Training in progress, step 50

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "klyang/MentaLLaMA-chat-7B-hf",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "o_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 sha256:45715f9893990aa8c86de66f75e098bb9aa1855a474b95ec5680e856764d3e59
+size 80013120

llama3_lora_sft.yaml

@@ -0,0 +1,46 @@
+### model
+model_name_or_path: klyang/MentaLLaMA-chat-7B-hf
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: course-train-fold10
+dataset_dir: data_private
+template: llama2
+cutoff_len: 1024
+# max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/psy-course/MentaLLaMA-chat-7B/train/fold10
+logging_steps: 10
+save_steps: 50
+plot_loss: true
+overwrite_output_dir: true
+save_total_limit: 3
+push_to_hub: true
+hub_model_id: chchen/MentaLLaMA-chat-7B-PsyCourse-fold10
+load_best_model_at_end: true
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 16
+learning_rate: 1.0e-4
+num_train_epochs: 5.0
+lr_scheduler_type: cosine
+warmup_ratio: 0.1
+bf16: true
+ddp_timeout: 180000000
+enable_liger_kernel: true
+
+### eval
+val_size: 0.1
+per_device_eval_batch_size: 1
+eval_strategy: steps
+eval_steps: 50

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": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if loop.index0 == 0 and system_message is defined %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '<s>' + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

trainer_log.jsonl

@@ -0,0 +1,6 @@
+{"current_steps": 10, "total_steps": 3245, "loss": 1.6846, "lr": 3.0769230769230774e-06, "epoch": 0.015392015392015393, "percentage": 0.31, "elapsed_time": "0:01:26", "remaining_time": "7:46:20"}
+{"current_steps": 20, "total_steps": 3245, "loss": 1.7088, "lr": 6.153846153846155e-06, "epoch": 0.030784030784030785, "percentage": 0.62, "elapsed_time": "0:02:53", "remaining_time": "7:47:16"}
+{"current_steps": 30, "total_steps": 3245, "loss": 1.6361, "lr": 9.230769230769232e-06, "epoch": 0.046176046176046176, "percentage": 0.92, "elapsed_time": "0:04:21", "remaining_time": "7:47:11"}
+{"current_steps": 40, "total_steps": 3245, "loss": 1.3897, "lr": 1.230769230769231e-05, "epoch": 0.06156806156806157, "percentage": 1.23, "elapsed_time": "0:05:48", "remaining_time": "7:45:59"}
+{"current_steps": 50, "total_steps": 3245, "loss": 0.8796, "lr": 1.5384615384615387e-05, "epoch": 0.07696007696007696, "percentage": 1.54, "elapsed_time": "0:07:16", "remaining_time": "7:44:30"}
+{"current_steps": 50, "total_steps": 3245, "eval_loss": 0.6148930191993713, "epoch": 0.07696007696007696, "percentage": 1.54, "elapsed_time": "0:10:33", "remaining_time": "11:15:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69434fb9955612c60424816492e74be5c53827b31acb508422535647ff199311
+size 5624