Training in progress, step 47

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "gate_up_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea74090dfed8c6d164aa09249c830408b3e55ce3afa4d8bc6c464f7830df28b
+size 23102912

runs/Jun09_11-17-48_77b1a6bc4b2b/events.out.tfevents.1749468138.77b1a6bc4b2b.3916.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1f76a811dd93d84ac8424c2c023c531214d9836eace60c48ed034236c6b7ae
+size 8280

runs/Jun09_11-23-53_77b1a6bc4b2b/events.out.tfevents.1749468289.77b1a6bc4b2b.5547.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fdf1a0043681ab5abe5567264aaa3af78f74d07cf74bf2ccd26ddf32000504f
+size 8280

runs/Jun09_11-26-25_77b1a6bc4b2b/events.out.tfevents.1749468443.77b1a6bc4b2b.6352.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9549ac1aae5145806a7522c293fafd2152d17180a3160a39ef1ebc6239e1ee83
+size 18692

runs/Jun09_11-38-43_77b1a6bc4b2b/events.out.tfevents.1749469179.77b1a6bc4b2b.9319.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8271dfa66f2ec80762fc93f69b23e36397db3f7be411bf3cad13b9aeee9f3d22
+size 8963

runs/Jun09_11-40-49_77b1a6bc4b2b/events.out.tfevents.1749469314.77b1a6bc4b2b.10269.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a7919af45cc8c36c2e29afba15e3cb66f20d3dec837cac463ec3f3a69dd053b
+size 18625

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc2a16d487ee4eb18f1568d858e31bcced6df199ba88038b72988874d54d69d0
+size 7544

training_config.json

@@ -0,0 +1,93 @@
+{
+  "experiment_key": "base",
+  "save_safetensors": true,
+  "max_shard_size": "10GB",
+  "local_rank": 0,
+  "use_gradient_checkpointing": true,
+  "trainer_key": "lm",
+  "force_fp32": false,
+  "force_fp16": false,
+  "from_gptq": false,
+  "huggingface_hub_token": null,
+  "single_gpu": true,
+  "master_port": 9994,
+  "deepspeed_stage": "stage_2",
+  "deepspeed_config_path": null,
+  "fsdp_strategy": "",
+  "fsdp_offload": true,
+  "seed": 42,
+  "stabilize": false,
+  "norm_fp32": false,
+  "path_to_env_file": "./.env",
+  "prepare_dataset": true,
+  "lora_hub_model_id": null,
+  "lora_model_local_path": null,
+  "fused_model_local_path": null,
+  "fuse_after_training": false,
+  "quantization_dataset_id": null,
+  "quantization_max_samples": 1024,
+  "quantized_model_path": "./quantized_model/",
+  "quantized_hub_model_id": null,
+  "quantized_hub_private_repo": true,
+  "dataset_key": "soda",
+  "train_local_path_to_data": "./train.jsonl",
+  "eval_local_path_to_data": null,
+  "shuffle": true,
+  "max_eval_samples": 1000,
+  "add_eval_to_train_if_no_path": false,
+  "tokenizer_name_or_path": null,
+  "tokenizer_use_fast": null,
+  "tokenizer_padding_side": null,
+  "collator_key": "lm",
+  "max_length": 2048,
+  "model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "push_to_hub_bos_add_bos_token": false,
+  "use_flash_attention_2": false,
+  "trust_remote_code": false,
+  "device_map": null,
+  "prepare_model_for_kbit_training": true,
+  "offload_folder": null,
+  "load_in_8bit": false,
+  "load_in_4bit": true,
+  "llm_int8_threshold": 6.0,
+  "llm_int8_has_fp16_weight": true,
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_quantize_after_model_init": false,
+  "gptq_bits": 4,
+  "gptq_group_size": 128,
+  "gptq_disable_exllama": true,
+  "apply_lora": true,
+  "lora_rank": 8,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "raw_lora_target_modules": "all",
+  "output_dir": "./outputs/",
+  "per_device_train_batch_size": 2,
+  "do_eval": false,
+  "per_device_eval_batch_size": null,
+  "gradient_accumulation_steps": 2,
+  "eval_accumulation_steps": null,
+  "eval_delay": 0,
+  "eval_steps": 1000,
+  "warmup_steps": 5,
+  "max_steps": 47,
+  "num_train_epochs": 1,
+  "learning_rate": 0.0002,
+  "max_grad_norm": 1.0,
+  "weight_decay": 0.001,
+  "label_smoothing_factor": 0.0,
+  "logging_steps": 1,
+  "save_steps": 50,
+  "save_total_limit": 1,
+  "optim": "paged_adamw_8bit",
+  "push_to_hub": true,
+  "hub_model_id": "Demo-LoRA",
+  "hub_private_repo": false,
+  "neftune_noise_alpha": null,
+  "project_name": null,
+  "report_to_wandb": false,
+  "wandb_api_key": null,
+  "wandb_project": null,
+  "wandb_entity": null
+}