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-7b-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:ad08a13448968a1c90fe5b9c031048f4eea166d4d2d71c31e7b6763541ced6f6
+size 67154893

added_tokens.json

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

checkpoint-12/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-12/adapter_config.json

@@ -0,0 +1,23 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-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-12/adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad08a13448968a1c90fe5b9c031048f4eea166d4d2d71c31e7b6763541ced6f6
+size 67154893

checkpoint-12/added_tokens.json

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

checkpoint-12/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a4ea92f22fc96a0d4074f4f8aa0b738d3830f9b17bd5709f8dee66071641e6
+size 134325445

checkpoint-12/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d721a336286dc83d73a4f5dea214e2a10a0504b44cc0df4658691c76ca84b18b
+size 18615

checkpoint-12/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c2413ae53fc1ef17a4cd89e1a13b34e3414058f2ac68662bf808e647a540e6c
+size 18679

checkpoint-12/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a743cd664f30abe5e3c0bca0955ec7b0b17a7ca5e447a2629efb5df37a80c915
+size 18679

checkpoint-12/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2456791adb431abc17aef99ba1e664360f2ee95d451aea411082812e87cf3cdc
+size 18679

checkpoint-12/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c582bdf9a62052f5c7714ea0ad98e66325cda0c6c58759c0be919e992608b43
+size 18679

checkpoint-12/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:261697186a97391ee0bf89f29f8cf2242833166e1803758175a2f9c4c4ef9454
+size 627

checkpoint-12/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-12/tokenizer.model

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

checkpoint-12/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-12/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": 0.7733290791511536,
+  "best_model_checkpoint": "ctllama7b/checkpoint-12",
+  "epoch": 5.086956521739131,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "eval_loss": 0.9089534878730774,
+      "eval_runtime": 8.5765,
+      "eval_samples_per_second": 10.027,
+      "eval_steps_per_second": 0.7,
+      "step": 2
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 0.9039565920829773,
+      "eval_runtime": 8.6271,
+      "eval_samples_per_second": 9.969,
+      "eval_steps_per_second": 0.695,
+      "step": 4
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.8946,
+      "step": 5
+    },
+    {
+      "epoch": 2.09,
+      "eval_loss": 0.8744738101959229,
+      "eval_runtime": 8.6363,
+      "eval_samples_per_second": 9.958,
+      "eval_steps_per_second": 0.695,
+      "step": 6
+    },
+    {
+      "epoch": 3.09,
+      "eval_loss": 0.8518250584602356,
+      "eval_runtime": 8.6389,
+      "eval_samples_per_second": 9.955,
+      "eval_steps_per_second": 0.695,
+      "step": 8
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 1.4285714285714287e-05,
+      "loss": 0.844,
+      "step": 10
+    },
+    {
+      "epoch": 4.09,
+      "eval_loss": 0.7924608588218689,
+      "eval_runtime": 8.6417,
+      "eval_samples_per_second": 9.952,
+      "eval_steps_per_second": 0.694,
+      "step": 10
+    },
+    {
+      "epoch": 5.09,
+      "eval_loss": 0.7733290791511536,
+      "eval_runtime": 8.6368,
+      "eval_samples_per_second": 9.957,
+      "eval_steps_per_second": 0.695,
+      "step": 12
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 138,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "total_flos": 1.2482646458236928e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-12/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a28d331e80dabfad199c64be770675c6c306ca4fdc0aa80d4b3ae144a4ca1259
+size 4027

runs/Sep27_02-45-57_watgpu308/events.out.tfevents.1695782758.watgpu308.134136.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25122db6efaec7fac9d5a50302758427a662d1c2bcece98b25682cc8ea2cffed
+size 6704

runs/Sep27_03-35-54_watgpu308/events.out.tfevents.1695785756.watgpu308.135013.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa07ab269a73f2fca2fae691f88ae1e93be047fe41430087da8fdde474fc2701
+size 4452

runs/Sep27_03-42-19_watgpu308/events.out.tfevents.1695786141.watgpu308.135308.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b11c29557594ed135a1d5316cad13c7447b26e675677980faf28bb9e99ca16
+size 4452

runs/Sep27_03-45-34_watgpu308/events.out.tfevents.1695786335.watgpu308.135599.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c28b9bbe72f26d623eb75535cecfcaccf38810c7ef3637bcee058ea7f19cd3
+size 6704

runs/Sep27_04-12-32_watgpu308/events.out.tfevents.1695787953.watgpu308.135921.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:654c12fcfc131f46f66932b2b7411624f5ecb4389432c2c11dd16b27a8a3e99e
+size 6704

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:a28d331e80dabfad199c64be770675c6c306ca4fdc0aa80d4b3ae144a4ca1259
+size 4027

training_params.json

@@ -0,0 +1 @@
+{"model": "codellama/CodeLlama-7b-Python-hf", "data_path": "/u3/ns3mathe/tdg/2_code_llama_finetuning/dataset_processing/data", "project_name": "ctllama7b", "train_split": "train", "valid_split": "validation", "text_column": "text", "lr": 2e-05, "epochs": 6, "batch_size": 3, "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/ctllama7b", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null}