init(project): update

.gitattributes

@@ -33,3 +33,4 @@ 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
+adapter_model.bin filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,135 @@
+---
+library_name: peft
+tags:
+- generated_from_trainer
+base_model: Qwen/Qwen1.5-32B-Chat
+model-index:
+- name: out-qwen32
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: /workspace/models/Qwen1.5-32B-Chat
+trust_remote_code: true
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: /workspace/axolotl/alpaca.json
+    type: alpaca
+dataset_prepared_path:
+val_set_size: 0.05
+output_dir: ./out-qwen32
+
+
+sequence_len: 1400  # supports up to 32k
+sample_packing: false
+pad_to_sequence_len: false
+
+adapter: lora
+lora_model_dir:
+lora_r: 64
+lora_alpha: 16
+lora_dropout: 0.05
+lora_target_linear: true
+lora_fan_in_fan_out:
+
+wandb_mode: online
+wandb_project: huixiangdou-cr
+wandb_entity:
+wandb_watch:
+wandb_name: qwen32
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 4
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.0002
+
+train_on_inputs: false
+group_by_length: false
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 1
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# out-qwen32
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0370
+
+## 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: 0.0002
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.0183        | 1.0   | 273  | 0.0370          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/models/Qwen1.5-32B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41ac20cca5e79b36124b8be554f4a39b5881ad1264f9aaf0e7336c105a8970a
+size 1067774538

added_tokens.json

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

checkpoint-273/.gitattributes

@@ -0,0 +1,5 @@
+optimizer.pt filter=lfs diff=lfs merge=lfs -text
+scheduler.pt filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+rng_state_0.pth filter=lfs diff=lfs merge=lfs -text
+rng_state_1.pth filter=lfs diff=lfs merge=lfs -text

checkpoint-273/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: /workspace/models/Qwen1.5-32B-Chat
+---
+
+# 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 0.10.0

checkpoint-273/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/models/Qwen1.5-32B-Chat",
+  "bias": "none",
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-273/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a656eb89c1187ab356656bf4b3ea2ffd08794461b18436814c95133c418bd953
+size 1067572632

checkpoint-273/added_tokens.json

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

checkpoint-273/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51ef7d8f79d5ae9a6bc310a05c85d1cda063415aeed30df73d939a6f217929e1
+size 1070592852

checkpoint-273/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6a37ad2ba54e5f130ead2dcfdafb7407d7f6384fd23c04e97eb71877086a5e4
+size 14512

checkpoint-273/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f792bcd0bfb455779a45a47d34d78b580dbc8840134dda1927b249d3dd34807d
+size 14512

checkpoint-273/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3e84ed13f83816f3e41377c7e1d71844281071e6d70615ec54d17f91b34771
+size 1064

checkpoint-273/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-273/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 %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-273/trainer_state.json

