Training in progress, step 10

.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": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "o_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:cba75385b157f18b5d64118f11cd95f228998ec1a8a92bd9bff91d5b858f87da
+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-doc-train-fold10
+dataset_dir: data_private
+template: mistral
+cutoff_len: 2048
+# max_samples: 1000
+overwrite_cache: true
+preprocessing_num_workers: 16
+
+### output
+output_dir: saves/psy-course-doc/Ministral-8B-Instruct-2410/train/fold10
+logging_steps: 1
+save_steps: 10
+plot_loss: true
+overwrite_output_dir: true
+save_total_limit: 3
+push_to_hub: true
+hub_model_id: chchen/Ministral-8B-Instruct-2410-PsyCourse-doc-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: 10

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 +1,11 @@
+{"current_steps": 1, "total_steps": 125, "loss": 0.2122, "lr": 7.692307692307694e-06, "epoch": 0.03950617283950617, "percentage": 0.8, "elapsed_time": "0:00:29", "remaining_time": "1:01:17"}
+{"current_steps": 2, "total_steps": 125, "loss": 0.2224, "lr": 1.5384615384615387e-05, "epoch": 0.07901234567901234, "percentage": 1.6, "elapsed_time": "0:01:00", "remaining_time": "1:01:49"}
+{"current_steps": 3, "total_steps": 125, "loss": 0.1749, "lr": 2.307692307692308e-05, "epoch": 0.11851851851851852, "percentage": 2.4, "elapsed_time": "0:01:30", "remaining_time": "1:01:38"}
+{"current_steps": 4, "total_steps": 125, "loss": 0.2466, "lr": 3.0769230769230774e-05, "epoch": 0.1580246913580247, "percentage": 3.2, "elapsed_time": "0:01:59", "remaining_time": "1:00:26"}
+{"current_steps": 5, "total_steps": 125, "loss": 0.2216, "lr": 3.846153846153846e-05, "epoch": 0.19753086419753085, "percentage": 4.0, "elapsed_time": "0:02:26", "remaining_time": "0:58:28"}
+{"current_steps": 6, "total_steps": 125, "loss": 0.2093, "lr": 4.615384615384616e-05, "epoch": 0.23703703703703705, "percentage": 4.8, "elapsed_time": "0:02:57", "remaining_time": "0:58:35"}
+{"current_steps": 7, "total_steps": 125, "loss": 0.2611, "lr": 5.384615384615385e-05, "epoch": 0.2765432098765432, "percentage": 5.6, "elapsed_time": "0:03:25", "remaining_time": "0:57:44"}
+{"current_steps": 8, "total_steps": 125, "loss": 0.1887, "lr": 6.153846153846155e-05, "epoch": 0.3160493827160494, "percentage": 6.4, "elapsed_time": "0:03:52", "remaining_time": "0:56:34"}
+{"current_steps": 9, "total_steps": 125, "loss": 0.1552, "lr": 6.923076923076924e-05, "epoch": 0.35555555555555557, "percentage": 7.2, "elapsed_time": "0:04:20", "remaining_time": "0:55:51"}
+{"current_steps": 10, "total_steps": 125, "loss": 0.1441, "lr": 7.692307692307693e-05, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:04:50", "remaining_time": "0:55:42"}
+{"current_steps": 10, "total_steps": 125, "eval_loss": 0.12334010004997253, "epoch": 0.3950617283950617, "percentage": 8.0, "elapsed_time": "0:05:15", "remaining_time": "1:00:27"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c092341f3caa37fbea739d2d54455de69f32912a6b8f6601d520b1caf87a6434
+size 5624