Add checkpoint

adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "peft_type": "LORA"}

ckpt_itr_100/adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "peft_type": "LORA", "base_model_name_or_path": "/mnt/ui_copilot/data_rw/finetuning/base/models--meta-llama--Llama-3.3-70B-Instruct", "task_type": "CAUSAL_LM"}

ckpt_itr_100/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59eabc2a2d2380f5c3bc4dd0a9ceffdbb8c3d3c468e155fdb3c5fb349b50ff35
+size 390899394

ckpt_itr_200/adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "peft_type": "LORA", "base_model_name_or_path": "/mnt/ui_copilot/data_rw/finetuning/base/models--meta-llama--Llama-3.3-70B-Instruct", "task_type": "CAUSAL_LM"}

ckpt_itr_200/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d032a5cceb625db904667cf768c5b5f5371e6eaa6515b34c3adef7177769489
+size 390899394

ckpt_itr_250/adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "peft_type": "LORA", "base_model_name_or_path": "/mnt/ui_copilot/data_rw/finetuning/base/models--meta-llama--Llama-3.3-70B-Instruct", "task_type": "CAUSAL_LM"}

ckpt_itr_250/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee4ffdb7b533284c0cf41216411cab311c4d5e548d596a6d6aa3e7829f34a43f
+size 390899394

ckpt_itr_50/adapter_config.json

@@ -0,0 +1 @@
+{"r": 16, "lora_alpha": 32, "target_modules": ["q_proj", "v_proj", "o_proj", "gate_proj", "down_proj", "up_proj"], "peft_type": "LORA", "base_model_name_or_path": "/mnt/ui_copilot/data_rw/finetuning/base/models--meta-llama--Llama-3.3-70B-Instruct", "task_type": "CAUSAL_LM"}

ckpt_itr_50/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3efd343cf5159892cbc97de5aa81600a2857183a9e52c4e5b2b9c1bea3f04af3
+size 390898430

config.json

@@ -0,0 +1 @@
+{"architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 128000, "eos_token_id": [128001, 128008, 128009], "head_dim": 128, "hidden_act": "silu", "hidden_size": 8192, "initializer_range": 0.02, "intermediate_size": 28672, "max_position_embeddings": 131072, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 64, "num_hidden_layers": 80, "num_key_value_heads": 8, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": {"factor": 8.0, "high_freq_factor": 4.0, "low_freq_factor": 1.0, "original_max_position_embeddings": 8192, "rope_type": "llama3"}, "rope_theta": 500000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.47.0.dev0", "use_cache": true, "vocab_size": 128256}