Model save

README.md

@@ -0,0 +1,63 @@
+---
+license: llama2
+base_model: codellama/CodeLlama-7b-Instruct-hf
+tags:
+- generated_from_trainer
+model-index:
+- name: codellama-7b-inst-sft-lora-test
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# codellama-7b-inst-sft-lora-test
+
+This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6483
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 1024
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.6579        | 0.49  | 1    | 1.6482          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c96f5d29af1f922422da0bf97d235a4f3cc768da58a51d34cf53ef8a2616b4d3
+size 134252592

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.49,
+    "eval_loss": 1.6482644081115723,
+    "eval_runtime": 1524.9151,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 15.155,
+    "eval_steps_per_second": 0.948,
+    "train_loss": 2.3372400999069214,
+    "train_runtime": 2103.1993,
+    "train_samples": 2078,
+    "train_samples_per_second": 0.988,
+    "train_steps_per_second": 0.001
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.49,
+    "eval_loss": 1.6482644081115723,
+    "eval_runtime": 1524.9151,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 15.155,
+    "eval_steps_per_second": 0.948
+}

runs/Jan11_15-38-24_dl-host10/events.out.tfevents.1704955122.dl-host10.139132.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aec705cc59ed6605fc441784a8cf7323b229c53b6dbfb57c982cb2bc2583014
+size 5140

runs/Jan12_07-09-12_dl-host10/events.out.tfevents.1705010966.dl-host10.169225.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:514de9b1d5d8b52bde44d97451096dcfe2cde115b798ed289cf71fa6f97f8b95
+size 5140

runs/Jan12_07-09-12_dl-host10/events.out.tfevents.1705014594.dl-host10.169225.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9cc1a273bb6de16756d2ef2cbbf13c21233e4baa8eb9f9cebb685ba70f6ef0
+size 354

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_config.json

@@ -0,0 +1,82 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.49,
+    "train_loss": 2.3372400999069214,
+    "train_runtime": 2103.1993,
+    "train_samples": 2078,
+    "train_samples_per_second": 0.988,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.49230769230769234,
+  "eval_steps": 500,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.49,
+      "learning_rate": 2e-05,
+      "loss": 1.6579,
+      "step": 1
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.648226261138916,
+      "eval_runtime": 1525.0437,
+      "eval_samples_per_second": 15.154,
+      "eval_steps_per_second": 0.948,
+      "step": 1
+    },
+    {
+      "epoch": 0.49,
+      "step": 1,
+      "total_flos": 909231154790400.0,
+      "train_loss": 2.3372400999069214,
+      "train_runtime": 2103.1993,
+      "train_samples_per_second": 0.988,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "total_flos": 909231154790400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93f3a5ea9e00e0ddec5d9339578649c62f8899f5c8af281023a17e36c2da8730
+size 5688