@@ -0,0 +1,1940 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 273,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.609375,
+      "learning_rate": 2e-05,
+      "loss": 0.6806,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.703125,
+      "learning_rate": 4e-05,
+      "loss": 0.4976,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.671875,
+      "learning_rate": 6e-05,
+      "loss": 0.811,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.8203125,
+      "learning_rate": 8e-05,
+      "loss": 0.7326,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.0001,
+      "loss": 0.4289,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.296875,
+      "learning_rate": 0.00012,
+      "loss": 0.0229,
+      "step": 6
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.00014,
+      "loss": 0.2144,
+      "step": 7
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.40625,
+      "learning_rate": 0.00016,
+      "loss": 0.2301,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.4453125,
+      "learning_rate": 0.00018,
+      "loss": 0.2772,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.51171875,
+      "learning_rate": 0.0002,
+      "loss": 0.1217,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.90625,
+      "learning_rate": 0.00019999286567172776,
+      "loss": 0.283,
+      "step": 11
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.376953125,
+      "learning_rate": 0.00019997146370488383,
+      "loss": 0.181,
+      "step": 12
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.216796875,
+      "learning_rate": 0.00019993579715324135,
+      "loss": 0.1375,
+      "step": 13
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.326171875,
+      "learning_rate": 0.00019988587110593808,
+      "loss": 0.1605,
+      "step": 14
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.1708984375,
+      "learning_rate": 0.00019982169268675023,
+      "loss": 0.1368,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.1220703125,
+      "learning_rate": 0.00019974327105307604,
+      "loss": 0.1352,
+      "step": 16
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 0.00019965061739462902,
+      "loss": 0.1368,
+      "step": 17
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00019954374493184152,
+      "loss": 0.133,
+      "step": 18
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00019942266891397815,
+      "loss": 0.1212,
+      "step": 19
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.0001992874066169601,
+      "loss": 0.1162,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.00019913797734089997,
+      "loss": 0.1086,
+      "step": 21
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 0.00019897440240734788,
+      "loss": 0.1138,
+      "step": 22
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.158203125,
+      "learning_rate": 0.00019879670515624936,
+      "loss": 0.1119,
+      "step": 23
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 0.0001986049109426148,
+      "loss": 0.0804,
+      "step": 24
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00019839904713290184,
+      "loss": 0.1984,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.208984375,
+      "learning_rate": 0.00019817914310111046,
+      "loss": 0.0655,
+      "step": 26
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.00019794523022459166,
+      "loss": 0.1026,
+      "step": 27
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019769734187957038,
+      "loss": 0.1749,
+      "step": 28
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.33203125,
+      "learning_rate": 0.00019743551343638324,
+      "loss": 0.191,
+      "step": 29
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 0.00019715978225443148,
+      "loss": 0.1551,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.05126953125,
+      "learning_rate": 0.0001968701876768505,
+      "loss": 0.1128,
+      "step": 31
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.00019656677102489588,
+      "loss": 0.1195,
+      "step": 32
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 0.00019624957559204761,
+      "loss": 0.1093,
+      "step": 33
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 0.0001959186466378326,
+      "loss": 0.1163,
+      "step": 34
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.13671875,
+      "learning_rate": 0.00019557403138136672,
+      "loss": 0.1314,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.0615234375,
+      "learning_rate": 0.00019521577899461731,
+      "loss": 0.1091,
+      "step": 36
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.11865234375,
+      "learning_rate": 0.000194843940595387,
+      "loss": 0.1141,
+      "step": 37
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.07080078125,
+      "learning_rate": 0.0001944585692400199,
+      "loss": 0.1056,
+      "step": 38
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 0.00019405971991583108,
+      "loss": 0.1257,
+      "step": 39
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.05712890625,
+      "learning_rate": 0.00019364744953326074,
+      "loss": 0.1166,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.16796875,
+      "learning_rate": 0.00019322181691775386,
+      "loss": 0.1177,
+      "step": 41
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 0.00019278288280136647,
+      "loss": 0.1162,
