Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: Qwen/Qwen2-1.5B-Instruct
+library_name: peft
+license: other
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2024-06-17-19-49-05
+  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_2024-06-17-19-49-05
+
+This model is a fine-tuned version of [Qwen/Qwen2-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2-1.5B-Instruct) on the glaive_toolcall_zh and the glaive_toolcall_en datasets.
+
+## 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: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 8
+- 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: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B-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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_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 sha256:1ee7344c30e4a82b5d39ec5658f22cd1b2276c90ecba3888af07aaba4d5d8baa
+size 36981072

added_tokens.json

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

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.976,
+    "num_input_tokens_seen": 3930992,
+    "total_flos": 3.112338516554547e+16,
+    "train_loss": 0.7158093615885703,
+    "train_runtime": 1518.3826,
+    "train_samples_per_second": 3.952,
+    "train_steps_per_second": 0.122
+}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen2-1.5B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-100/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2-1.5B-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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142b541804154cdf55535cba3bf359060655705c04b2c70424439acab5776e94
+size 36981072

checkpoint-100/added_tokens.json

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

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:896f35e3a63391ce73f91fc816e88b284f2576bc9ae78f947efe30b98075b4b5
+size 74188650

checkpoint-100/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cb795a5cea0baa625c50007a6c9da09c6bbb5c16b560424070384a479e7d8a6
+size 14512

checkpoint-100/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f19604377bd828eb366c68946ad997a4ff4d69beaeea93ee58915135768ec63
+size 14512

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55724697010011e64bbf43c3defc76460bd60cacef335b6b65467214bd93cd54
+size 1064

checkpoint-100/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
+  }
+}

checkpoint-100/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
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,193 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.19458943605422974,
+      "learning_rate": 4.9910902453260824e-05,
+      "loss": 0.8099,
+      "num_input_tokens_seen": 114944,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.23063905537128448,
+      "learning_rate": 4.964424488287009e-05,
+      "loss": 0.958,
+      "num_input_tokens_seen": 227728,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.22587424516677856,
+      "learning_rate": 4.920192797165511e-05,
+      "loss": 0.715,
+      "num_input_tokens_seen": 326640,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.17264235019683838,
+      "learning_rate": 4.858710446774951e-05,
+      "loss": 0.7585,
+      "num_input_tokens_seen": 437280,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.19875957071781158,
+      "learning_rate": 4.780415671242334e-05,
+      "loss": 0.7342,
+      "num_input_tokens_seen": 530192,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.36600446701049805,
+      "learning_rate": 4.685866540361456e-05,
+      "loss": 0.6904,
+      "num_input_tokens_seen": 634960,
+      "step": 30
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.20120520889759064,
+      "learning_rate": 4.5757369817809415e-05,
+      "loss": 0.8254,
+      "num_input_tokens_seen": 740704,
+      "step": 35
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.22245633602142334,
+      "learning_rate": 4.45081197738023e-05,
+      "loss": 0.7551,
+      "num_input_tokens_seen": 841600,
+      "step": 40
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.27814680337905884,
+      "learning_rate": 4.3119819680728e-05,
+      "loss": 0.7747,
+      "num_input_tokens_seen": 947648,
+      "step": 45
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.27052441239356995,
+      "learning_rate": 4.160236506918098e-05,
+      "loss": 0.7027,
+      "num_input_tokens_seen": 1047520,
+      "step": 50
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.38937926292419434,
+      "learning_rate": 3.9966572057815373e-05,
+      "loss": 0.7581,
+      "num_input_tokens_seen": 1148080,
+      "step": 55
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.37379005551338196,
+      "learning_rate": 3.822410025817406e-05,
+      "loss": 0.7221,
+      "num_input_tokens_seen": 1252880,
+      "step": 60
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.34213003516197205,
+      "learning_rate": 3.638736966726585e-05,
+      "loss": 0.8214,
+      "num_input_tokens_seen": 1364304,
+      "step": 65
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.33407434821128845,
+      "learning_rate": 3.44694721402644e-05,
+      "loss": 0.6304,
+      "num_input_tokens_seen": 1466240,
+      "step": 70
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.33909159898757935,
+      "learning_rate": 3.2484078074333954e-05,
+      "loss": 0.6434,
+      "num_input_tokens_seen": 1558752,
+      "step": 75
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4054814577102661,
+      "learning_rate": 3.0445338968721287e-05,
+      "loss": 0.6796,
+      "num_input_tokens_seen": 1668480,
+      "step": 80
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.2723485231399536,
+      "learning_rate": 2.836778655564653e-05,
+      "loss": 0.6651,
+      "num_input_tokens_seen": 1773264,
+      "step": 85
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.3467393219470978,
+      "learning_rate": 2.6266229220967818e-05,
+      "loss": 0.7844,
+      "num_input_tokens_seen": 1885920,
+      "step": 90
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.4250239431858063,
+      "learning_rate": 2.4155646452913296e-05,
+      "loss": 0.8139,
+      "num_input_tokens_seen": 1996656,
+      "step": 95
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.30656036734580994,
+      "learning_rate": 2.2051082071228854e-05,
+      "loss": 0.6717,
+      "num_input_tokens_seen": 2102896,
+      "step": 100
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 186,
+  "num_input_tokens_seen": 2102896,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.664954843267072e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25fff679805feed7cb125ffaa9aa318c0b1ee7ef433e1a91fc410bc3dfcec03b
+size 5304

