init

README.md

@@ -0,0 +1,158 @@
+---
+base_model: Qwen/Qwen1.5-14B-Chat
+library_name: peft
+license: other
+metrics:
+- accuracy
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: 20240819-183631_rm_qwen-rm-1e-5
+  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. -->
+
+# 20240819-183631_rm_qwen-rm-1e-5
+
+This model is a fine-tuned version of [Qwen/Qwen1.5-14B-Chat](https://huggingface.co/Qwen/Qwen1.5-14B-Chat) on the all_reward_cutoff_6000 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6893
+- Accuracy: 0.6641
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 4.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss | Accuracy |
+|:-------------:|:------:|:----:|:---------------:|:--------:|
+| 1.075         | 0.0431 | 50   | 1.0182          | 0.4932   |
+| 1.0505        | 0.0863 | 100  | 0.9944          | 0.5010   |
+| 0.9387        | 0.1294 | 150  | 0.9101          | 0.5049   |
+| 0.92          | 0.1726 | 200  | 0.9020          | 0.5049   |
+| 0.9531        | 0.2157 | 250  | 0.8868          | 0.5223   |
+| 0.849         | 0.2589 | 300  | 0.8567          | 0.5340   |
+| 0.8897        | 0.3020 | 350  | 0.8523          | 0.5262   |
+| 0.8512        | 0.3452 | 400  | 0.8105          | 0.5262   |
+| 0.7854        | 0.3883 | 450  | 0.7994          | 0.5107   |
+| 0.8147        | 0.4315 | 500  | 0.7859          | 0.5398   |
+| 0.8075        | 0.4746 | 550  | 0.7566          | 0.5553   |
+| 0.8282        | 0.5178 | 600  | 0.7454          | 0.5146   |
+| 0.7524        | 0.5609 | 650  | 0.7317          | 0.4990   |
+| 0.7338        | 0.6041 | 700  | 0.7267          | 0.5340   |
+| 0.7909        | 0.6472 | 750  | 0.7111          | 0.5612   |
+| 0.7783        | 0.6904 | 800  | 0.7211          | 0.5301   |
+| 0.7895        | 0.7335 | 850  | 0.7070          | 0.5592   |
+| 0.6881        | 0.7767 | 900  | 0.7710          | 0.5379   |
+| 0.7137        | 0.8198 | 950  | 0.6908          | 0.5806   |
+| 0.6924        | 0.8630 | 1000 | 0.6857          | 0.6      |
+| 0.7275        | 0.9061 | 1050 | 0.6835          | 0.5767   |
+| 0.67          | 0.9493 | 1100 | 0.6888          | 0.5709   |
+| 0.6787        | 0.9924 | 1150 | 0.6860          | 0.5961   |
+| 0.7012        | 1.0356 | 1200 | 0.6847          | 0.5709   |
+| 0.6765        | 1.0787 | 1250 | 0.6961          | 0.5786   |
+| 0.7052        | 1.1219 | 1300 | 0.6881          | 0.6058   |
+| 0.6804        | 1.1650 | 1350 | 0.6778          | 0.6097   |
+| 0.6644        | 1.2082 | 1400 | 0.6810          | 0.6194   |
+| 0.6566        | 1.2513 | 1450 | 0.6820          | 0.6136   |
+| 0.7024        | 1.2945 | 1500 | 0.6745          | 0.6117   |
+| 0.7241        | 1.3376 | 1550 | 0.6698          | 0.6136   |
+| 0.7378        | 1.3808 | 1600 | 0.6734          | 0.6058   |
+| 0.6584        | 1.4239 | 1650 | 0.6994          | 0.6      |
+| 0.6724        | 1.4671 | 1700 | 0.6715          | 0.6097   |
+| 0.6774        | 1.5102 | 1750 | 0.6700          | 0.6136   |
+| 0.6653        | 1.5534 | 1800 | 0.6696          | 0.6097   |
+| 0.6641        | 1.5965 | 1850 | 0.6733          | 0.5981   |
+| 0.7241        | 1.6397 | 1900 | 0.6653          | 0.5961   |
+| 0.6496        | 1.6828 | 1950 | 0.6761          | 0.6117   |
+| 0.662         | 1.7260 | 2000 | 0.6729          | 0.6039   |
+| 0.7049        | 1.7691 | 2050 | 0.6758          | 0.6136   |
+| 0.6483        | 1.8123 | 2100 | 0.6742          | 0.6136   |
+| 0.678         | 1.8554 | 2150 | 0.6696          | 0.6311   |
+| 0.678         | 1.8986 | 2200 | 0.6690          | 0.6233   |
+| 0.6953        | 1.9417 | 2250 | 0.6624          | 0.6252   |
+| 0.6969        | 1.9849 | 2300 | 0.6725          | 0.6369   |
+| 0.6492        | 2.0280 | 2350 | 0.6568          | 0.6485   |
+| 0.6572        | 2.0712 | 2400 | 0.6698          | 0.6447   |
+| 0.6204        | 2.1143 | 2450 | 0.6550          | 0.6544   |
+| 0.6479        | 2.1575 | 2500 | 0.6610          | 0.6447   |
+| 0.6954        | 2.2006 | 2550 | 0.6637          | 0.6680   |
+| 0.5668        | 2.2438 | 2600 | 0.6660          | 0.6583   |
+| 0.6185        | 2.2869 | 2650 | 0.6793          | 0.6680   |
+| 0.5314        | 2.3301 | 2700 | 0.6752          | 0.6718   |
+| 0.6406        | 2.3732 | 2750 | 0.6681          | 0.6563   |
+| 0.7011        | 2.4164 | 2800 | 0.6722          | 0.6680   |
+| 0.6195        | 2.4595 | 2850 | 0.6644          | 0.6757   |
+| 0.6675        | 2.5027 | 2900 | 0.6530          | 0.6602   |
+| 0.5796        | 2.5458 | 2950 | 0.6489          | 0.6602   |
+| 0.6148        | 2.5890 | 3000 | 0.6675          | 0.6680   |
+| 0.6293        | 2.6321 | 3050 | 0.6685          | 0.6369   |
+| 0.6095        | 2.6753 | 3100 | 0.6718          | 0.6621   |
+| 0.5422        | 2.7184 | 3150 | 0.6905          | 0.6485   |
+| 0.6089        | 2.7616 | 3200 | 0.6814          | 0.6544   |
+| 0.6238        | 2.8047 | 3250 | 0.6739          | 0.6466   |
+| 0.7386        | 2.8479 | 3300 | 0.6622          | 0.6485   |
+| 0.6166        | 2.8910 | 3350 | 0.6567          | 0.6544   |
+| 0.5866        | 2.9342 | 3400 | 0.6616          | 0.6505   |
+| 0.6348        | 2.9773 | 3450 | 0.6634          | 0.6563   |
+| 0.5907        | 3.0205 | 3500 | 0.6642          | 0.6583   |
+| 0.4985        | 3.0636 | 3550 | 0.6904          | 0.6544   |
+| 0.53          | 3.1068 | 3600 | 0.6926          | 0.6466   |
+| 0.5728        | 3.1499 | 3650 | 0.6939          | 0.6544   |
+| 0.5011        | 3.1931 | 3700 | 0.6916          | 0.6602   |
+| 0.4987        | 3.2362 | 3750 | 0.6906          | 0.6544   |
+| 0.5909        | 3.2794 | 3800 | 0.6882          | 0.6583   |
+| 0.5194        | 3.3225 | 3850 | 0.6874          | 0.6524   |
+| 0.5925        | 3.3657 | 3900 | 0.6854          | 0.6602   |
+| 0.4709        | 3.4088 | 3950 | 0.6879          | 0.6621   |
+| 0.5317        | 3.4520 | 4000 | 0.6886          | 0.6602   |
+| 0.5821        | 3.4951 | 4050 | 0.6889          | 0.6660   |
+| 0.5887        | 3.5383 | 4100 | 0.6891          | 0.6641   |
+| 0.5362        | 3.5814 | 4150 | 0.6879          | 0.6641   |
+| 0.4971        | 3.6246 | 4200 | 0.6888          | 0.6641   |
+| 0.5009        | 3.6677 | 4250 | 0.6899          | 0.6641   |
+| 0.5813        | 3.7109 | 4300 | 0.6887          | 0.6621   |
+| 0.6147        | 3.7540 | 4350 | 0.6891          | 0.6641   |
+| 0.6033        | 3.7972 | 4400 | 0.6891          | 0.6641   |
+| 0.565         | 3.8403 | 4450 | 0.6891          | 0.6660   |
+| 0.5044        | 3.8835 | 4500 | 0.6893          | 0.6641   |
+| 0.613         | 3.9266 | 4550 | 0.6894          | 0.6660   |
+| 0.4614        | 3.9698 | 4600 | 0.6896          | 0.6641   |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.43.4
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-14B-Chat",
+  "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": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "k_proj",
+    "down_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 sha256:644d9df2baa902d7309573e8b02b4bb0ea91a273749961d88dc0da24c5b2998c
+size 124756544