+      "step": 42
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.130859375,
+      "learning_rate": 0.00019233070981410007,
+      "loss": 0.1177,
+      "step": 43
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.0732421875,
+      "learning_rate": 0.00019186536247496518,
+      "loss": 0.1173,
+      "step": 44
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 0.00019138690718277542,
+      "loss": 0.1203,
+      "step": 45
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.130859375,
+      "learning_rate": 0.0001908954122066731,
+      "loss": 0.1223,
+      "step": 46
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.12890625,
+      "learning_rate": 0.00019039094767638832,
+      "loss": 0.1167,
+      "step": 47
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.0712890625,
+      "learning_rate": 0.00018987358557223232,
+      "loss": 0.1071,
+      "step": 48
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.1083984375,
+      "learning_rate": 0.00018934339971482674,
+      "loss": 0.102,
+      "step": 49
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 0.00018880046575457074,
+      "loss": 0.1141,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.12255859375,
+      "learning_rate": 0.0001882448611608463,
+      "loss": 0.1055,
+      "step": 51
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00018767666521096466,
+      "loss": 0.1366,
+      "step": 52
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 0.00018709595897885439,
+      "loss": 0.1267,
+      "step": 53
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.16796875,
+      "learning_rate": 0.00018650282532349332,
+      "loss": 0.1128,
+      "step": 54
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00018589734887708556,
+      "loss": 0.1116,
+      "step": 55
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018527961603298572,
+      "loss": 0.097,
+      "step": 56
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 0.00018464971493337167,
+      "loss": 0.167,
+      "step": 57
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.138671875,
+      "learning_rate": 0.00018400773545666787,
+      "loss": 0.1611,
+      "step": 58
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.037353515625,
+      "learning_rate": 0.00018335376920472097,
+      "loss": 0.1157,
+      "step": 59
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 0.0001826879094897294,
+      "loss": 0.1383,
+      "step": 60
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.07373046875,
+      "learning_rate": 0.00018201025132092889,
+      "loss": 0.1336,
+      "step": 61
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018132089139103613,
+      "loss": 0.1026,
+      "step": 62
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.103515625,
+      "learning_rate": 0.00018061992806245184,
+      "loss": 0.1365,
+      "step": 63
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.043701171875,
+      "learning_rate": 0.00017990746135322592,
+      "loss": 0.1014,
+      "step": 64
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.00017918359292278611,
+      "loss": 0.1093,
+      "step": 65
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.12109375,
+      "learning_rate": 0.00017844842605743258,
+      "loss": 0.1131,
+      "step": 66
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017770206565560033,
+      "loss": 0.1105,
+      "step": 67
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 0.00017694461821289172,
+      "loss": 0.0952,
+      "step": 68
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.0703125,
+      "learning_rate": 0.00017617619180688085,
+      "loss": 0.1139,
+      "step": 69
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.044189453125,
+      "learning_rate": 0.00017539689608169238,
+      "loss": 0.0941,
+      "step": 70
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.0001746068422323568,
+      "loss": 0.1306,
+      "step": 71
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.12353515625,
+      "learning_rate": 0.00017380614298894442,
+      "loss": 0.1205,
+      "step": 72
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.11572265625,
+      "learning_rate": 0.0001729949126004802,
+      "loss": 0.0854,
+      "step": 73
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00017217326681864207,
+      "loss": 0.0948,
+      "step": 74
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.20703125,
+      "learning_rate": 0.00017134132288124465,
+      "loss": 0.1466,
+      "step": 75
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00017049919949551102,
+      "loss": 0.1167,
+      "step": 76
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.044921875,
+      "learning_rate": 0.00016964701682113475,
+      "loss": 0.1052,
+      "step": 77
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001687848964531348,
+      "loss": 0.1252,
+      "step": 78
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 0.00016791296140450545,
+      "loss": 0.1048,
+      "step": 79
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.095703125,
+      "learning_rate": 0.00016703133608866414,
+      "loss": 0.1167,
+      "step": 80
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016614014630169917,
+      "loss": 0.1167,
+      "step": 81
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.05859375,
