Upload folder using huggingface_hub

training_checkpoints/checkpoint-6420/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-6420/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-6420/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a71a2c8c687cc3dcd88f2c79022e61b22daab938b47a37ea974c5dfd44ddb417
+size 50626520

training_checkpoints/checkpoint-6420/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea8b9e848834dfcf4aa242c0616a5e7610167d5848d1e789b5af15f3fa23fe55
+size 101430714

training_checkpoints/checkpoint-6420/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1468041093c8e481936d2df6e94ed5b3fce293d739190b51d09240bc75d1972b
+size 14244

training_checkpoints/checkpoint-6420/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5fd31e41220ac04ae4bcaa13e125c8a274d03dd8c444a33274b9d0a35f1ef56
+size 1064

training_checkpoints/checkpoint-6420/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-6420/tokenizer.model

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

training_checkpoints/checkpoint-6420/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-6420/trainer_state.json

@@ -0,0 +1,311 @@
+{
+  "best_metric": 0.7849208402678758,
+  "best_model_checkpoint": "tiny-llama/checkpoint-1284",
+  "epoch": 9.996107434799534,
+  "eval_steps": 500,
+  "global_step": 6420,
+  "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
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.4470404984423676e-05,
+      "loss": 0.2132,
+      "step": 2000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 3.057632398753894e-05,
+      "loss": 0.0571,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8264910921766073,
+      "eval_f1_macro": 0.7690440255949657,
+      "eval_f1_micro": 0.8264910921766073,
+      "eval_f1_weighted": 0.8261718999247398,
+      "eval_loss": 1.114306926727295,
+      "eval_macro_fpr": 0.015230795356958942,
+      "eval_macro_sensitivity": 0.7762905253241136,
+      "eval_macro_specificity": 0.9869101098294825,
+      "eval_precision": 0.8312136257886843,
+      "eval_precision_macro": 0.7904073004865061,
+      "eval_recall": 0.8264910921766073,
+      "eval_recall_macro": 0.7762905253241136,
+      "eval_runtime": 1399.2136,
+      "eval_samples_per_second": 0.923,
+      "eval_steps_per_second": 0.462,
+      "eval_weighted_fpr": 0.014773776546629732,
+      "eval_weighted_sensitivity": 0.8264910921766073,
+      "eval_weighted_specificity": 0.9771605552656325,
+      "step": 2569
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 2.6682242990654205e-05,
+      "loss": 0.0187,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8319132455460883,
+      "eval_f1_macro": 0.7637547171369754,
+      "eval_f1_micro": 0.8319132455460883,
+      "eval_f1_weighted": 0.8302763212360192,
+      "eval_loss": 1.110449194908142,
+      "eval_macro_fpr": 0.014862942310551715,
+      "eval_macro_sensitivity": 0.7723638117326753,
+      "eval_macro_specificity": 0.9872593002552416,
+      "eval_precision": 0.8316344032874086,
+      "eval_precision_macro": 0.7744559231287563,
+      "eval_recall": 0.8319132455460883,
+      "eval_recall_macro": 0.7723638117326753,
+      "eval_runtime": 1397.1179,
+      "eval_samples_per_second": 0.924,
+      "eval_steps_per_second": 0.462,
+      "eval_weighted_fpr": 0.014226709499770536,
+      "eval_weighted_sensitivity": 0.8319132455460883,
+      "eval_weighted_specificity": 0.9769762582825359,
+      "step": 3211
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 2.2788161993769472e-05,
+      "loss": 0.0071,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8241673121611154,
+      "eval_f1_macro": 0.745099817904837,
+      "eval_f1_micro": 0.8241673121611154,
+      "eval_f1_weighted": 0.8209070583364038,
+      "eval_loss": 1.144503116607666,
+      "eval_macro_fpr": 0.01570185641881881,
+      "eval_macro_sensitivity": 0.738352723089731,
+      "eval_macro_specificity": 0.9866424210438552,
+      "eval_precision": 0.8210083679630991,
+      "eval_precision_macro": 0.7683618012500858,
+      "eval_recall": 0.8241673121611154,
+      "eval_recall_macro": 0.738352723089731,
+      "eval_runtime": 1397.6847,
+      "eval_samples_per_second": 0.924,
+      "eval_steps_per_second": 0.462,
+      "eval_weighted_fpr": 0.015010249289162203,
+      "eval_weighted_sensitivity": 0.8241673121611154,
+      "eval_weighted_specificity": 0.9754690034967137,