llamaboard_config.yaml

@@ -0,0 +1,65 @@
+top.booster: none
+top.checkpoint_path: null
+top.finetuning_type: lora
+top.model_name: Qwen2-1.5B-Chat
+top.quantization_bit: '4'
+top.rope_scaling: none
+top.template: qwen
+top.visual_inputs: false
+train.additional_target: ''
+train.badam_mode: layer
+train.badam_switch_interval: 50
+train.badam_switch_mode: ascending
+train.badam_update_ratio: 0.05
+train.batch_size: 2
+train.compute_type: fp16
+train.create_new_adapter: false
+train.cutoff_len: 3024
+train.dataset:
+- glaive_toolcall_zh
+- glaive_toolcall_en
+train.dataset_dir: data
+train.ds_offload: false
+train.ds_stage: none
+train.freeze_extra_modules: ''
+train.freeze_trainable_layers: 2
+train.freeze_trainable_modules: all
+train.galore_rank: 16
+train.galore_scale: 0.25
+train.galore_target: all
+train.galore_update_interval: 200
+train.gradient_accumulation_steps: 8
+train.learning_rate: 5e-5
+train.logging_steps: 5
+train.lora_alpha: 16
+train.lora_dropout: 0
+train.lora_rank: 8
+train.lora_target: ''
+train.loraplus_lr_ratio: 0
+train.lr_scheduler_type: cosine
+train.max_grad_norm: '1.0'
+train.max_samples: '100000'
+train.neftune_alpha: 0
+train.num_train_epochs: '3.0'
+train.optim: adamw_torch
+train.packing: false
+train.ppo_score_norm: false
+train.ppo_whiten_rewards: false
+train.pref_beta: 0.1
+train.pref_ftx: 0
+train.pref_loss: sigmoid
+train.report_to: false
+train.resize_vocab: false
+train.reward_model: null
+train.save_steps: 100
+train.shift_attn: false
+train.training_stage: Supervised Fine-Tuning
+train.upcast_layernorm: false
+train.use_badam: false
+train.use_dora: false
+train.use_galore: false
+train.use_llama_pro: false
+train.use_pissa: false
+train.use_rslora: false
+train.val_size: 0
+train.warmup_steps: 0