+      "learning_rate": 0.00016523951920442034,
+      "loss": 0.1091,
+      "step": 82
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.07666015625,
+      "learning_rate": 0.00016432958330421497,
+      "loss": 0.1055,
+      "step": 83
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.09765625,
+      "learning_rate": 0.00016341046843671144,
+      "loss": 0.1157,
+      "step": 84
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.045654296875,
+      "learning_rate": 0.0001624823057472534,
+      "loss": 0.109,
+      "step": 85
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016154522767218725,
+      "loss": 0.0934,
+      "step": 86
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 0.000160599367919965,
+      "loss": 0.113,
+      "step": 87
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 0.0001596448614520661,
+      "loss": 0.1089,
+      "step": 88
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.05419921875,
+      "learning_rate": 0.0001586818444637402,
+      "loss": 0.1066,
+      "step": 89
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.0001577104543645738,
+      "loss": 0.1249,
+      "step": 90
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00015673082975888386,
+      "loss": 0.0955,
+      "step": 91
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.0634765625,
+      "learning_rate": 0.0001557431104259408,
+      "loss": 0.0873,
+      "step": 92
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001547474373000238,
+      "loss": 0.1362,
+      "step": 93
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.053466796875,
+      "learning_rate": 0.0001537439524503116,
+      "loss": 0.1005,
+      "step": 94
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 0.00015273279906061082,
+      "loss": 0.1119,
+      "step": 95
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.068359375,
+      "learning_rate": 0.00015171412140892575,
+      "loss": 0.099,
+      "step": 96
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 0.0001506880648468719,
+      "loss": 0.0794,
+      "step": 97
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 0.00014965477577893598,
+      "loss": 0.0942,
+      "step": 98
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.05224609375,
+      "learning_rate": 0.0001486144016415862,
+      "loss": 0.0958,
+      "step": 99
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.140625,
+      "learning_rate": 0.0001475670908822351,
+      "loss": 0.099,
+      "step": 100
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.07470703125,
+      "learning_rate": 0.00014651299293805774,
+      "loss": 0.0978,
+      "step": 101
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.205078125,
+      "learning_rate": 0.0001454522582146695,
+      "loss": 0.1197,
+      "step": 102
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.0001443850380646649,
+      "loss": 0.1078,
+      "step": 103
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001433114847660217,
+      "loss": 0.0835,
+      "step": 104
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00014223175150037296,
+      "loss": 0.0961,
+      "step": 105
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00014114599233114986,
+      "loss": 0.1005,
+      "step": 106
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.109375,
+      "learning_rate": 0.00014005436218159927,
+      "loss": 0.1072,
+      "step": 107
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 0.00013895701681267784,
+      "loss": 0.0974,
+      "step": 108
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.15234375,
+      "learning_rate": 0.00013785411280082746,
+      "loss": 0.1143,
+      "step": 109
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 0.00013674580751563356,
+      "loss": 0.1296,
+      "step": 110
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.1689453125,
+      "learning_rate": 0.00013563225909737076,
+      "loss": 0.1022,
+      "step": 111
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 0.00013451362643443832,
+      "loss": 0.0633,
+      "step": 112
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.0001333900691406889,
+      "loss": 0.1276,
+      "step": 113
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1591796875,
+      "learning_rate": 0.0001322617475326538,
+      "loss": 0.117,
+      "step": 114
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00013112882260666805,
+      "loss": 0.0645,
+      "step": 115
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 0.00012999145601589823,
+      "loss": 0.0632,
+      "step": 116
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.1181640625,
+      "learning_rate": 0.00012884981004727676,
+      "loss": 0.0832,
+      "step": 117
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.12109375,
+      "learning_rate": 0.00012770404759834594,
+      "loss": 0.0769,
+      "step": 118
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 0.00012655433215401438,
+      "loss": 0.0413,
+      "step": 119
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00012540082776323007,
+      "loss": 0.0832,
+      "step": 120
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 0.0001242436990155728,
+      "loss": 0.0197,
+      "step": 121
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.2392578125,
+      "learning_rate": 0.00012308311101776932,