added_tokens.json

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

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.997411003236246,
+    "eval_accuracy": 0.6640776699029126,
+    "eval_loss": 0.6892674565315247,
+    "eval_runtime": 320.8936,
+    "eval_samples_per_second": 1.605,
+    "eval_steps_per_second": 1.605,
+    "total_flos": 0.0,
+    "train_loss": 0.6694142627746947,
+    "train_runtime": 66014.9203,
+    "train_samples_per_second": 0.281,
+    "train_steps_per_second": 0.07
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.997411003236246,
+    "eval_accuracy": 0.6640776699029126,
+    "eval_loss": 0.6892674565315247,
+    "eval_runtime": 320.8936,
+    "eval_samples_per_second": 1.605,
+    "eval_steps_per_second": 1.605
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "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 +1,44 @@
+{
+  "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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.997411003236246,
+    "total_flos": 0.0,
+    "train_loss": 0.6694142627746947,
+    "train_runtime": 66014.9203,
+    "train_samples_per_second": 0.281,
+    "train_steps_per_second": 0.07
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c27aae13966f8d29cf532f061e2cc40c91aade7e1806f67541fa8f4d331e219
+size 5432

value_head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5b94b8226272a90516bb5a06e5501672ffd0c038f8ca4a3f31dfbcbc9d3fa2a
+size 20684