running_log.txt

@@ -0,0 +1,334 @@
+06/17/2024 19:50:24 - INFO - transformers.models.auto.tokenization_auto - Could not locate the tokenizer configuration file, will try to use the model config instead.
+
+06/17/2024 19:50:25 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json
+
+06/17/2024 19:50:25 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+
+06/17/2024 19:50:30 - INFO - transformers.tokenization_utils_base - loading file vocab.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/vocab.json
+
+06/17/2024 19:50:30 - INFO - transformers.tokenization_utils_base - loading file merges.txt from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/merges.txt
+
+06/17/2024 19:50:30 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer.json
+
+06/17/2024 19:50:30 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at None
+
+06/17/2024 19:50:30 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at None
+
+06/17/2024 19:50:30 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/tokenizer_config.json
+
+06/17/2024 19:50:31 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+06/17/2024 19:50:31 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+06/17/2024 19:50:31 - WARNING - transformers.tokenization_utils_base - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+
+06/17/2024 19:50:31 - INFO - llamafactory.data.template - Replace eos token: <|im_end|>
+
+06/17/2024 19:50:31 - INFO - llamafactory.data.loader - Loading dataset llamafactory/glaive_toolcall_zh...
+
+06/17/2024 19:50:37 - INFO - llamafactory.data.loader - Loading dataset llamafactory/glaive_toolcall_en...
+
+06/17/2024 19:50:43 - INFO - llamafactory.data.loader - Loading dataset llamafactory/glaive_toolcall_zh...
+
+06/17/2024 19:50:47 - INFO - llamafactory.data.loader - Loading dataset llamafactory/glaive_toolcall_en...
+
+06/17/2024 19:50:52 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json
+
+06/17/2024 19:50:52 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "_name_or_path": "Qwen/Qwen2-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+
+06/17/2024 19:50:52 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit.
+
+06/17/2024 19:50:52 - INFO - llamafactory.model.model_utils.quantization - Quantizing model to 4 bit.
+
+06/17/2024 19:50:59 - INFO - transformers.modeling_utils - loading weights file model.safetensors from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/model.safetensors
+
+06/17/2024 19:50:59 - INFO - transformers.modeling_utils - Instantiating Qwen2ForCausalLM model under default dtype torch.float16.
+
+06/17/2024 19:50:59 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "eos_token_id": 151645
+}
+
+
+06/17/2024 19:51:06 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing Qwen2ForCausalLM.
+
+
+06/17/2024 19:51:06 - INFO - transformers.modeling_utils - All the weights of Qwen2ForCausalLM were initialized from the model checkpoint at Qwen/Qwen2-1.5B-Instruct.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2ForCausalLM for predictions without further training.
+
+06/17/2024 19:51:06 - INFO - transformers.generation.configuration_utils - loading configuration file generation_config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/generation_config.json
+
+06/17/2024 19:51:06 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8
+}
+
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.model_utils.misc - Found linear modules: o_proj,v_proj,down_proj,gate_proj,k_proj,up_proj,q_proj
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.model_utils.checkpointing - Gradient checkpointing enabled.
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.adapter - Upcasting trainable params to float32.
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.adapter - Fine-tuning method: LoRA
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.model_utils.misc - Found linear modules: down_proj,k_proj,gate_proj,up_proj,o_proj,v_proj,q_proj
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.loader - trainable params: 9232384 || all params: 1552946688 || trainable%: 0.5945
+
