemmaForCausalLM) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: nan
+
+## 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: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 100
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.0           | 0.0004 | 1    | nan             |
+| 0.0           | 0.0112 | 25   | nan             |
+| 0.0           | 0.0225 | 50   | nan             |
+| 0.0           | 0.0337 | 75   | nan             |
+| 0.0           | 0.0450 | 100  | nan             |
+
+
+### Framework versions
+
+- PEFT 0.13.2
+- Transformers 4.46.0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.1
+- Tokenizers 0.20.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "fxmarty/tiny-random-GemmaForCausalLM",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddb3041c60d7f90f1133d3cc75f1f5aca7bff3f43bbf565c18e1bcb00efcfca
+size 14424

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74cf4e09c5ed83bb82d0e7d8e3d6d510d96367ff96a844212b7de14580c5266
+size 10624

config.json

@@ -0,0 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "fxmarty/tiny-random-GemmaForCausalLM",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 8,
+  "hidden_act": "gelu",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 2,
+  "max_position_embeddings": 512,
+  "model_type": "gemma",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.0",
+  "use_cache": false,
+  "vocab_size": 256000
+}

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: fxmarty/tiny-random-GemmaForCausalLM
+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 0.13.2

last-checkpoint/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "fxmarty/tiny-random-GemmaForCausalLM",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b74cf4e09c5ed83bb82d0e7d8e3d6d510d96367ff96a844212b7de14580c5266
+size 10624

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fb16a3af30e4d341b749cc7197d9b94b3ed1a9aaf643e8d767177d3ac2a8cd
+size 26498

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d908c46d108238ef38ce2d6b400da8ee470558ac3166d90b6b5a4ef218316d
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63c485bbbab0efcfc1ffe32fd177108a9f70be1875ea3aacad3c4f064a5974b
+size 34315097

