Training in progress, step 40

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/tinyllama",
+  "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": [
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "k_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:be4b9db42bafc0797619853c54867f0657d42c174c280399042523803335f875
+size 403743472

axolotl_config.yaml

@@ -0,0 +1,57 @@
+adapter: lora
+base_model: unsloth/tinyllama
+batch_size: 64
+bf16: true
+chat_template: tokenizer_default_fallback_alpaca
+datasets:
+- format: custom
+  path: https://gradients.s3.eu-north-1.amazonaws.com/1619d5c4fda918de_train_data.json?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVVZOOA7SA4UOFLPI%2F20250209%2Feu-north-1%2Fs3%2Faws4_request&X-Amz-Date=20250209T105617Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=02ee79ed43b8e249b18535c8d2b439c262793ee8a3ac4a93e676f23db64fcee9
+  type:
+    field_instruction: input
+    field_output: output
+    format: '{instruction}'
+    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/f9f404f8-0d42-4e2e-892f-c51231bfc8a4
+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: 5
+model_type: AutoModelForCausalLM
+num_epochs: 10000
+optimizer: adamw_bnb_8bit
+output_dir: /root/.sn56/axolotl/tmp/f9f404f8-0d42-4e2e-892f-c51231bfc8a4
+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: LlamaTokenizerFast
+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/tinyllama-https://gradients.s3.eu-north-1.amazonaws.com/1619d5c4fda918de_train_data.json?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVVZOOA7SA4UOFLPI%2F20250209%2Feu-north-1%2Fs3%2Faws4_request&X-Amz-Date=20250209T105617Z&X-Amz-Expires=604800&X-Amz-SignedHeaders=host&X-Amz-Signature=02ee79ed43b8e249b18535c8d2b439c262793ee8a3ac4a93e676f23db64fcee9
+wandb_project: Gradients-On-Demand
+wandb_run: your_name
+wandb_runid: default
+warmup_ratio: 0.05

config.json

@@ -0,0 +1,33 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "unsloth/tinyllama",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.47.1",
+  "unsloth_version": "2024.9",
+  "use_cache": false,
+  "vocab_size": 32000
+}

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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction: ' + message['content'] + '\n\n' }}{% elif message['role'] == 'assistant' %}{{ '### Response: ' + message['content'] + eos_token}}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc543989776dbe8bb3a126b1df4dadb0d0cf94c38d0461f13565424f500a752
+size 7096