+06/17/2024 19:51:07 - INFO - llamafactory.model.loader - trainable params: 9232384 || all params: 1552946688 || trainable%: 0.5945
+
+06/17/2024 19:51:07 - WARNING - accelerate.utils.other - Detected kernel version 5.4.0, which is below the recommended minimum of 5.5.0; this can cause the process to hang. It is recommended to upgrade the kernel to the minimum version or higher.
+
+06/17/2024 19:51:07 - INFO - transformers.trainer - Using auto half precision backend
+
+06/17/2024 19:51:07 - INFO - transformers.trainer - ***** Running training *****
+
+06/17/2024 19:51:07 - INFO - transformers.trainer -   Num examples = 2,000
+
+06/17/2024 19:51:07 - INFO - transformers.trainer -   Num Epochs = 3
+
+06/17/2024 19:51:07 - INFO - transformers.trainer -   Instantaneous batch size per device = 2
+
+06/17/2024 19:51:07 - INFO - transformers.trainer -   Total train batch size (w. parallel, distributed & accumulation) = 32
+
+06/17/2024 19:51:07 - INFO - transformers.trainer -   Gradient Accumulation steps = 8
+
+06/17/2024 19:51:07 - INFO - transformers.trainer -   Total optimization steps = 186
+
+06/17/2024 19:51:07 - INFO - transformers.trainer -   Number of trainable parameters = 9,232,384
+
+06/17/2024 19:51:52 - INFO - llamafactory.extras.callbacks - {'loss': 0.8099, 'learning_rate': 4.9911e-05, 'epoch': 0.08, 'throughput': 2566.78}
+
+06/17/2024 19:52:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.9580, 'learning_rate': 4.9644e-05, 'epoch': 0.16, 'throughput': 2542.66}
+
+06/17/2024 19:53:18 - INFO - llamafactory.extras.callbacks - {'loss': 0.7150, 'learning_rate': 4.9202e-05, 'epoch': 0.24, 'throughput': 2505.70}
+
+06/17/2024 19:54:02 - INFO - llamafactory.extras.callbacks - {'loss': 0.7585, 'learning_rate': 4.8587e-05, 'epoch': 0.32, 'throughput': 2511.00}
+
+06/17/2024 19:54:37 - INFO - llamafactory.extras.callbacks - {'loss': 0.7342, 'learning_rate': 4.7804e-05, 'epoch': 0.40, 'throughput': 2533.17}
+
+06/17/2024 19:55:16 - INFO - llamafactory.extras.callbacks - {'loss': 0.6904, 'learning_rate': 4.6859e-05, 'epoch': 0.48, 'throughput': 2557.91}
+
+06/17/2024 19:55:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.8254, 'learning_rate': 4.5757e-05, 'epoch': 0.56, 'throughput': 2587.35}
+
+06/17/2024 19:56:34 - INFO - llamafactory.extras.callbacks - {'loss': 0.7551, 'learning_rate': 4.4508e-05, 'epoch': 0.64, 'throughput': 2578.43}
+
+06/17/2024 19:57:15 - INFO - llamafactory.extras.callbacks - {'loss': 0.7747, 'learning_rate': 4.3120e-05, 'epoch': 0.72, 'throughput': 2580.98}
+
+06/17/2024 19:57:54 - INFO - llamafactory.extras.callbacks - {'loss': 0.7027, 'learning_rate': 4.1602e-05, 'epoch': 0.80, 'throughput': 2578.88}
+
+06/17/2024 19:58:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.7581, 'learning_rate': 3.9967e-05, 'epoch': 0.88, 'throughput': 2580.17}
+
+06/17/2024 19:59:13 - INFO - llamafactory.extras.callbacks - {'loss': 0.7221, 'learning_rate': 3.8224e-05, 'epoch': 0.96, 'throughput': 2583.14}
+
+06/17/2024 19:59:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.8214, 'learning_rate': 3.6387e-05, 'epoch': 1.04, 'throughput': 2587.56}
+
+06/17/2024 20:00:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.6304, 'learning_rate': 3.4469e-05, 'epoch': 1.12, 'throughput': 2580.91}
+
+06/17/2024 20:01:12 - INFO - llamafactory.extras.callbacks - {'loss': 0.6434, 'learning_rate': 3.2484e-05, 'epoch': 1.20, 'throughput': 2577.50}
+
+06/17/2024 20:01:55 - INFO - llamafactory.extras.callbacks - {'loss': 0.6796, 'learning_rate': 3.0445e-05, 'epoch': 1.28, 'throughput': 2575.34}
+
+06/17/2024 20:02:35 - INFO - llamafactory.extras.callbacks - {'loss': 0.6651, 'learning_rate': 2.8368e-05, 'epoch': 1.36, 'throughput': 2580.63}
+
+06/17/2024 20:03:17 - INFO - llamafactory.extras.callbacks - {'loss': 0.7844, 'learning_rate': 2.6266e-05, 'epoch': 1.44, 'throughput': 2586.23}
+
+06/17/2024 20:04:01 - INFO - llamafactory.extras.callbacks - {'loss': 0.8139, 'learning_rate': 2.4156e-05, 'epoch': 1.52, 'throughput': 2581.43}
+
+06/17/2024 20:04:43 - INFO - llamafactory.extras.callbacks - {'loss': 0.6717, 'learning_rate': 2.2051e-05, 'epoch': 1.60, 'throughput': 2578.63}
+
