Training in progress, step 50

.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 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Ministral-8B-Instruct-2410",
+  "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": [
+    "up_proj",
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "q_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:f568c0d2079a4512644718a1b6649af85ee6613f2d9e872c50cf93a05ddce222
+size 87360584

llama3_lora_sft.yaml

@@ -0,0 +1,46 @@
+### model
+model_name_or_path: mistralai/Ministral-8B-Instruct-2410
+trust_remote_code: true
+
+### method
+stage: sft
+do_train: true
+finetuning_type: lora
+lora_target: all
+
+### dataset
+dataset: course-train-fold1
+dataset_dir: data_private
+template: mistral
+cutoff_len: 1024
+# max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/psy-course/Ministral-8B-Instruct-2410/train/fold3
+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/Ministral-8B-Instruct-2410-PsyCourse-fold3
+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 +1,24 @@
+{
+  "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": "</s>",
+  "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:d7edbeaf20dd7f571b5dd1c54d9ace4f9b6299127cc7ba2afb14a6d51a4a79a4
+size 17078136

trainer_log.jsonl

@@ -0,0 +1,6 @@
+{"current_steps": 10, "total_steps": 3245, "loss": 1.3361, "lr": 3.0769230769230774e-06, "epoch": 0.015390534821085032, "percentage": 0.31, "elapsed_time": "0:01:25", "remaining_time": "7:42:38"}
+{"current_steps": 20, "total_steps": 3245, "loss": 1.2705, "lr": 6.153846153846155e-06, "epoch": 0.030781069642170065, "percentage": 0.62, "elapsed_time": "0:02:55", "remaining_time": "7:52:55"}
+{"current_steps": 30, "total_steps": 3245, "loss": 1.0344, "lr": 9.230769230769232e-06, "epoch": 0.0461716044632551, "percentage": 0.92, "elapsed_time": "0:04:29", "remaining_time": "8:00:58"}
+{"current_steps": 40, "total_steps": 3245, "loss": 0.5543, "lr": 1.230769230769231e-05, "epoch": 0.06156213928434013, "percentage": 1.23, "elapsed_time": "0:06:03", "remaining_time": "8:05:44"}
+{"current_steps": 50, "total_steps": 3245, "loss": 0.2581, "lr": 1.5384615384615387e-05, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:07:39", "remaining_time": "8:09:01"}
+{"current_steps": 50, "total_steps": 3245, "eval_loss": 0.24142955243587494, "epoch": 0.07695267410542517, "percentage": 1.54, "elapsed_time": "0:11:03", "remaining_time": "11:46:35"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d753bacc0b878f626261363aa7671c2e325123e7fa832cc581427fe5e70f05d4
+size 5624