Upload folder using huggingface_hub

training_checkpoints/checkpoint-1926/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-1926/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": [
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj"
+  ],
+  "task_type": "SEQ_CLS"
+}

training_checkpoints/checkpoint-1926/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf10866b3b4dde336fa75cd84ec01eaeee066cac028c964c98a54d0a311504e6
+size 50626520

training_checkpoints/checkpoint-1926/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1b3bbfd96b5b8bf980d7078362e14de96a62735bebed252dc4b036fc47112d2
+size 101430714

training_checkpoints/checkpoint-1926/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a9b3441045cec6251b5e2d0f020d72734979a5c5e65c886fe9318c5c15e087
+size 14244

training_checkpoints/checkpoint-1926/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f6fd9669bf65b94099869c64621148aa0238a64b03926c5ff1fce3c23795487
+size 1064

training_checkpoints/checkpoint-1926/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-1926/tokenizer.model

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

training_checkpoints/checkpoint-1926/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-1926/trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.7849208402678758,
+  "best_model_checkpoint": "tiny-llama/checkpoint-1284",
+  "epoch": 2.99883223043986,
+  "eval_steps": 500,
+  "global_step": 1926,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.614485981308411e-05,
+      "loss": 1.0444,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8055770720371804,
+      "eval_f1_macro": 0.6986433125217109,
+      "eval_f1_micro": 0.8055770720371804,
+      "eval_f1_weighted": 0.8014415131779974,
+      "eval_loss": 0.5968185067176819,
+      "eval_macro_fpr": 0.017477297659887057,
+      "eval_macro_sensitivity": 0.6995136011888944,
+      "eval_macro_specificity": 0.9852356804676051,
+      "eval_precision": 0.8049997976909469,
+      "eval_precision_macro": 0.7121994461809698,
+      "eval_recall": 0.8055770720371804,
+      "eval_recall_macro": 0.6995136011888944,
+      "eval_runtime": 1398.4578,
+      "eval_samples_per_second": 0.923,
+      "eval_steps_per_second": 0.462,
+      "eval_weighted_fpr": 0.01694686381743299,
+      "eval_weighted_sensitivity": 0.8055770720371804,
+      "eval_weighted_specificity": 0.9729581349768969,
+      "step": 642
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.2250778816199374e-05,
+      "loss": 0.4788,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8195197521301317,
+      "eval_f1_macro": 0.7849208402678758,
+      "eval_f1_micro": 0.8195197521301317,
+      "eval_f1_weighted": 0.8172221848923289,
+      "eval_loss": 0.696565568447113,
+      "eval_macro_fpr": 0.016141504898788652,
+      "eval_macro_sensitivity": 0.782528240704334,
+      "eval_macro_specificity": 0.9863319896705219,
+      "eval_precision": 0.8221579556499354,
+      "eval_precision_macro": 0.8091762597974816,
+      "eval_recall": 0.8195197521301317,
+      "eval_recall_macro": 0.782528240704334,
+      "eval_runtime": 1392.2226,
+      "eval_samples_per_second": 0.927,
+      "eval_steps_per_second": 0.464,
+      "eval_weighted_fpr": 0.01548687271518777,
+      "eval_weighted_sensitivity": 0.8195197521301317,
+      "eval_weighted_specificity": 0.9754600929277001,
+      "step": 1284
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 3.836448598130841e-05,
+      "loss": 0.3354,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8326878388845856,
+      "eval_f1_macro": 0.7742114597713703,
+      "eval_f1_micro": 0.8326878388845856,
+      "eval_f1_weighted": 0.8281979563082781,
+      "eval_loss": 0.8046467304229736,
+      "eval_macro_fpr": 0.014819935806968648,
+      "eval_macro_sensitivity": 0.7581833318977771,
+      "eval_macro_specificity": 0.9872339538797621,
+      "eval_precision": 0.8276269450338689,
+      "eval_precision_macro": 0.8057581057880366,
+      "eval_recall": 0.8326878388845856,
+      "eval_recall_macro": 0.7581833318977771,
+      "eval_runtime": 1396.4981,
+      "eval_samples_per_second": 0.924,
+      "eval_steps_per_second": 0.463,
+      "eval_weighted_fpr": 0.01414908947988995,
+      "eval_weighted_sensitivity": 0.8326878388845856,
+      "eval_weighted_specificity": 0.9758214693118433,
+      "step": 1926
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6420,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.8593227297574093e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-1926/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63f5fd560de7929fa900a07f6b2ea1ff18602c1b6c7171e4c9203c260226c44b
+size 4600