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 +1,178 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: unsloth/Mistral-Nemo-Instruct-2407
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: 73b25e66-016c-4e72-b14a-6d44193e7dab
+  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
+adapter: lora
+base_model: unsloth/Mistral-Nemo-Instruct-2407
+bf16: auto
+chat_template: llama3
+dataset_prepared_path: null
+datasets:
+- data_files:
+  - 964654e817cd6286_train_data.json
+  ds_type: json
+  format: custom
+  path: /workspace/input_data/964654e817cd6286_train_data.json
+  type:
+    field_instruction: prompt
+    field_output: text
+    format: '{instruction}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+debug: null
+deepspeed: null
+device_map: auto
+do_eval: true
+early_stopping_patience: 2
+eval_batch_size: 4
+eval_max_new_tokens: 128
+eval_steps: 150
+eval_table_size: null
+evals_per_epoch: null
+flash_attention: true
+fp16: false
+fsdp: null
+fsdp_config: null
+gradient_accumulation_steps: 4
+gradient_checkpointing: false
+group_by_length: true
+hub_model_id: baby-dev/73b25e66-016c-4e72-b14a-6d44193e7dab
+hub_repo: null
+hub_strategy: end
+hub_token: null
+learning_rate: 0.0002
+load_in_4bit: false
+load_in_8bit: false
+local_rank: null
+logging_steps: 50
+lora_alpha: 64
+lora_dropout: 0.05
+lora_fan_in_fan_out: null
+lora_model_dir: null
+lora_r: 32
+lora_target_linear: true
+lr_scheduler: constant
+max_grad_norm: 1.0
+max_memory:
+  0: 75GB
+max_steps: 4898
+micro_batch_size: 4
+mlflow_experiment_name: /tmp/964654e817cd6286_train_data.json
+model_type: AutoModelForCausalLM
+num_epochs: 10
+optim_args:
+  adam_beta1: 0.9
+  adam_beta2: 0.95
+  adam_epsilon: 1e-5
+optimizer: adamw_bnb_8bit
+output_dir: miner_id_24
+pad_to_sequence_len: true
+resume_from_checkpoint: null
+s2_attention: null
+sample_packing: false
+save_steps: 150
+saves_per_epoch: null
+sequence_len: 512
+strict: false
+tf32: true
+tokenizer_type: AutoTokenizer
+train_on_inputs: false
+trust_remote_code: true
+val_set_size: 0.05
+wandb_entity: null
+wandb_mode: online
+wandb_name: 55ef476f-abbc-4a55-8a7c-e23d354f83dc
+wandb_project: SN56-41
+wandb_run: your_name
+wandb_runid: 55ef476f-abbc-4a55-8a7c-e23d354f83dc
+warmup_steps: 50
+weight_decay: 0.0
+xformers_attention: null
+
+```
+
+</details><br>
+
+# 73b25e66-016c-4e72-b14a-6d44193e7dab
+
+This model is a fine-tuned version of [unsloth/Mistral-Nemo-Instruct-2407](https://huggingface.co/unsloth/Mistral-Nemo-Instruct-2407) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8360
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_steps: 50
+- training_steps: 4898
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0001 | 1    | 1.0585          |
+| 3.586         | 0.0141 | 150  | 0.8885          |
+| 3.4879        | 0.0282 | 300  | 0.8705          |
+| 3.4871        | 0.0423 | 450  | 0.8649          |
+| 3.4143        | 0.0565 | 600  | 0.8548          |
+| 3.4282        | 0.0706 | 750  | 0.8510          |
+| 3.4107        | 0.0847 | 900  | 0.8489          |
+| 3.4089        | 0.0988 | 1050 | 0.8427          |
+| 3.4357        | 0.1129 | 1200 | 0.8434          |
+| 3.3729        | 0.1270 | 1350 | 0.8426          |
+| 3.3947        | 0.1411 | 1500 | 0.8415          |
+| 3.3947        | 0.1553 | 1650 | 0.8387          |
+| 3.3415        | 0.1694 | 1800 | 0.8400          |
+| 3.3761        | 0.1835 | 1950 | 0.8368          |
+| 3.3649        | 0.1976 | 2100 | 0.8358          |
+| 3.3475        | 0.2117 | 2250 | 0.8358          |
+| 3.3436        | 0.2258 | 2400 | 0.8342          |
+| 3.3446        | 0.2399 | 2550 | 0.8360          |
+| 3.3354        | 0.2541 | 2700 | 0.8360          |
+
+
+### 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": "unsloth/Mistral-Nemo-Instruct-2407",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
+    "o_proj",
+    "gate_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 sha256:38cd6c3f1ae4ea910098ef0000d4060545ff96b20ac622e221605e37c22930d5
+size 456332938

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf69335cbcb1d56e0119325f5f870fa3e99d978623cae76ab5a23902cb597d3
+size 456206152

config.json

@@ -0,0 +1,30 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "unsloth/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,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.0",
+  "unsloth_fixed": true,
+  "use_cache": false,
+  "vocab_size": 131072
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "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:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa30655d0638d6ca1ff47367b91d0a2a3eda736102730177952baa36814be61
+size 6776