+      "loss": 0.0549,
+      "step": 122
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.38671875,
+      "learning_rate": 0.00012191922937013489,
+      "loss": 0.0665,
+      "step": 123
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.32421875,
+      "learning_rate": 0.00012075222014294447,
+      "loss": 0.1273,
+      "step": 124
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 0.00011958224985273648,
+      "loss": 0.0877,
+      "step": 125
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00011840948543855335,
+      "loss": 0.1127,
+      "step": 126
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.00011723409423812134,
+      "loss": 0.0416,
+      "step": 127
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.00011605624396397398,
+      "loss": 0.0571,
+      "step": 128
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 0.00011487610267952142,
+      "loss": 0.1001,
+      "step": 129
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 0.00011369383877507034,
+      "loss": 0.0259,
+      "step": 130
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.1953125,
+      "learning_rate": 0.0001125096209437967,
+      "loss": 0.0805,
+      "step": 131
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.00011132361815767554,
+      "loss": 0.0239,
+      "step": 132
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.00011013599964337107,
+      "loss": 0.0768,
+      "step": 133
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00010894693485809016,
+      "loss": 0.0132,
+      "step": 134
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 0.00010775659346540303,
+      "loss": 0.0746,
+      "step": 135
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 0.00010656514531103483,
+      "loss": 0.0221,
+      "step": 136
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1220703125,
+      "learning_rate": 0.00010537276039863049,
+      "loss": 0.0503,
+      "step": 137
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.10546875,
+      "learning_rate": 0.00010417960886549798,
+      "loss": 0.0546,
+      "step": 138
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.039306640625,
+      "learning_rate": 0.00010298586095833151,
+      "loss": 0.0095,
+      "step": 139
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 0.251953125,
+      "learning_rate": 0.00010179168700892001,
+      "loss": 0.1242,
+      "step": 140
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00010059725740984284,
+      "loss": 0.1958,
+      "step": 141
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 9.940274259015721e-05,
+      "loss": 0.0345,
+      "step": 142
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.12109375,
+      "learning_rate": 9.820831299108003e-05,
+      "loss": 0.0371,
+      "step": 143
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.26171875,
+      "learning_rate": 9.701413904166852e-05,
+      "loss": 0.0501,
+      "step": 144
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.318359375,
+      "learning_rate": 9.582039113450208e-05,
+      "loss": 0.0902,
+      "step": 145
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 9.462723960136952e-05,
+      "loss": 0.0528,
+      "step": 146
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.15625,
+      "learning_rate": 9.34348546889652e-05,
+      "loss": 0.0657,
+      "step": 147
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 9.224340653459698e-05,
+      "loss": 0.0547,
+      "step": 148
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.26171875,
+      "learning_rate": 9.10530651419099e-05,
+      "loss": 0.1411,
+      "step": 149
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.375,
+      "learning_rate": 8.986400035662896e-05,
+      "loss": 0.1156,
+      "step": 150
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.322265625,
+      "learning_rate": 8.867638184232446e-05,
+      "loss": 0.1539,
+      "step": 151
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.17578125,
+      "learning_rate": 8.749037905620334e-05,
+      "loss": 0.1194,
+      "step": 152
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.15234375,
+      "learning_rate": 8.630616122492967e-05,
+      "loss": 0.0595,
+      "step": 153
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 8.512389732047859e-05,
+      "loss": 0.0666,
+      "step": 154
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.115234375,
+      "learning_rate": 8.394375603602603e-05,
+      "loss": 0.0883,
+      "step": 155
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.103515625,
+      "learning_rate": 8.276590576187869e-05,
+      "loss": 0.0889,
+      "step": 156
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 8.159051456144668e-05,
+      "loss": 0.0751,
+      "step": 157
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 8.041775014726353e-05,
+      "loss": 0.0864,
+      "step": 158
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 7.924777985705556e-05,
+      "loss": 0.0768,
+      "step": 159
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 7.808077062986514e-05,
+      "loss": 0.0617,
+      "step": 160
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 7.69168889822307e-05,
+      "loss": 0.0586,
+      "step": 161
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.15625,
+      "learning_rate": 7.575630098442723e-05,