+      "step": 3853
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 1.8894080996884735e-05,
+      "loss": 0.0002,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8326878388845856,
+      "eval_f1_macro": 0.7617153787626418,
+      "eval_f1_micro": 0.8326878388845856,
+      "eval_f1_weighted": 0.8292501117913054,
+      "eval_loss": 1.2032252550125122,
+      "eval_macro_fpr": 0.014823835936918472,
+      "eval_macro_sensitivity": 0.752929076567028,
+      "eval_macro_specificity": 0.9872777146881934,
+      "eval_precision": 0.8301989992809635,
+      "eval_precision_macro": 0.7985351753450873,
+      "eval_recall": 0.8326878388845856,
+      "eval_recall_macro": 0.752929076567028,
+      "eval_runtime": 1403.2825,
+      "eval_samples_per_second": 0.92,
+      "eval_steps_per_second": 0.46,
+      "eval_weighted_fpr": 0.01414908947988995,
+      "eval_weighted_sensitivity": 0.8326878388845856,
+      "eval_weighted_specificity": 0.9764778814383137,
+      "step": 4495
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 1.5e-05,
+      "loss": 0.0028,
+      "step": 4500
+    },
+    {
+      "epoch": 7.79,
+      "learning_rate": 1.1105919003115265e-05,
+      "loss": 0.0028,
+      "step": 5000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.82571649883811,
+      "eval_f1_macro": 0.755227710037701,
+      "eval_f1_micro": 0.82571649883811,
+      "eval_f1_weighted": 0.8229426380981488,
+      "eval_loss": 1.1918259859085083,
+      "eval_macro_fpr": 0.015546599693760165,
+      "eval_macro_sensitivity": 0.7493334411200354,
+      "eval_macro_specificity": 0.986754396380849,
+      "eval_precision": 0.8225901566549486,
+      "eval_precision_macro": 0.7737967354767298,
+      "eval_recall": 0.82571649883811,
+      "eval_recall_macro": 0.7493334411200354,
+      "eval_runtime": 1398.648,
+      "eval_samples_per_second": 0.923,
+      "eval_steps_per_second": 0.462,
+      "eval_weighted_fpr": 0.01485246550927454,
+      "eval_weighted_sensitivity": 0.82571649883811,
+      "eval_weighted_specificity": 0.975599446874626,
+      "step": 5138
+    },
+    {
+      "epoch": 8.56,
+      "learning_rate": 7.21183800623053e-06,
+      "loss": 0.0,
+      "step": 5500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.831138652207591,
+      "eval_f1_macro": 0.7592477157964134,
+      "eval_f1_micro": 0.831138652207591,
+      "eval_f1_weighted": 0.8276161418464294,
+      "eval_loss": 1.21809720993042,
+      "eval_macro_fpr": 0.014976927943039621,
+      "eval_macro_sensitivity": 0.7521526164801944,
+      "eval_macro_specificity": 0.987168901409934,
+      "eval_precision": 0.8285866244573639,
+      "eval_precision_macro": 0.7935003071971033,
+      "eval_recall": 0.831138652207591,
+      "eval_recall_macro": 0.7521526164801944,
+      "eval_runtime": 1400.0048,
+      "eval_samples_per_second": 0.922,
+      "eval_steps_per_second": 0.461,
+      "eval_weighted_fpr": 0.014304461942257218,
+      "eval_weighted_sensitivity": 0.831138652207591,
+      "eval_weighted_specificity": 0.9763948689414159,
+      "step": 5780
+    },
+    {
+      "epoch": 9.34,
+      "learning_rate": 3.317757009345795e-06,
+      "loss": 0.0018,
+      "step": 6000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8326878388845856,
+      "eval_f1_macro": 0.7609324863449892,
+      "eval_f1_micro": 0.8326878388845856,
+      "eval_f1_weighted": 0.8291452810040447,
+      "eval_loss": 1.2264705896377563,
+      "eval_macro_fpr": 0.014820307106127618,
+      "eval_macro_sensitivity": 0.7535993757394536,
+      "eval_macro_specificity": 0.9872791783457928,
+      "eval_precision": 0.8301404715570689,
+      "eval_precision_macro": 0.7954769466906811,
+      "eval_recall": 0.8326878388845856,
+      "eval_recall_macro": 0.7535993757394536,
+      "eval_runtime": 1398.3427,
+      "eval_samples_per_second": 0.923,
+      "eval_steps_per_second": 0.462,
+      "eval_weighted_fpr": 0.01414908947988995,
+      "eval_weighted_sensitivity": 0.8326878388845856,
+      "eval_weighted_specificity": 0.9764998363023064,
+      "step": 6420
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6420,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 6.195329920873267e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_checkpoints/checkpoint-6420/training_args.bin

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