Training in progress, step 1640

.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

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Mistral-Nemo-Instruct-2407",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj",
+    "k_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:f5c133cbae1bf24ff38ab2204204c17ce35bf25e5f51ddc26ab53af3ce673b47
+size 1824599104

axolotl_config.yaml

@@ -0,0 +1,58 @@
+adapter: lora
+base_model: unsloth/Mistral-Nemo-Instruct-2407
+batch_size: 64
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- format: custom
+  path: https://gradients.s3.eu-north-1.amazonaws.com/770e7d1149f051d4_train_data.json?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVVZOOA7SA4UOFLPI%2F20250210%2Feu-north-1%2Fs3%2Faws4_request&X-Amz-Date=20250210T085315Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=5f8e3f412d280dc0a512928601968f5a64f92fcb369fa357d24c2803630144c2
+  type:
+    field_input: context
+    field_instruction: instruction
+    field_output: response
+    format: '{instruction} {input}'
+    no_input_format: '{instruction}'
+    system_format: '{system}'
+    system_prompt: ''
+device_map: auto
+eval_sample_packing: false
+eval_steps: 0.1
+flash_attention: true
+gradient_checkpointing: true
+group_by_length: true
+hub_model_id: SystemAdmin123/3cdbdb76-a3d3-4c38-abe0-1eb63d76d0b0
+hub_strategy: checkpoint
+learning_rate: 0.0001
+logging_steps: 10
+lora_alpha: 256
+lora_dropout: 0.1
+lora_r: 128
+lora_target_linear: true
+lr_scheduler: cosine
+max_steps: 11200
+micro_batch_size: 1
+model_type: AutoModelForCausalLM
+num_epochs: 10000
+optimizer: adamw_bnb_8bit
+output_dir: /root/.sn56/axolotl/tmp/3cdbdb76-a3d3-4c38-abe0-1eb63d76d0b0
+pad_to_sequence_len: true
+resize_token_embeddings_to_32x: false
+sample_packing: true
+save_steps: 40
+save_total_limit: 1
+sequence_len: 2048
+tokenizer_type: PreTrainedTokenizerFast
+torch_dtype: bf16
+training_args_kwargs:
+  disable_tqdm: true
+  hub_private_repo: true
+  save_only_model: true
+trust_remote_code: true
+val_set_size: 0.01
+wandb_entity: ''
+wandb_mode: online
+wandb_name: unsloth/Mistral-Nemo-Instruct-2407-https://gradients.s3.eu-north-1.amazonaws.com/770e7d1149f051d4_train_data.json?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVVZOOA7SA4UOFLPI%2F20250210%2Feu-north-1%2Fs3%2Faws4_request&X-Amz-Date=20250210T085315Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=5f8e3f412d280dc0a512928601968f5a64f92fcb369fa357d24c2803630144c2
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05

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": "4.47.1",
+  "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 sha256:35bd6400315cdf815af66aa5981001f1f24845cf8dd063dd9fdcfe3f05024997
+size 10808