+06/17/2024 20:04:43 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-1.5B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-100
+
+06/17/2024 20:04:44 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json
+
+06/17/2024 20:04:44 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+
+06/17/2024 20:04:44 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-1.5B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-100/tokenizer_config.json
+
+06/17/2024 20:04:44 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-1.5B-Chat/lora/train_2024-06-17-19-49-05/checkpoint-100/special_tokens_map.json
+
+06/17/2024 20:05:27 - INFO - llamafactory.extras.callbacks - {'loss': 0.7524, 'learning_rate': 1.9968e-05, 'epoch': 1.68, 'throughput': 2577.77}
+
+06/17/2024 20:06:06 - INFO - llamafactory.extras.callbacks - {'loss': 0.6310, 'learning_rate': 1.7920e-05, 'epoch': 1.76, 'throughput': 2578.49}
+
+06/17/2024 20:06:48 - INFO - llamafactory.extras.callbacks - {'loss': 0.7462, 'learning_rate': 1.5923e-05, 'epoch': 1.84, 'throughput': 2578.25}
+
+06/17/2024 20:07:32 - INFO - llamafactory.extras.callbacks - {'loss': 0.6148, 'learning_rate': 1.3990e-05, 'epoch': 1.92, 'throughput': 2578.95}
+
+06/17/2024 20:08:10 - INFO - llamafactory.extras.callbacks - {'loss': 0.7145, 'learning_rate': 1.2136e-05, 'epoch': 2.00, 'throughput': 2582.83}
+
+06/17/2024 20:08:52 - INFO - llamafactory.extras.callbacks - {'loss': 0.6798, 'learning_rate': 1.0374e-05, 'epoch': 2.08, 'throughput': 2583.35}
+
+06/17/2024 20:09:31 - INFO - llamafactory.extras.callbacks - {'loss': 0.6754, 'learning_rate': 8.7157e-06, 'epoch': 2.16, 'throughput': 2584.30}
+
+06/17/2024 20:10:10 - INFO - llamafactory.extras.callbacks - {'loss': 0.6708, 'learning_rate': 7.1737e-06, 'epoch': 2.24, 'throughput': 2584.52}
+
+06/17/2024 20:10:46 - INFO - llamafactory.extras.callbacks - {'loss': 0.6386, 'learning_rate': 5.7587e-06, 'epoch': 2.32, 'throughput': 2587.95}
+
+06/17/2024 20:11:24 - INFO - llamafactory.extras.callbacks - {'loss': 0.6995, 'learning_rate': 4.4809e-06, 'epoch': 2.40, 'throughput': 2590.06}
+
+06/17/2024 20:12:06 - INFO - llamafactory.extras.callbacks - {'loss': 0.6691, 'learning_rate': 3.3494e-06, 'epoch': 2.48, 'throughput': 2593.15}
+
+06/17/2024 20:12:50 - INFO - llamafactory.extras.callbacks - {'loss': 0.6024, 'learning_rate': 2.3721e-06, 'epoch': 2.56, 'throughput': 2588.49}
+
+06/17/2024 20:13:28 - INFO - llamafactory.extras.callbacks - {'loss': 0.6484, 'learning_rate': 1.5562e-06, 'epoch': 2.64, 'throughput': 2591.26}
+
+06/17/2024 20:14:10 - INFO - llamafactory.extras.callbacks - {'loss': 0.7137, 'learning_rate': 9.0736e-07, 'epoch': 2.72, 'throughput': 2585.69}
+
+06/17/2024 20:14:56 - INFO - llamafactory.extras.callbacks - {'loss': 0.7770, 'learning_rate': 4.3025e-07, 'epoch': 2.80, 'throughput': 2589.29}
+
+06/17/2024 20:15:36 - INFO - llamafactory.extras.callbacks - {'loss': 0.6529, 'learning_rate': 1.2827e-07, 'epoch': 2.88, 'throughput': 2590.50}
+
+06/17/2024 20:16:16 - INFO - llamafactory.extras.callbacks - {'loss': 0.6996, 'learning_rate': 3.5659e-09, 'epoch': 2.96, 'throughput': 2590.41}
+
+06/17/2024 20:16:26 - INFO - transformers.trainer - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+06/17/2024 20:16:26 - INFO - transformers.trainer - Saving model checkpoint to saves/Qwen2-1.5B-Chat/lora/train_2024-06-17-19-49-05
+
+06/17/2024 20:16:27 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/featurize/.cache/huggingface/hub/models--Qwen--Qwen2-1.5B-Instruct/snapshots/ba1cf1846d7df0a0591d6c00649f57e798519da8/config.json
+
+06/17/2024 20:16:27 - INFO - transformers.configuration_utils - Model config Qwen2Config {
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
+
+
+06/17/2024 20:16:27 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Qwen2-1.5B-Chat/lora/train_2024-06-17-19-49-05/tokenizer_config.json
+
+06/17/2024 20:16:27 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Qwen2-1.5B-Chat/lora/train_2024-06-17-19-49-05/special_tokens_map.json
+
+06/17/2024 20:16:27 - WARNING - llamafactory.extras.ploting - No metric eval_loss to plot.
+
+06/17/2024 20:16:27 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

