Upload 11 files

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: defog/sqlcoder-7b-2
+model-index:
+- name: train_2024-02-27-09-48-46
+  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. -->
+
+# train_2024-02-27-09-48-46
+
+This model is a fine-tuned version of [defog/sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2) on the self_cognition dataset.
+
+## 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: 2.5e-05
+- train_batch_size: 5
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 20
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 1
+- num_epochs: 30.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.8.2
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.1
+- Tokenizers 0.15.2

adapter_config.json

@@ -0,0 +1,27 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "defog/sqlcoder-7b-2",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4639ef7860076ecf8d306adcd0e05fc81642fb14ba637e90093112ee0397ae4d
+size 67126104

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 30.0,
+    "train_loss": 0.8538130601247151,
+    "train_runtime": 2104.0236,
+    "train_samples_per_second": 1.141,
+    "train_steps_per_second": 0.057
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -0,0 +1,90 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    },
+    "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>",
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 30.0,
+    "train_loss": 0.8538130601247151,
+    "train_runtime": 2104.0236,
+    "train_samples_per_second": 1.141,
+    "train_steps_per_second": 0.057
+}

trainer_log.jsonl

@@ -0,0 +1,25 @@
+{"current_steps": 5, "total_steps": 120, "loss": 1.6733, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.493036906838148e-05, "epoch": 1.25, "percentage": 4.17, "elapsed_time": "0:01:26", "remaining_time": "0:33:00"}
+{"current_steps": 10, "total_steps": 120, "loss": 1.5341, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4648822424126846e-05, "epoch": 2.5, "percentage": 8.33, "elapsed_time": "0:02:55", "remaining_time": "0:32:12"}
+{"current_steps": 15, "total_steps": 120, "loss": 1.5014, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4155902867554447e-05, "epoch": 3.75, "percentage": 12.5, "elapsed_time": "0:04:21", "remaining_time": "0:30:29"}
+{"current_steps": 20, "total_steps": 120, "loss": 1.3282, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3460186525516237e-05, "epoch": 5.0, "percentage": 16.67, "elapsed_time": "0:05:50", "remaining_time": "0:29:10"}
+{"current_steps": 25, "total_steps": 120, "loss": 1.2251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2573777911867937e-05, "epoch": 6.25, "percentage": 20.83, "elapsed_time": "0:07:17", "remaining_time": "0:27:42"}
+{"current_steps": 30, "total_steps": 120, "loss": 1.1738, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1512099325465313e-05, "epoch": 7.5, "percentage": 25.0, "elapsed_time": "0:08:44", "remaining_time": "0:26:13"}
+{"current_steps": 35, "total_steps": 120, "loss": 1.0707, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.029362252323417e-05, "epoch": 8.75, "percentage": 29.17, "elapsed_time": "0:10:14", "remaining_time": "0:24:51"}
+{"current_steps": 40, "total_steps": 120, "loss": 0.9962, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.89395473368362e-05, "epoch": 10.0, "percentage": 33.33, "elapsed_time": "0:11:40", "remaining_time": "0:23:20"}
+{"current_steps": 45, "total_steps": 120, "loss": 0.8998, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.747343282456151e-05, "epoch": 11.25, "percentage": 37.5, "elapsed_time": "0:13:09", "remaining_time": "0:21:55"}
+{"current_steps": 50, "total_steps": 120, "loss": 0.8471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5920787375901038e-05, "epoch": 12.5, "percentage": 41.67, "elapsed_time": "0:14:36", "remaining_time": "0:20:26"}
+{"current_steps": 55, "total_steps": 120, "loss": 0.7282, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4308624900419257e-05, "epoch": 13.75, "percentage": 45.83, "elapsed_time": "0:16:03", "remaining_time": "0:18:58"}
+{"current_steps": 60, "total_steps": 120, "loss": 0.6841, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2664994822634489e-05, "epoch": 15.0, "percentage": 50.0, "elapsed_time": "0:17:30", "remaining_time": "0:17:30"}
+{"current_steps": 65, "total_steps": 120, "loss": 0.6456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1018494060353718e-05, "epoch": 16.25, "percentage": 54.17, "elapsed_time": "0:18:57", "remaining_time": "0:16:02"}
+{"current_steps": 70, "total_steps": 120, "loss": 0.6238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.397769477372204e-06, "epoch": 17.5, "percentage": 58.33, "elapsed_time": "0:20:26", "remaining_time": "0:14:36"}
+{"current_steps": 75, "total_steps": 120, "loss": 0.5803, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.831019467181105e-06, "epoch": 18.75, "percentage": 62.5, "elapsed_time": "0:21:52", "remaining_time": "0:13:07"}
+{"current_steps": 80, "total_steps": 120, "loss": 0.5901, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.345503339445723e-06, "epoch": 20.0, "percentage": 66.67, "elapsed_time": "0:23:20", "remaining_time": "0:11:40"}
+{"current_steps": 85, "total_steps": 120, "loss": 0.5654, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.967067045259296e-06, "epoch": 21.25, "percentage": 70.83, "elapsed_time": "0:24:49", "remaining_time": "0:10:13"}