+      "loss": 0.1025,
+      "step": 162
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 7.459917223676993e-05,
+      "loss": 0.0485,
+      "step": 163
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.19140625,
+      "learning_rate": 7.344566784598564e-05,
+      "loss": 0.1085,
+      "step": 164
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 7.229595240165405e-05,
+      "loss": 0.0757,
+      "step": 165
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 7.115018995272325e-05,
+      "loss": 0.0769,
+      "step": 166
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 7.000854398410182e-05,
+      "loss": 0.1229,
+      "step": 167
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 6.887117739333196e-05,
+      "loss": 0.0633,
+      "step": 168
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 6.773825246734622e-05,
+      "loss": 0.0513,
+      "step": 169
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 6.660993085931113e-05,
+      "loss": 0.0394,
+      "step": 170
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.125,
+      "learning_rate": 6.54863735655617e-05,
+      "loss": 0.0949,
+      "step": 171
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 6.436774090262925e-05,
+      "loss": 0.0946,
+      "step": 172
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.07861328125,
+      "learning_rate": 6.325419248436649e-05,
+      "loss": 0.0683,
+      "step": 173
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 6.214588719917256e-05,
+      "loss": 0.0412,
+      "step": 174
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 6.104298318732218e-05,
+      "loss": 0.1105,
+      "step": 175
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 5.994563781840079e-05,
+      "loss": 0.0435,
+      "step": 176
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.0595703125,
+      "learning_rate": 5.885400766885015e-05,
+      "loss": 0.0325,
+      "step": 177
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.12890625,
+      "learning_rate": 5.776824849962705e-05,
+      "loss": 0.069,
+      "step": 178
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.050537109375,
+      "learning_rate": 5.668851523397829e-05,
+      "loss": 0.0448,
+      "step": 179
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 5.561496193533515e-05,
+      "loss": 0.0747,
+      "step": 180
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.140625,
+      "learning_rate": 5.4547741785330505e-05,
+      "loss": 0.0832,
+      "step": 181
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.11865234375,
+      "learning_rate": 5.3487007061942276e-05,
+      "loss": 0.0725,
+      "step": 182
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 5.243290911776497e-05,
+      "loss": 0.0729,
+      "step": 183
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.126953125,
+      "learning_rate": 5.138559835841381e-05,
+      "loss": 0.0649,
+      "step": 184
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 5.0345224221064025e-05,
+      "loss": 0.0435,
+      "step": 185
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 4.931193515312813e-05,
+      "loss": 0.0313,
+      "step": 186
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 4.828587859107425e-05,
+      "loss": 0.0618,
+      "step": 187
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 4.726720093938921e-05,
+      "loss": 0.0298,
+      "step": 188
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 4.625604754968839e-05,
+      "loss": 0.0169,
+      "step": 189
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.23046875,
+      "learning_rate": 4.525256269997621e-05,
+      "loss": 0.1029,
+      "step": 190
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 4.4256889574059236e-05,
+      "loss": 0.0387,
+      "step": 191
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 4.3269170241116155e-05,
+      "loss": 0.0474,
+      "step": 192
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 4.2289545635426206e-05,
+      "loss": 0.0285,
+      "step": 193
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 4.1318155536259795e-05,
+      "loss": 0.0821,
+      "step": 194
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.216796875,
+      "learning_rate": 4.035513854793389e-05,
+      "loss": 0.0698,
+      "step": 195
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.146484375,
+      "learning_rate": 3.940063208003503e-05,
+      "loss": 0.0526,
+      "step": 196
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 3.845477232781278e-05,
+      "loss": 0.0513,
+      "step": 197
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.126953125,
+      "learning_rate": 3.751769425274661e-05,
+      "loss": 0.0394,
+      "step": 198
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.10546875,
+      "learning_rate": 3.658953156328857e-05,
+      "loss": 0.032,
+      "step": 199
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.171875,
+      "learning_rate": 3.567041669578507e-05,
+      "loss": 0.0509,
+      "step": 200
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.083984375,
+      "learning_rate": 3.476048079557967e-05,
+      "loss": 0.0255,
+      "step": 201
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.326171875,
+      "learning_rate": 3.3859853698300855e-05,
+      "loss": 0.1141,
+      "step": 202