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 +1,9 @@
+{
+    "epoch": 2.976,
+    "num_input_tokens_seen": 3930992,
+    "total_flos": 3.112338516554547e+16,
+    "train_loss": 0.7158093615885703,
+    "train_runtime": 1518.3826,
+    "train_samples_per_second": 3.952,
+    "train_steps_per_second": 0.122
+}

trainer_log.jsonl

@@ -0,0 +1,38 @@
+{"current_steps": 5, "total_steps": 186, "loss": 0.8099, "learning_rate": 4.9910902453260824e-05, "epoch": 0.08, "percentage": 2.69, "elapsed_time": "0:00:44", "remaining_time": "0:27:01", "throughput": "2566.78", "total_tokens": 114944}
+{"current_steps": 10, "total_steps": 186, "loss": 0.958, "learning_rate": 4.964424488287009e-05, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:01:29", "remaining_time": "0:26:16", "throughput": "2542.66", "total_tokens": 227728}
+{"current_steps": 15, "total_steps": 186, "loss": 0.715, "learning_rate": 4.920192797165511e-05, "epoch": 0.24, "percentage": 8.06, "elapsed_time": "0:02:10", "remaining_time": "0:24:46", "throughput": "2505.70", "total_tokens": 326640}
+{"current_steps": 20, "total_steps": 186, "loss": 0.7585, "learning_rate": 4.858710446774951e-05, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:02:54", "remaining_time": "0:24:05", "throughput": "2511.00", "total_tokens": 437280}
+{"current_steps": 25, "total_steps": 186, "loss": 0.7342, "learning_rate": 4.780415671242334e-05, "epoch": 0.4, "percentage": 13.44, "elapsed_time": "0:03:29", "remaining_time": "0:22:27", "throughput": "2533.17", "total_tokens": 530192}
+{"current_steps": 30, "total_steps": 186, "loss": 0.6904, "learning_rate": 4.685866540361456e-05, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:04:08", "remaining_time": "0:21:30", "throughput": "2557.91", "total_tokens": 634960}
+{"current_steps": 35, "total_steps": 186, "loss": 0.8254, "learning_rate": 4.5757369817809415e-05, "epoch": 0.56, "percentage": 18.82, "elapsed_time": "0:04:46", "remaining_time": "0:20:35", "throughput": "2587.35", "total_tokens": 740704}
+{"current_steps": 40, "total_steps": 186, "loss": 0.7551, "learning_rate": 4.45081197738023e-05, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:05:26", "remaining_time": "0:19:51", "throughput": "2578.43", "total_tokens": 841600}
+{"current_steps": 45, "total_steps": 186, "loss": 0.7747, "learning_rate": 4.3119819680728e-05, "epoch": 0.72, "percentage": 24.19, "elapsed_time": "0:06:07", "remaining_time": "0:19:10", "throughput": "2580.98", "total_tokens": 947648}
+{"current_steps": 50, "total_steps": 186, "loss": 0.7027, "learning_rate": 4.160236506918098e-05, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:06:46", "remaining_time": "0:18:24", "throughput": "2578.88", "total_tokens": 1047520}
+{"current_steps": 55, "total_steps": 186, "loss": 0.7581, "learning_rate": 3.9966572057815373e-05, "epoch": 0.88, "percentage": 29.57, "elapsed_time": "0:07:24", "remaining_time": "0:17:39", "throughput": "2580.17", "total_tokens": 1148080}
+{"current_steps": 60, "total_steps": 186, "loss": 0.7221, "learning_rate": 3.822410025817406e-05, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:08:05", "remaining_time": "0:16:58", "throughput": "2583.14", "total_tokens": 1252880}
+{"current_steps": 65, "total_steps": 186, "loss": 0.8214, "learning_rate": 3.638736966726585e-05, "epoch": 1.04, "percentage": 34.95, "elapsed_time": "0:08:47", "remaining_time": "0:16:21", "throughput": "2587.56", "total_tokens": 1364304}
+{"current_steps": 70, "total_steps": 186, "loss": 0.6304, "learning_rate": 3.44694721402644e-05, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:09:28", "remaining_time": "0:15:41", "throughput": "2580.91", "total_tokens": 1466240}
+{"current_steps": 75, "total_steps": 186, "loss": 0.6434, "learning_rate": 3.2484078074333954e-05, "epoch": 1.2, "percentage": 40.32, "elapsed_time": "0:10:04", "remaining_time": "0:14:55", "throughput": "2577.50", "total_tokens": 1558752}
+{"current_steps": 80, "total_steps": 186, "loss": 0.6796, "learning_rate": 3.0445338968721287e-05, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:10:47", "remaining_time": "0:14:18", "throughput": "2575.34", "total_tokens": 1668480}
+{"current_steps": 85, "total_steps": 186, "loss": 0.6651, "learning_rate": 2.836778655564653e-05, "epoch": 1.3599999999999999, "percentage": 45.7, "elapsed_time": "0:11:27", "remaining_time": "0:13:36", "throughput": "2580.63", "total_tokens": 1773264}
+{"current_steps": 90, "total_steps": 186, "loss": 0.7844, "learning_rate": 2.6266229220967818e-05, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:12:09", "remaining_time": "0:12:57", "throughput": "2586.23", "total_tokens": 1885920}