last-checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,773 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04496023828926293,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00044960238289262934,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.00044960238289262934,
+      "eval_loss": NaN,
+      "eval_runtime": 38.0764,
+      "eval_samples_per_second": 98.407,
+      "eval_steps_per_second": 49.217,
+      "step": 1
+    },
+    {
+      "epoch": 0.0008992047657852587,
+      "grad_norm": NaN,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.001348807148677888,
+      "grad_norm": NaN,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.0017984095315705174,
+      "grad_norm": NaN,
+      "learning_rate": 4e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0022480119144631465,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.002697614297355776,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0031472166802484053,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0035968190631410347,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.004046421446033664,
+      "grad_norm": NaN,
+      "learning_rate": 9e-05,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.004496023828926293,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0049456262118189225,
+      "grad_norm": NaN,
+      "learning_rate": 9.99695413509548e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.005395228594711552,
+      "grad_norm": NaN,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.005844830977604181,
+      "grad_norm": NaN,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.006294433360496811,
+      "grad_norm": NaN,
+      "learning_rate": 9.951340343707852e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.00674403574338944,
+      "grad_norm": NaN,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0071936381262820695,
+      "grad_norm": NaN,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.007643240509174699,
+      "grad_norm": NaN,
+      "learning_rate": 9.851478631379982e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.008092842892067327,
+      "grad_norm": NaN,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.008542445274959957,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.008992047657852586,
+      "grad_norm": NaN,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.009441650040745216,
+      "grad_norm": NaN,
+      "learning_rate": 9.635919272833938e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.009891252423637845,
+      "grad_norm": NaN,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.010340854806530474,
+      "grad_norm": NaN,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.010790457189423104,
+      "grad_norm": NaN,
+      "learning_rate": 9.414737964294636e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.011240059572315733,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.011240059572315733,
+      "eval_loss": NaN,
+      "eval_runtime": 13.6049,
+      "eval_samples_per_second": 275.415,
+      "eval_steps_per_second": 137.744,
+      "step": 25
+    },
+    {
+      "epoch": 0.011689661955208363,
+      "grad_norm": NaN,
+      "learning_rate": 9.24024048078213e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.012139264338100992,
+      "grad_norm": NaN,
+      "learning_rate": 9.145187862775209e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.012588866720993621,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.01303846910388625,
+      "grad_norm": NaN,
+      "learning_rate": 8.940053768033609e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.01348807148677888,
+      "grad_norm": NaN,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.01393767386967151,
+      "grad_norm": NaN,
+      "learning_rate": 8.715724127386972e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.014387276252564139,
+      "grad_norm": NaN,
+      "learning_rate": 8.596699001693255e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.014836878635456768,
+      "grad_norm": NaN,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.015286481018349398,
+      "grad_norm": NaN,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 0.015736083401242027,
+      "grad_norm": NaN,
+      "learning_rate": 8.213938048432697e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.016185685784134655,
+      "grad_norm": NaN,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.016635288167027286,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 0.017084890549919914,
+      "grad_norm": NaN,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 0.017534492932812545,
+      "grad_norm": NaN,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.017984095315705172,
+      "grad_norm": NaN,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.018433697698597803,
+      "grad_norm": NaN,
+      "learning_rate": 7.347357813929454e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.01888330008149043,
+      "grad_norm": NaN,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.019332902464383062,
+      "grad_norm": NaN,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.01978250484727569,
+      "grad_norm": NaN,
+      "learning_rate": 6.873032967079561e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.02023210723016832,
+      "grad_norm": NaN,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.02068170961306095,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.02113131199595358,
+      "grad_norm": NaN,
+      "learning_rate": 6.378186779084995e-05,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.021580914378846208,
+      "grad_norm": NaN,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.02203051676173884,
+      "grad_norm": NaN,
+      "learning_rate": 6.0395584540887963e-05,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.022480119144631466,
+      "grad_norm": NaN,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.022480119144631466,
+      "eval_loss": NaN,
+      "eval_runtime": 13.5404,
+      "eval_samples_per_second": 276.728,
+      "eval_steps_per_second": 138.401,
+      "step": 50
+    },
+    {
+      "epoch": 0.022929721527524097,
+      "grad_norm": NaN,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.023379323910416725,
+      "grad_norm": NaN,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.0,
+      "step": 52
+    },
+    {
+      "epoch": 0.023828926293309356,
+      "grad_norm": NaN,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 0.0,
+      "step": 53
+    },
+    {
+      "epoch": 0.024278528676201984,
+      "grad_norm": NaN,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.02472813105909461,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 55
+    },
+    {
+      "epoch": 0.025177733441987243,
+      "grad_norm": NaN,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.0,
+      "step": 56
+    },
+    {
+      "epoch": 0.02562733582487987,
+      "grad_norm": NaN,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.0260769382077725,
+      "grad_norm": NaN,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.0,
+      "step": 58
+    },
+    {
+      "epoch": 0.02652654059066513,
+      "grad_norm": NaN,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 0.0,
+      "step": 59
+    },
+    {
+      "epoch": 0.02697614297355776,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.027425745356450388,
+      "grad_norm": NaN,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 0.0,
+      "step": 61
+    },
+    {
+      "epoch": 0.02787534773934302,
+      "grad_norm": NaN,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.0,
+      "step": 62
+    },
+    {
+      "epoch": 0.028324950122235647,
+      "grad_norm": NaN,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 0.0,
+      "step": 63
+    },
+    {
+      "epoch": 0.028774552505128278,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 64
+    },
+    {
+      "epoch": 0.029224154888020906,
+      "grad_norm": NaN,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0,
+      "step": 65
+    },
+    {
+      "epoch": 0.029673757270913537,
+      "grad_norm": NaN,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.030123359653806164,
+      "grad_norm": NaN,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 0.0,
+      "step": 67
+    },
+    {
+      "epoch": 0.030572962036698795,
+      "grad_norm": NaN,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.0,
+      "step": 68
+    },
+    {
+      "epoch": 0.031022564419591423,
+      "grad_norm": NaN,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.031472166802484054,
+      "grad_norm": NaN,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.03192176918537668,
+      "grad_norm": NaN,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 0.0,
+      "step": 71
+    },
+    {
+      "epoch": 0.03237137156826931,
+      "grad_norm": NaN,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.032820973951161944,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 73
+    },
+    {
+      "epoch": 0.03327057633405457,
+      "grad_norm": NaN,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.0,
+      "step": 74
+    },
+    {
+      "epoch": 0.0337201787169472,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.0337201787169472,
+      "eval_loss": NaN,
+      "eval_runtime": 10.0776,
+      "eval_samples_per_second": 371.813,
+      "eval_steps_per_second": 185.956,
+      "step": 75
+    },
+    {
+      "epoch": 0.03416978109983983,
+      "grad_norm": NaN,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.0,
+      "step": 76
+    },
+    {
+      "epoch": 0.03461938348273246,
+      "grad_norm": NaN,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.0,
+      "step": 77
+    },
+    {
+      "epoch": 0.03506898586562509,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.03551858824851772,
+      "grad_norm": NaN,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.0,
+      "step": 79
+    },
+    {
+      "epoch": 0.035968190631410345,
+      "grad_norm": NaN,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.03641779301430297,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.03686739539719561,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 82
+    },
+    {
+      "epoch": 0.037316997780088235,
+      "grad_norm": NaN,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.0,
+      "step": 83
+    },
+    {
+      "epoch": 0.03776660016298086,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.03821620254587349,
+      "grad_norm": NaN,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 85
+    },
+    {
+      "epoch": 0.038665804928766125,
+      "grad_norm": NaN,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.0,
+      "step": 86
+    },
+    {
+      "epoch": 0.03911540731165875,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.03956500969455138,
+      "grad_norm": NaN,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.0,
+      "step": 88
+    },
+    {
+      "epoch": 0.04001461207744401,
+      "grad_norm": NaN,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.0,
+      "step": 89
+    },
+    {
+      "epoch": 0.04046421446033664,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.04091381684322927,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.0413634192261219,
+      "grad_norm": NaN,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.041813021609014525,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.04226262399190716,
+      "grad_norm": NaN,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.04271222637479979,
+      "grad_norm": NaN,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.043161828757692415,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.04361143114058504,
+      "grad_norm": NaN,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.04406103352347768,
+      "grad_norm": NaN,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.044510635906370305,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.04496023828926293,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.04496023828926293,
+      "eval_loss": NaN,
+      "eval_runtime": 6.0311,
+      "eval_samples_per_second": 621.278,
+      "eval_steps_per_second": 310.722,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 51433046016.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0e6c58b0e91a062fb2c395c9030842fd543bce0abddf7bede1cdd2db06fcbe
+size 6776

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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:a63c485bbbab0efcfc1ffe32fd177108a9f70be1875ea3aacad3c4f064a5974b
+size 34315097

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c0e6c58b0e91a062fb2c395c9030842fd543bce0abddf7bede1cdd2db06fcbe
+size 6776