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.1728515625,
+      "learning_rate": 3.2968663911335894e-05,
+      "loss": 0.0673,
+      "step": 203
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.0625,
+      "learning_rate": 3.208703859549457e-05,
+      "loss": 0.0184,
+      "step": 204
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.119140625,
+      "learning_rate": 3.12151035468652e-05,
+      "loss": 0.0542,
+      "step": 205
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 3.0352983178865256e-05,
+      "loss": 0.0334,
+      "step": 206
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.265625,
+      "learning_rate": 2.9500800504489022e-05,
+      "loss": 0.0897,
+      "step": 207
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.197265625,
+      "learning_rate": 2.8658677118755382e-05,
+      "loss": 0.1091,
+      "step": 208
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.1875,
+      "learning_rate": 2.7826733181357932e-05,
+      "loss": 0.1194,
+      "step": 209
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.21875,
+      "learning_rate": 2.7005087399519835e-05,
+      "loss": 0.0697,
+      "step": 210
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 2.6193857011055622e-05,
+      "loss": 0.1141,
+      "step": 211
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 2.5393157767643228e-05,
+      "loss": 0.07,
+      "step": 212
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 2.4603103918307625e-05,
+      "loss": 0.0618,
+      "step": 213
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.0498046875,
+      "learning_rate": 2.3823808193119178e-05,
+      "loss": 0.0224,
+      "step": 214
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 2.305538178710831e-05,
+      "loss": 0.075,
+      "step": 215
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.11669921875,
+      "learning_rate": 2.2297934344399695e-05,
+      "loss": 0.0293,
+      "step": 216
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.064453125,
+      "learning_rate": 2.155157394256745e-05,
+      "loss": 0.0287,
+      "step": 217
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 2.0816407077213896e-05,
+      "loss": 0.1017,
+      "step": 218
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 2.0092538646774072e-05,
+      "loss": 0.0204,
+      "step": 219
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 1.938007193754816e-05,
+      "loss": 0.0253,
+      "step": 220
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 1.8679108608963903e-05,
+      "loss": 0.047,
+      "step": 221
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.10986328125,
+      "learning_rate": 1.7989748679071138e-05,
+      "loss": 0.0752,
+      "step": 222
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.11279296875,
+      "learning_rate": 1.7312090510270627e-05,
+      "loss": 0.0387,
+      "step": 223
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 1.6646230795279026e-05,
+      "loss": 0.0577,
+      "step": 224
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.115234375,
+      "learning_rate": 1.5992264543332124e-05,
+      "loss": 0.0637,
+      "step": 225
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 1.5350285066628343e-05,
+      "loss": 0.0656,
+      "step": 226
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.123046875,
+      "learning_rate": 1.4720383967014306e-05,
+      "loss": 0.0257,
+      "step": 227
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.12109375,
+      "learning_rate": 1.4102651122914434e-05,
+      "loss": 0.099,
+      "step": 228
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.3497174676506674e-05,
+      "loss": 0.0496,
+      "step": 229
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.14453125,
+      "learning_rate": 1.2904041021145596e-05,
+      "loss": 0.0549,
+      "step": 230
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 1.2323334789035367e-05,
+      "loss": 0.07,
+      "step": 231
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 1.17551388391537e-05,
+      "loss": 0.0498,
+      "step": 232
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.12109375,
+      "learning_rate": 1.1199534245429255e-05,
+      "loss": 0.0514,
+      "step": 233
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 1.0656600285173258e-05,
+      "loss": 0.0231,
+      "step": 234
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.04443359375,
+      "learning_rate": 1.0126414427767717e-05,
+      "loss": 0.0215,
+      "step": 235
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 9.609052323611666e-06,
+      "loss": 0.0237,
+      "step": 236
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 9.104587793326901e-06,
+      "loss": 0.0196,
+      "step": 237
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 8.613092817224611e-06,
+      "loss": 0.0842,
+      "step": 238
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.1513671875,
+      "learning_rate": 8.134637525034839e-06,
+      "loss": 0.0692,
+      "step": 239
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 7.669290185899946e-06,
+      "loss": 0.0384,
+      "step": 240
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 7.217117198633561e-06,
+      "loss": 0.0359,
+      "step": 241
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 6.778183082246148e-06,
+      "loss": 0.0195,
+      "step": 242
