finetuned_swe_model

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/3acdd690e65c24f42a24581b8467af98bd3ca357444580f8012aacd2bd607921 filter=lfs diff=lfs merge=lfs -text
+models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/67e9ad31c8c32abf3a55ee7fc7217b3ecb35fd3c74d98a5bd233e0e4d6964f46 filter=lfs diff=lfs merge=lfs -text
+models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/8d4782b4a69ef03845159ce1a15e272aadaaf134dc138d68f616098e8531729c filter=lfs diff=lfs merge=lfs -text
+models--meta-llama--Meta-Llama-3-8B-Instruct/blobs/d8cf9c4d0dd972e1a2131bfe656235ee98221679711a3beef6d46dadf0f20b5c filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,72 @@
+---
+license: llama3
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: meta-llama/Meta-Llama-3-8B-Instruct
+model-index:
+- name: huggingface
+  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. -->
+
+# huggingface
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6105
+
+## 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: 5e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 143  | 0.4964          |
+| No log        | 2.0   | 286  | 0.4890          |
+| No log        | 3.0   | 429  | 0.4935          |
+| 0.4575        | 4.0   | 572  | 0.5059          |
+| 0.4575        | 5.0   | 715  | 0.5353          |
+| 0.4575        | 6.0   | 858  | 0.5662          |
+| 0.3146        | 7.0   | 1001 | 0.5934          |
+| 0.3146        | 8.0   | 1144 | 0.6105          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.0.1+cu117
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afff1919995940cfa3acd02be91db2068b0bdb599052e04fa6daac897d9863e5
+size 2185311008

finetuned_opt/checkpoint-1000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

finetuned_opt/checkpoint-1000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.2"
+}

finetuned_opt/checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4304e4463b24eaeea8ae1a18477af8a8a00c3b8d51d9688f3179f0514ef8602
+size 1324830880

finetuned_opt/checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49ea0d9cdd5ec7c07f3f29642735a2425faec3e0f6627c4d928e0b410b85da40
+size 2649895593

finetuned_opt/checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833a35a71573ee39d3f3b295ae9e92436d0d7e4a2de003040778e0d72b7957c2
+size 14575

finetuned_opt/checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e00893699672ec57dfa3f5d9ad4d0361b3bdb34bd2428aad07fd1723f9277bdc
+size 627

finetuned_opt/checkpoint-1000/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

finetuned_opt/checkpoint-1000/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "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
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

finetuned_opt/checkpoint-1000/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2453300124533002,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6226650062266501,
+      "grad_norm": 0.0,
+      "learning_rate": 3.9622249896222504e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": NaN,
+      "eval_runtime": 154.5064,
+      "eval_samples_per_second": 3.508,
+      "eval_steps_per_second": 3.508,
+      "step": 803
+    },
+    {
+      "epoch": 1.2453300124533002,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9244499792445003e-05,
+      "loss": 0.0,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2409,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3725798682918912.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

finetuned_opt/checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec94e88043c8d9f8f5ed99a8c4de459e905c871df64a0b285066748d671d4238
+size 4731

finetuned_opt/checkpoint-1500/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

finetuned_opt/checkpoint-1500/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.2"
+}

finetuned_opt/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4304e4463b24eaeea8ae1a18477af8a8a00c3b8d51d9688f3179f0514ef8602
+size 1324830880

finetuned_opt/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1c2005edbabcc4564b3d7f4882327ba62fa84de35c2472e67d7032d0a4a08f5
+size 2649895593

finetuned_opt/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c019dd6e95accb5dadaa3d85698b8fb16d2251c5c4f8acf9e4668276999911c8
+size 14575

finetuned_opt/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb52cf00f57c3e00e9a8e553d4a03be74f1942d85bb2fcdfeff2682cf78726c7
+size 627

finetuned_opt/checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

finetuned_opt/checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "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
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

finetuned_opt/checkpoint-1500/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.86799501867995,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6226650062266501,
+      "grad_norm": 0.0,
+      "learning_rate": 3.9622249896222504e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": NaN,
+      "eval_runtime": 154.5064,
+      "eval_samples_per_second": 3.508,
+      "eval_steps_per_second": 3.508,
+      "step": 803
+    },
+    {
+      "epoch": 1.2453300124533002,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9244499792445003e-05,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86799501867995,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8866749688667497e-05,
+      "loss": 0.0,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2409,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5589629940006912.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

finetuned_opt/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec94e88043c8d9f8f5ed99a8c4de459e905c871df64a0b285066748d671d4238
+size 4731

finetuned_opt/checkpoint-2000/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

finetuned_opt/checkpoint-2000/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.41.2"
+}

finetuned_opt/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4304e4463b24eaeea8ae1a18477af8a8a00c3b8d51d9688f3179f0514ef8602
+size 1324830880

finetuned_opt/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7171c2383acf146aa692d7cbb94da45f81efb2e98497d8080ef44fb36adbd981
+size 2649895593

finetuned_opt/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6caf882df17434d44c53ca14c773115b07656f1e3a433cd00fdfb93fbedf063f
+size 14575

finetuned_opt/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e631b06b7805e6b76878f6802122685be23f139a9528a5b7d5064c758aa0eea0
+size 627

finetuned_opt/checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

finetuned_opt/checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": true,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "1": {
+      "content": "<pad>",
+      "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
+    }
+  },
+  "bos_token": "</s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "</s>"
+}

finetuned_opt/checkpoint-2000/trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4906600249066004,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6226650062266501,
+      "grad_norm": 0.0,
+      "learning_rate": 3.9622249896222504e-05,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": NaN,
+      "eval_runtime": 154.5064,
+      "eval_samples_per_second": 3.508,
+      "eval_steps_per_second": 3.508,
+      "step": 803
+    },
+    {
+      "epoch": 1.2453300124533002,
+      "grad_norm": 0.0,
+      "learning_rate": 2.9244499792445003e-05,
+      "loss": 0.0,
+      "step": 1000
+    },
+    {
+      "epoch": 1.86799501867995,
+      "grad_norm": 0.0,
+      "learning_rate": 1.8866749688667497e-05,
+      "loss": 0.0,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": NaN,
+      "eval_runtime": 152.6303,
+      "eval_samples_per_second": 3.551,
+      "eval_steps_per_second": 3.551,
+      "step": 1606
+    },
+    {
+      "epoch": 2.4906600249066004,
+      "grad_norm": 0.0,
+      "learning_rate": 8.488999584889996e-06,
+      "loss": 0.0,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2409,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7451597365837824.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

finetuned_opt/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec94e88043c8d9f8f5ed99a8c4de459e905c871df64a0b285066748d671d4238
+size 4731