Upload folder using huggingface_hub

training_checkpoints/checkpoint-1/README.md

@@ -0,0 +1,24 @@
+---
+library_name: peft
+---
+## Training procedure
+
+
+The following `bitsandbytes` quantization config was used during training:
+- quant_method: bitsandbytes
+- _load_in_8bit: False
+- _load_in_4bit: True
+- llm_int8_threshold: 6.0
+- llm_int8_skip_modules: None
+- llm_int8_enable_fp32_cpu_offload: False
+- llm_int8_has_fp16_weight: False
+- bnb_4bit_quant_type: nf4
+- bnb_4bit_use_double_quant: True
+- bnb_4bit_compute_dtype: bfloat16
+- bnb_4bit_quant_storage: uint8
+- load_in_4bit: True
+- load_in_8bit: False
+### Framework versions
+
+
+- PEFT 0.4.0

training_checkpoints/checkpoint-1/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "up_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

training_checkpoints/checkpoint-1/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ff8c895844281187566f7aff252fba423042ab0f6452e2b1e576c6f13aed97
+size 50626520

training_checkpoints/checkpoint-1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d299709225afdca2dc8f644cd79e61e80ea84a7e99367a2dd2b3b0a44318209e
+size 1896

training_checkpoints/checkpoint-1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44c6659bffb2e2e32f2e45af0512bebea16230ca74ee094f313b4ac171113c16
+size 14244

training_checkpoints/checkpoint-1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bce2d3a2f8f216440846a555f3fa52ce4ec5a8eae429c1264154fbef75bbeae
+size 1064

training_checkpoints/checkpoint-1/trainer_state.json

@@ -0,0 +1,43 @@
+{
+  "best_metric": 0.014878712478886842,
+  "best_model_checkpoint": "tiny-llama/checkpoint-1",
+  "epoch": 0.0015552099533437014,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "eval_accuracy": 0.022463206816421378,
+      "eval_f1_macro": 0.014878712478886842,
+      "eval_f1_micro": 0.02246320681642138,
+      "eval_f1_weighted": 0.021101822374009954,
+      "eval_loss": 4.1563401222229,
+      "eval_macro_fpr": 0.4479452594392761,
+      "eval_macro_sensitivity": 0.06168923132504932,
+      "eval_macro_specificity": 0.9325328659403387,
+      "eval_precision": 0.07571006152540787,
+      "eval_precision_macro": 0.032699496485226985,
+      "eval_recall": 0.022463206816421378,
+      "eval_recall_macro": 0.06168923132504932,
+      "eval_runtime": 235.6581,
+      "eval_samples_per_second": 5.478,
+      "eval_steps_per_second": 0.687,
+      "eval_weighted_fpr": 0.7565947242206235,
+      "eval_weighted_sensitivity": 0.022463206816421378,
+      "eval_weighted_specificity": 0.9655297822886598,
+      "step": 1
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 24125116514304.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002faf22a5f134690fba598354ef90ba6392bcae20c41e85bc4caa5bcc9cde72
+size 4920