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.11962890625,
+      "learning_rate": 6.3525504667392595e-06,
+      "loss": 0.0531,
+      "step": 243
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 5.940280084168947e-06,
+      "loss": 0.0815,
+      "step": 244
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.06884765625,
+      "learning_rate": 5.541430759980138e-06,
+      "loss": 0.0291,
+      "step": 245
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.11474609375,
+      "learning_rate": 5.1560594046130115e-06,
+      "loss": 0.0621,
+      "step": 246
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.1328125,
+      "learning_rate": 4.784221005382705e-06,
+      "loss": 0.0761,
+      "step": 247
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 4.425968618633292e-06,
+      "loss": 0.0197,
+      "step": 248
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 4.081353362167406e-06,
+      "loss": 0.0318,
+      "step": 249
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 3.750424407952402e-06,
+      "loss": 0.0758,
+      "step": 250
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.045166015625,
+      "learning_rate": 3.4332289751041526e-06,
+      "loss": 0.0201,
+      "step": 251
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.212890625,
+      "learning_rate": 3.129812323149528e-06,
+      "loss": 0.0379,
+      "step": 252
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 2.8402177455685296e-06,
+      "loss": 0.0331,
+      "step": 253
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 2.564486563616786e-06,
+      "loss": 0.0441,
+      "step": 254
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.078125,
+      "learning_rate": 2.3026581204296347e-06,
+      "loss": 0.025,
+      "step": 255
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 2.0547697754083605e-06,
+      "loss": 0.0885,
+      "step": 256
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 1.8208568988895558e-06,
+      "loss": 0.0393,
+      "step": 257
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.0546875,
+      "learning_rate": 1.6009528670981711e-06,
+      "loss": 0.0358,
+      "step": 258
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 1.3950890573852126e-06,
+      "loss": 0.0784,
+      "step": 259
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 1.2032948437506576e-06,
+      "loss": 0.0441,
+      "step": 260
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.1220703125,
+      "learning_rate": 1.0255975926521166e-06,
+      "loss": 0.0274,
+      "step": 261
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.080078125,
+      "learning_rate": 8.620226591000479e-07,
+      "loss": 0.0153,
+      "step": 262
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.130859375,
+      "learning_rate": 7.125933830398945e-07,
+      "loss": 0.0462,
+      "step": 263
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.05810546875,
+      "learning_rate": 5.773310860218373e-07,
+      "loss": 0.0356,
+      "step": 264
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.171875,
+      "learning_rate": 4.562550681584954e-07,
+      "loss": 0.0545,
+      "step": 265
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 3.4938260537098476e-07,
+      "loss": 0.0547,
+      "step": 266
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 2.567289469239786e-07,
+      "loss": 0.0342,
+      "step": 267
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 1.7830731324977036e-07,
+      "loss": 0.0276,
+      "step": 268
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 1.1412889406192673e-07,
+      "loss": 0.0597,
+      "step": 269
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.050048828125,
+      "learning_rate": 6.420284675865418e-08,
+      "loss": 0.0197,
+      "step": 270
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 2.853629511617717e-08,
+      "loss": 0.0884,
+      "step": 271
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.16015625,
+      "learning_rate": 7.134328272240254e-09,
+      "loss": 0.1165,
+      "step": 272
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.04638671875,
+      "learning_rate": 0.0,
+      "loss": 0.0183,
+      "step": 273
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.03699357807636261,
+      "eval_runtime": 12.8888,
+      "eval_samples_per_second": 8.922,
+      "eval_steps_per_second": 1.164,
+      "step": 273
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 273,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.1059186691407872e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-273/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362b3d8b292f1f980958acbffd8d406599c84afb31dd2798e6cb61f5d8ebc346
+size 5816

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/workspace/models/Qwen1.5-32B-Chat",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 27392,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 35,
+  "model_type": "qwen2",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 64,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

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 +1,43 @@
+{
+  "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 %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|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": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}