Upload folder using huggingface_hub

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- autotrain
+- text-generation
+widget:
+- text: "I love AutoTrain because "
+---
+
+# Model Trained Using AutoTrain

adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-13b-Python-hf",
+  "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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62bc5bd4a46f60271750fae00219ad75ee8e9d4bd5c115149a8a2f80e2749f3
+size 104915277

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

checkpoint-18/README.md

@@ -0,0 +1,34 @@
+---
+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: False
+- bnb_4bit_compute_dtype: float16
+
+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: False
+- bnb_4bit_compute_dtype: float16
+### Framework versions
+
+- PEFT 0.6.0.dev0
+
+- PEFT 0.6.0.dev0

checkpoint-18/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-13b-Python-hf",
+  "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": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-18/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a62bc5bd4a46f60271750fae00219ad75ee8e9d4bd5c115149a8a2f80e2749f3
+size 104915277

checkpoint-18/added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

checkpoint-18/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16b101e4498a4be396121c6084a64e799f73779274b66649a3830f42d93d97bd
+size 209849861

checkpoint-18/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf06745891a84de37b7f3e261f691c7f6adbbcdb3e3c1a383b9f7ef98aaf21ee
+size 18615

checkpoint-18/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79308aafc0265a18762a3be5b82ed74929888dd68c3fc8c9ff0e85622eb255f
+size 18679

checkpoint-18/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81df9e50875c525430667de63159568a8671cd9c97ae849f05de48df945eb504
+size 18679

checkpoint-18/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8052549508c3029b840154e6421317357a30638cce5cfd83ac6f546eb6986f2e
+size 18679

checkpoint-18/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d80e403a441eb181c9a5723a9a21af3b0b95bb3525ca54fb193eeeef4e4128c1
+size 18679

checkpoint-18/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6773b32377f5c7c114b7dcd5f3668cd9dc143d6ec7187c117bd9c51f1e6e6956
+size 627

checkpoint-18/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-18/tokenizer.model

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

checkpoint-18/tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 4096,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": false
+}

checkpoint-18/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": 0.7995160818099976,
+  "best_model_checkpoint": "ctllama13bnsem/checkpoint-18",
+  "epoch": 5.085714285714285,
+  "eval_steps": 500,
+  "global_step": 18,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "eval_loss": 1.0205086469650269,
+      "eval_runtime": 15.9897,
+      "eval_samples_per_second": 5.378,
+      "eval_steps_per_second": 0.563,
+      "step": 3
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 0.9894978404045105,
+      "eval_runtime": 15.9229,
+      "eval_samples_per_second": 5.401,
+      "eval_steps_per_second": 0.565,
+      "step": 6
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 7.61904761904762e-06,
+      "loss": 0.9836,
+      "step": 8
+    },
+    {
+      "epoch": 2.09,
+      "eval_loss": 0.9659651517868042,
+      "eval_runtime": 15.9785,
+      "eval_samples_per_second": 5.382,
+      "eval_steps_per_second": 0.563,
+      "step": 9
+    },
+    {
+      "epoch": 3.09,
+      "eval_loss": 0.9247913360595703,
+      "eval_runtime": 15.9478,
+      "eval_samples_per_second": 5.393,
+      "eval_steps_per_second": 0.564,
+      "step": 12
+    },
+    {
+      "epoch": 4.09,
+      "eval_loss": 0.8596590757369995,
+      "eval_runtime": 15.9282,
+      "eval_samples_per_second": 5.399,
+      "eval_steps_per_second": 0.565,
+      "step": 15
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 1.523809523809524e-05,
+      "loss": 0.9024,
+      "step": 16
+    },
+    {
+      "epoch": 5.09,
+      "eval_loss": 0.7995160818099976,
+      "eval_runtime": 15.9408,
+      "eval_samples_per_second": 5.395,
+      "eval_steps_per_second": 0.565,
+      "step": 18
+    }
+  ],
+  "logging_steps": 8,
+  "max_steps": 210,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 2.890598298995917e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6c9e170ce5c76a83c40a46191a3ff939832f81e03d8e3feea3c31cbe158fa6
+size 4027

runs/Oct01_18-36-05_watgpu308/events.out.tfevents.1696185367.watgpu308.172765.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c26e06d9108e715e90b5bba77c88cbb311c47b46b1c59cd452c12e0c066bb49
+size 6720

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 4096,
+  "pad_token": null,
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b6c9e170ce5c76a83c40a46191a3ff939832f81e03d8e3feea3c31cbe158fa6
+size 4027

training_params.json

@@ -0,0 +1 @@
+{"model": "codellama/CodeLlama-13b-Python-hf", "data_path": "/u3/ns3mathe/tdg/2_code_llama_finetuning/dataset_processing/data", "project_name": "ctllama13bnsem", "train_split": "train", "valid_split": "validation", "text_column": "text", "lr": 2e-05, "epochs": 6, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 4096, "use_peft": true, "lora_r": 32, "lora_alpha": 64, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 4096, "repo_id": "NobleMathews/ctllama13bnsem", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null}