+{"current_steps": 95, "total_steps": 186, "loss": 0.8139, "learning_rate": 2.4155646452913296e-05, "epoch": 1.52, "percentage": 51.08, "elapsed_time": "0:12:53", "remaining_time": "0:12:20", "throughput": "2581.43", "total_tokens": 1996656}
+{"current_steps": 100, "total_steps": 186, "loss": 0.6717, "learning_rate": 2.2051082071228854e-05, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:13:35", "remaining_time": "0:11:41", "throughput": "2578.63", "total_tokens": 2102896}
+{"current_steps": 105, "total_steps": 186, "loss": 0.7524, "learning_rate": 1.9967536997783494e-05, "epoch": 1.6800000000000002, "percentage": 56.45, "elapsed_time": "0:14:18", "remaining_time": "0:11:02", "throughput": "2577.77", "total_tokens": 2214272}
+{"current_steps": 110, "total_steps": 186, "loss": 0.631, "learning_rate": 1.79198623329424e-05, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:14:58", "remaining_time": "0:10:20", "throughput": "2578.49", "total_tokens": 2316448}
+{"current_steps": 115, "total_steps": 186, "loss": 0.7462, "learning_rate": 1.5922653499838137e-05, "epoch": 1.8399999999999999, "percentage": 61.83, "elapsed_time": "0:15:40", "remaining_time": "0:09:40", "throughput": "2578.25", "total_tokens": 2425248}
+{"current_steps": 120, "total_steps": 186, "loss": 0.6148, "learning_rate": 1.399014621105914e-05, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:16:23", "remaining_time": "0:09:01", "throughput": "2578.95", "total_tokens": 2537680}
+{"current_steps": 125, "total_steps": 186, "loss": 0.7145, "learning_rate": 1.2136114999284288e-05, "epoch": 2.0, "percentage": 67.2, "elapsed_time": "0:17:02", "remaining_time": "0:08:19", "throughput": "2582.83", "total_tokens": 2642080}
+{"current_steps": 130, "total_steps": 186, "loss": 0.6798, "learning_rate": 1.0373775035117305e-05, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "0:17:44", "remaining_time": "0:07:38", "throughput": "2583.35", "total_tokens": 2750752}
+{"current_steps": 135, "total_steps": 186, "loss": 0.6754, "learning_rate": 8.715687931944449e-06, "epoch": 2.16, "percentage": 72.58, "elapsed_time": "0:18:23", "remaining_time": "0:06:56", "throughput": "2584.30", "total_tokens": 2852096}
+{"current_steps": 140, "total_steps": 186, "loss": 0.6708, "learning_rate": 7.173672209219495e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:19:02", "remaining_time": "0:06:15", "throughput": "2584.52", "total_tokens": 2951888}
+{"current_steps": 145, "total_steps": 186, "loss": 0.6386, "learning_rate": 5.758719052376693e-06, "epoch": 2.32, "percentage": 77.96, "elapsed_time": "0:19:38", "remaining_time": "0:05:33", "throughput": "2587.95", "total_tokens": 3049616}
+{"current_steps": 150, "total_steps": 186, "loss": 0.6995, "learning_rate": 4.480913969818098e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:20:16", "remaining_time": "0:04:51", "throughput": "2590.06", "total_tokens": 3150784}
+{"current_steps": 155, "total_steps": 186, "loss": 0.6691, "learning_rate": 3.3493649053890326e-06, "epoch": 2.48, "percentage": 83.33, "elapsed_time": "0:20:58", "remaining_time": "0:04:11", "throughput": "2593.15", "total_tokens": 3262992}
+{"current_steps": 160, "total_steps": 186, "loss": 0.6024, "learning_rate": 2.372137318741968e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:21:42", "remaining_time": "0:03:31", "throughput": "2588.49", "total_tokens": 3371440}
+{"current_steps": 165, "total_steps": 186, "loss": 0.6484, "learning_rate": 1.5561966963229924e-06, "epoch": 2.64, "percentage": 88.71, "elapsed_time": "0:22:20", "remaining_time": "0:02:50", "throughput": "2591.26", "total_tokens": 3473680}
+{"current_steps": 170, "total_steps": 186, "loss": 0.7137, "learning_rate": 9.073589027514789e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:23:02", "remaining_time": "0:02:10", "throughput": "2585.69", "total_tokens": 3574736}
+{"current_steps": 175, "total_steps": 186, "loss": 0.777, "learning_rate": 4.302487264785521e-07, "epoch": 2.8, "percentage": 94.09, "elapsed_time": "0:23:48", "remaining_time": "0:01:29", "throughput": "2589.29", "total_tokens": 3697920}
+{"current_steps": 180, "total_steps": 186, "loss": 0.6529, "learning_rate": 1.2826691520262114e-07, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:24:28", "remaining_time": "0:00:48", "throughput": "2590.50", "total_tokens": 3803552}
+{"current_steps": 185, "total_steps": 186, "loss": 0.6996, "learning_rate": 3.565936007254855e-09, "epoch": 2.96, "percentage": 99.46, "elapsed_time": "0:25:08", "remaining_time": "0:00:08", "throughput": "2590.41", "total_tokens": 3907456}
+{"current_steps": 186, "total_steps": 186, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:25:18", "remaining_time": "0:00:00", "throughput": "2589.06", "total_tokens": 3930992}

