Upload folder using huggingface_hub

README.md

@@ -0,0 +1,60 @@
+---
+license: other
+base_model: Qwen/Qwen1.5-1.8B
+tags:
+- generated_from_trainer
+datasets:
+- minghaowu/kill_that_reviewer
+model-index:
+- name: Qwen1.5-1.8B-ktr
+  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. -->
+
+# Qwen1.5-1.8B-ktr
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-1.8B](https://huggingface.co/Qwen/Qwen1.5-1.8B) on the minghaowu/kill_that_reviewer 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.96,
+    "train_loss": 0.41267242623913675,
+    "train_runtime": 2160.1701,
+    "train_samples": 2000,
+    "train_samples_per_second": 4.629,
+    "train_steps_per_second": 0.144
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.39.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad0f92a195e578d6f0f388b5682f1fe2b42f333e78c75a09c383d3479bdcc0a9
+size 3673690696

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.96,
+    "train_loss": 0.41267242623913675,
+    "train_runtime": 2160.1701,
+    "train_samples": 2000,
+    "train_samples_per_second": 4.629,
+    "train_steps_per_second": 0.144
+}

trainer_state.json

@@ -0,0 +1,247 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.96,
+  "eval_steps": 500,
+  "global_step": 310,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 17.163537984134056,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 3.247,
+      "step": 10
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.018646756033027,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.9917,
+      "step": 20
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.102932183151889,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 0.5627,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.1713603687439784,
+      "learning_rate": 4.8387096774193554e-05,
+      "loss": 0.5618,
+      "step": 40
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.4859823149760207,
+      "learning_rate": 4.659498207885305e-05,
+      "loss": 0.5205,
+      "step": 50
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 2.272313000462373,
+      "learning_rate": 4.4802867383512545e-05,
+      "loss": 0.5124,
+      "step": 60
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 2.5273618623771386,
+      "learning_rate": 4.301075268817205e-05,
+      "loss": 0.4395,
+      "step": 70
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.90386763992575,
+      "learning_rate": 4.121863799283154e-05,
+      "loss": 0.4075,
+      "step": 80
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 2.1818059655411046,
+      "learning_rate": 3.9426523297491045e-05,
+      "loss": 0.4218,
+      "step": 90
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.8586027320750607,
+      "learning_rate": 3.763440860215054e-05,
+      "loss": 0.4045,
+      "step": 100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.367612894945561,
+      "learning_rate": 3.5842293906810036e-05,
+      "loss": 0.4047,
+      "step": 110
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 1.7552435519555452,
+      "learning_rate": 3.405017921146954e-05,
+      "loss": 0.4006,
+      "step": 120
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 1.6187500706970905,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.3502,
+      "step": 130
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 1.621006239401913,
+      "learning_rate": 3.046594982078853e-05,
+      "loss": 0.2912,
+      "step": 140
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 1.8302472177918652,
+      "learning_rate": 2.8673835125448028e-05,
+      "loss": 0.2914,
+      "step": 150
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 2.137720741340305,
+      "learning_rate": 2.6881720430107527e-05,
+      "loss": 0.2976,
+      "step": 160
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 1.6840762975810266,
+      "learning_rate": 2.5089605734767026e-05,
+      "loss": 0.306,
+      "step": 170
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.623859665642121,
+      "learning_rate": 2.3297491039426525e-05,
+      "loss": 0.3036,
+      "step": 180
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 1.4462761218350422,
+      "learning_rate": 2.1505376344086024e-05,
+      "loss": 0.2824,
+      "step": 190
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 1.5715993286842083,
+      "learning_rate": 1.9713261648745522e-05,
+      "loss": 0.1915,
+      "step": 200
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 1.40640376627855,
+      "learning_rate": 1.7921146953405018e-05,
+      "loss": 0.197,
+      "step": 210
+    },
+    {
+      "epoch": 3.52,
+      "grad_norm": 1.5607010212609245,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 0.1906,
+      "step": 220
+    },
+    {
+      "epoch": 3.68,
+      "grad_norm": 1.4815811366542657,
+      "learning_rate": 1.4336917562724014e-05,
+      "loss": 0.1974,
+      "step": 230
+    },
+    {
+      "epoch": 3.84,
+      "grad_norm": 1.5236794304094388,
+      "learning_rate": 1.2544802867383513e-05,
+      "loss": 0.1973,
+      "step": 240
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.3798039353727727,
+      "learning_rate": 1.0752688172043012e-05,
+      "loss": 0.1867,
+      "step": 250
+    },
+    {
+      "epoch": 4.16,
+      "grad_norm": 1.3649861078638328,
+      "learning_rate": 8.960573476702509e-06,
+      "loss": 0.11,
+      "step": 260
+    },
+    {
+      "epoch": 4.32,
+      "grad_norm": 1.254492221709335,
+      "learning_rate": 7.168458781362007e-06,
+      "loss": 0.1094,
+      "step": 270
+    },
+    {
+      "epoch": 4.48,
+      "grad_norm": 1.189476576700767,
+      "learning_rate": 5.376344086021506e-06,
+      "loss": 0.1111,
+      "step": 280
+    },
+    {
+      "epoch": 4.64,
+      "grad_norm": 1.1598377753968125,
+      "learning_rate": 3.5842293906810035e-06,
+      "loss": 0.1026,
+      "step": 290
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 1.0113867726860153,
+      "learning_rate": 1.7921146953405017e-06,
+      "loss": 0.1001,
+      "step": 300
+    },
+    {
+      "epoch": 4.96,
+      "grad_norm": 0.9129278851969916,
+      "learning_rate": 0.0,
+      "loss": 0.102,
+      "step": 310
+    },
+    {
+      "epoch": 4.96,
+      "step": 310,
+      "total_flos": 2.2549700766859264e+16,
+      "train_loss": 0.41267242623913675,
+      "train_runtime": 2160.1701,
+      "train_samples_per_second": 4.629,
+      "train_steps_per_second": 0.144
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 310,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2.2549700766859264e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51986c81930ab15434e32815906cef061c2bccc977d0c8fa9c61de4f5178f52a
+size 6200