+{"current_steps": 90, "total_steps": 120, "loss": 0.5594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7196934929050185e-06, "epoch": 22.5, "percentage": 75.0, "elapsed_time": "0:26:17", "remaining_time": "0:08:45"}
+{"current_steps": 95, "total_steps": 120, "loss": 0.5406, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.625085278017651e-06, "epoch": 23.75, "percentage": 79.17, "elapsed_time": "0:27:43", "remaining_time": "0:07:17"}
+{"current_steps": 100, "total_steps": 120, "loss": 0.5569, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7022870880697955e-06, "epoch": 25.0, "percentage": 83.33, "elapsed_time": "0:29:11", "remaining_time": "0:05:50"}
+{"current_steps": 105, "total_steps": 120, "loss": 0.5415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.673543508289639e-07, "epoch": 26.25, "percentage": 87.5, "elapsed_time": "0:30:40", "remaining_time": "0:04:22"}
+{"current_steps": 110, "total_steps": 120, "loss": 0.5503, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3307389184951696e-07, "epoch": 27.5, "percentage": 91.67, "elapsed_time": "0:32:09", "remaining_time": "0:02:55"}
+{"current_steps": 115, "total_steps": 120, "loss": 0.5384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.087414611775403e-07, "epoch": 28.75, "percentage": 95.83, "elapsed_time": "0:33:35", "remaining_time": "0:01:27"}
+{"current_steps": 120, "total_steps": 120, "loss": 0.5373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:35:04", "remaining_time": "0:00:00"}
+{"current_steps": 120, "total_steps": 120, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 30.0, "percentage": 100.0, "elapsed_time": "0:35:04", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,174 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 30.0,
+  "eval_steps": 500,
+  "global_step": 120,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.493036906838148e-05,
+      "loss": 1.6733,
+      "step": 5
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.4648822424126846e-05,
+      "loss": 1.5341,
+      "step": 10
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 2.4155902867554447e-05,
+      "loss": 1.5014,
+      "step": 15
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.3460186525516237e-05,
+      "loss": 1.3282,
+      "step": 20
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 2.2573777911867937e-05,
+      "loss": 1.2251,
+      "step": 25
+    },
+    {
+      "epoch": 7.5,
+      "learning_rate": 2.1512099325465313e-05,
+      "loss": 1.1738,
+      "step": 30
+    },
+    {
+      "epoch": 8.75,
+      "learning_rate": 2.029362252323417e-05,
+      "loss": 1.0707,
+      "step": 35
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.89395473368362e-05,
+      "loss": 0.9962,
+      "step": 40
+    },
+    {
+      "epoch": 11.25,
+      "learning_rate": 1.747343282456151e-05,
+      "loss": 0.8998,
+      "step": 45
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 1.5920787375901038e-05,
+      "loss": 0.8471,
+      "step": 50
+    },
+    {
+      "epoch": 13.75,
+      "learning_rate": 1.4308624900419257e-05,
+      "loss": 0.7282,
+      "step": 55
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 1.2664994822634489e-05,
+      "loss": 0.6841,
+      "step": 60
+    },
+    {
+      "epoch": 16.25,
+      "learning_rate": 1.1018494060353718e-05,
+      "loss": 0.6456,
+      "step": 65
+    },
+    {
+      "epoch": 17.5,
+      "learning_rate": 9.397769477372204e-06,
+      "loss": 0.6238,
+      "step": 70
+    },
+    {
+      "epoch": 18.75,
+      "learning_rate": 7.831019467181105e-06,
+      "loss": 0.5803,
+      "step": 75
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 6.345503339445723e-06,
+      "loss": 0.5901,
+      "step": 80
+    },
+    {
+      "epoch": 21.25,
+      "learning_rate": 4.967067045259296e-06,
+      "loss": 0.5654,
+      "step": 85
+    },
+    {
+      "epoch": 22.5,
+      "learning_rate": 3.7196934929050185e-06,
+      "loss": 0.5594,
+      "step": 90
+    },
+    {
+      "epoch": 23.75,
+      "learning_rate": 2.625085278017651e-06,
+      "loss": 0.5406,
+      "step": 95
+    },
+    {
+      "epoch": 25.0,
+      "learning_rate": 1.7022870880697955e-06,
+      "loss": 0.5569,
+      "step": 100
+    },
+    {
+      "epoch": 26.25,
+      "learning_rate": 9.673543508289639e-07,
+      "loss": 0.5415,
+      "step": 105
+    },
+    {
+      "epoch": 27.5,
+      "learning_rate": 4.3307389184951696e-07,
+      "loss": 0.5503,
+      "step": 110
+    },
+    {
+      "epoch": 28.75,
+      "learning_rate": 1.087414611775403e-07,
+      "loss": 0.5384,
+      "step": 115
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 0.0,
+      "loss": 0.5373,
+      "step": 120
+    },
+    {
+      "epoch": 30.0,
+      "step": 120,
+      "total_flos": 2.36562943574016e+16,
+      "train_loss": 0.8538130601247151,
+      "train_runtime": 2104.0236,
+      "train_samples_per_second": 1.141,
+      "train_steps_per_second": 0.057
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 120,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 100,
+  "total_flos": 2.36562943574016e+16,
+  "train_batch_size": 5,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948824c6f5a789118931893ce339016ad34f3ef01a118a23cacdc85bb0e6cb99
+size 4920