trainer_state.json

@@ -0,0 +1,339 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.976,
+  "eval_steps": 500,
+  "global_step": 186,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.19458943605422974,
+      "learning_rate": 4.9910902453260824e-05,
+      "loss": 0.8099,
+      "num_input_tokens_seen": 114944,
+      "step": 5
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.23063905537128448,
+      "learning_rate": 4.964424488287009e-05,
+      "loss": 0.958,
+      "num_input_tokens_seen": 227728,
+      "step": 10
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.22587424516677856,
+      "learning_rate": 4.920192797165511e-05,
+      "loss": 0.715,
+      "num_input_tokens_seen": 326640,
+      "step": 15
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.17264235019683838,
+      "learning_rate": 4.858710446774951e-05,
+      "loss": 0.7585,
+      "num_input_tokens_seen": 437280,
+      "step": 20
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.19875957071781158,
+      "learning_rate": 4.780415671242334e-05,
+      "loss": 0.7342,
+      "num_input_tokens_seen": 530192,
+      "step": 25
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.36600446701049805,
+      "learning_rate": 4.685866540361456e-05,
+      "loss": 0.6904,
+      "num_input_tokens_seen": 634960,
+      "step": 30
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.20120520889759064,
+      "learning_rate": 4.5757369817809415e-05,
+      "loss": 0.8254,
+      "num_input_tokens_seen": 740704,
+      "step": 35
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.22245633602142334,
+      "learning_rate": 4.45081197738023e-05,
+      "loss": 0.7551,
+      "num_input_tokens_seen": 841600,
+      "step": 40
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.27814680337905884,
+      "learning_rate": 4.3119819680728e-05,
+      "loss": 0.7747,
+      "num_input_tokens_seen": 947648,
+      "step": 45
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.27052441239356995,
+      "learning_rate": 4.160236506918098e-05,
+      "loss": 0.7027,
+      "num_input_tokens_seen": 1047520,
+      "step": 50
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.38937926292419434,
+      "learning_rate": 3.9966572057815373e-05,
+      "loss": 0.7581,
+      "num_input_tokens_seen": 1148080,
+      "step": 55
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.37379005551338196,
+      "learning_rate": 3.822410025817406e-05,
+      "loss": 0.7221,
+      "num_input_tokens_seen": 1252880,
+      "step": 60
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.34213003516197205,
+      "learning_rate": 3.638736966726585e-05,
+      "loss": 0.8214,
+      "num_input_tokens_seen": 1364304,
+      "step": 65
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.33407434821128845,
+      "learning_rate": 3.44694721402644e-05,
+      "loss": 0.6304,
+      "num_input_tokens_seen": 1466240,
+      "step": 70
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.33909159898757935,
+      "learning_rate": 3.2484078074333954e-05,
+      "loss": 0.6434,
+      "num_input_tokens_seen": 1558752,
+      "step": 75
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.4054814577102661,
+      "learning_rate": 3.0445338968721287e-05,
+      "loss": 0.6796,
+      "num_input_tokens_seen": 1668480,
+      "step": 80
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.2723485231399536,
+      "learning_rate": 2.836778655564653e-05,
+      "loss": 0.6651,
+      "num_input_tokens_seen": 1773264,
+      "step": 85
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.3467393219470978,
+      "learning_rate": 2.6266229220967818e-05,
+      "loss": 0.7844,
+      "num_input_tokens_seen": 1885920,
+      "step": 90
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.4250239431858063,
+      "learning_rate": 2.4155646452913296e-05,
+      "loss": 0.8139,
+      "num_input_tokens_seen": 1996656,
+      "step": 95
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.30656036734580994,
+      "learning_rate": 2.2051082071228854e-05,
+      "loss": 0.6717,
+      "num_input_tokens_seen": 2102896,
+      "step": 100
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.49129152297973633,
+      "learning_rate": 1.9967536997783494e-05,
+      "loss": 0.7524,
+      "num_input_tokens_seen": 2214272,
+      "step": 105
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.3904927670955658,
+      "learning_rate": 1.79198623329424e-05,
+      "loss": 0.631,
+      "num_input_tokens_seen": 2316448,
+      "step": 110
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.2829418182373047,
+      "learning_rate": 1.5922653499838137e-05,
+      "loss": 0.7462,
+      "num_input_tokens_seen": 2425248,
+      "step": 115
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.29749077558517456,
+      "learning_rate": 1.399014621105914e-05,
+      "loss": 0.6148,
+      "num_input_tokens_seen": 2537680,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.38928714394569397,
+      "learning_rate": 1.2136114999284288e-05,
+      "loss": 0.7145,
+      "num_input_tokens_seen": 2642080,
+      "step": 125
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.3223271369934082,
+      "learning_rate": 1.0373775035117305e-05,
+      "loss": 0.6798,
+      "num_input_tokens_seen": 2750752,
+      "step": 130
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 0.29905465245246887,
+      "learning_rate": 8.715687931944449e-06,
+      "loss": 0.6754,
+      "num_input_tokens_seen": 2852096,
+      "step": 135
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.3506278991699219,
+      "learning_rate": 7.173672209219495e-06,
+      "loss": 0.6708,
+      "num_input_tokens_seen": 2951888,
+      "step": 140
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.3896699547767639,
+      "learning_rate": 5.758719052376693e-06,
+      "loss": 0.6386,
+      "num_input_tokens_seen": 3049616,
+      "step": 145
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.5055662989616394,
+      "learning_rate": 4.480913969818098e-06,
+      "loss": 0.6995,
+      "num_input_tokens_seen": 3150784,
+      "step": 150
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 0.30896279215812683,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 0.6691,
+      "num_input_tokens_seen": 3262992,
+      "step": 155
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.30288368463516235,
+      "learning_rate": 2.372137318741968e-06,
+      "loss": 0.6024,
+      "num_input_tokens_seen": 3371440,
+      "step": 160
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.3581477999687195,
+      "learning_rate": 1.5561966963229924e-06,
+      "loss": 0.6484,
+      "num_input_tokens_seen": 3473680,
+      "step": 165
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.43826210498809814,
+      "learning_rate": 9.073589027514789e-07,
+      "loss": 0.7137,
+      "num_input_tokens_seen": 3574736,
+      "step": 170
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.22761593759059906,
+      "learning_rate": 4.302487264785521e-07,
+      "loss": 0.777,
+      "num_input_tokens_seen": 3697920,
+      "step": 175
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.3505564033985138,
+      "learning_rate": 1.2826691520262114e-07,
+      "loss": 0.6529,
+      "num_input_tokens_seen": 3803552,
+      "step": 180
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.48998603224754333,
+      "learning_rate": 3.565936007254855e-09,
+      "loss": 0.6996,
+      "num_input_tokens_seen": 3907456,
+      "step": 185
+    },
+    {
+      "epoch": 2.976,
+      "num_input_tokens_seen": 3930992,
+      "step": 186,
+      "total_flos": 3.112338516554547e+16,
+      "train_loss": 0.7158093615885703,
+      "train_runtime": 1518.3826,
+      "train_samples_per_second": 3.952,
+      "train_steps_per_second": 0.122
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 186,
+  "num_input_tokens_seen": 3930992,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.112338516554547e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25fff679805feed7cb125ffaa9aa318c0b1ee7ef433e1a91fc410bc3dfcec03b
+size 5304

training_args.yaml

@@ -0,0 +1,33 @@
+cutoff_len: 3024
+dataset: glaive_toolcall_zh,glaive_toolcall_en
+dataset_dir: data
+ddp_timeout: 180000000
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+fp16: true
+gradient_accumulation_steps: 8
+include_num_input_tokens_seen: true
+learning_rate: 5.0e-05
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: all
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 100000
+model_name_or_path: Qwen/Qwen2-1.5B-Instruct
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Qwen2-1.5B-Chat/lora/train_2024-06-17-19-49-05
+packing: false
+per_device_train_batch_size: 2
+plot_loss: true
+preprocessing_num_workers: 16
+quantization_bit: 4
+report_to: none
+save_steps: 100
+stage: sft
+template: qwen
+warmup_steps: 0