Upload folder using huggingface_hub

training_checkpoints/checkpoint-642/README.md

@@ -0,0 +1,21 @@
+---
+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
+### Framework versions
+
+
+- PEFT 0.4.0

training_checkpoints/checkpoint-642/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": [
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

training_checkpoints/checkpoint-642/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aab871a8ecd2948966e611d672f7f15045de846101112b111fd7529a20f029a
+size 50626520

training_checkpoints/checkpoint-642/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b44efd2169fc93c9e5cce7ca3a464fd333265fb144ae7dc66c0029cb9dcd7653
+size 101430714

training_checkpoints/checkpoint-642/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd77b752431d2ce006a52e3ec22b69b95db162654446b01060728ead42fdda22
+size 14244

training_checkpoints/checkpoint-642/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1547c471de33679c1f00a83db1e20c63a93cd5f5eed66671794dd505b6fcef
+size 1064

training_checkpoints/checkpoint-642/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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_checkpoints/checkpoint-642/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

training_checkpoints/checkpoint-642/tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_checkpoints/checkpoint-642/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": 0.6825948968456714,
+  "best_model_checkpoint": "tiny-llama/checkpoint-642",
+  "epoch": 0.9996107434799533,
+  "eval_steps": 500,
+  "global_step": 642,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.6152647975077886e-05,
+      "loss": 1.0491,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8109992254066615,
+      "eval_f1_macro": 0.6825948968456714,
+      "eval_f1_micro": 0.8109992254066615,
+      "eval_f1_weighted": 0.8049422701402866,
+      "eval_loss": 0.6238328218460083,
+      "eval_macro_fpr": 0.017127511820106363,
+      "eval_macro_sensitivity": 0.6881279883952739,
+      "eval_macro_specificity": 0.9855565316187128,
+      "eval_precision": 0.8182115378645501,
+      "eval_precision_macro": 0.723423168742811,
+      "eval_recall": 0.8109992254066615,
+      "eval_recall_macro": 0.6881279883952739,
+      "eval_runtime": 1397.6239,
+      "eval_samples_per_second": 0.924,
+      "eval_steps_per_second": 0.462,
+      "eval_weighted_fpr": 0.016373641121997046,
+      "eval_weighted_sensitivity": 0.8109992254066615,
+      "eval_weighted_specificity": 0.9723487488740324,
+      "step": 642
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6420,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6.197742432524698e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-642/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775edbef1a236739aee4d2ec1eb05a7261dcdcafc6d678204639e3f4466b9de1
+size 4600