Upload 17 files

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,202 @@
+---
+base_model: QWen/QWen2-VL-7B-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 0.12.0

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "QWen/QWen2-VL-7B-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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "^(?!.*visual).*(?:o_proj|down_proj|v_proj|k_proj|gate_proj|up_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 sha256:33d77cd37b44a09f2b3263c97ff1f01c8ae2d9b08d4998152ca701ea3d345e6e
+size 1291899160

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

classifier.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7766ec5208d4e65d100342ac0cbc38614005d281046d9f6ce9966e9ce92bdc66
+size 18889510

classifier_config.json

@@ -0,0 +1,12 @@
+{
+    "hidden_size": 3584,
+    "num_layers": 3,
+    "proj_dim": 1024,
+    "output_dim": 1,
+    "input_dropout": 0.0,
+    "dropout": [
+        0.2,
+        0.4,
+        0.1
+    ]
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91f857e57a0ebd5da444431251ab6133b34babe68d53dd5e68a76c6ba837d329
+size 2621800444

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "max_pixels": 12845056,
+    "min_pixels": 3136
+  },
+  "temporal_patch_size": 2
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:406931002ba53eb73a8ab57c9243a149b920df9dc0d62d5fc02056d2fc838a3a
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5838f58c6955f757e7dc7074adf41a021b58ead67bf7a9c406a0c7b47724e9f9
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:091aa7594dc2fcfbfa06b9e3c22a5f0562ac14f30375c13af7309407a0e67b8a
+size 11420371

tokenizer_config.json

@@ -0,0 +1,143 @@
+{
+  "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
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% 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|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1893 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0582010582010581,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "classification_loss": 0.6695,
+      "epoch": 0.005291005291005291,
+      "grad_norm": 16.771141052246094,
+      "learning_rate": 7.017543859649123e-07,
+      "lm_loss": 2.0851,
+      "loss": 2.7547,
+      "step": 1
+    },
+    {
+      "classification_loss": 0.7145,
+      "epoch": 0.010582010582010581,
+      "grad_norm": 27.93190574645996,
+      "learning_rate": 1.4035087719298246e-06,
+      "lm_loss": 1.9011,
+      "loss": 2.6157,
+      "step": 2
+    },
+    {
+      "classification_loss": 0.74,
+      "epoch": 0.015873015873015872,
+      "grad_norm": 19.260587692260742,
+      "learning_rate": 2.105263157894737e-06,
+      "lm_loss": 2.152,
+      "loss": 2.892,
+      "step": 3
+    },
+    {
+      "classification_loss": 0.668,
+      "epoch": 0.021164021164021163,
+      "grad_norm": 16.394054412841797,
+      "learning_rate": 2.8070175438596493e-06,
+      "lm_loss": 2.0417,
+      "loss": 2.7098,
+      "step": 4
+    },
+    {
+      "classification_loss": 0.6821,
+      "epoch": 0.026455026455026454,
+      "grad_norm": 18.829200744628906,
+      "learning_rate": 3.5087719298245615e-06,
+      "lm_loss": 2.0113,
+      "loss": 2.6933,
+      "step": 5
+    },
+    {
+      "classification_loss": 0.6701,
+      "epoch": 0.031746031746031744,
+      "grad_norm": 18.288366317749023,
+      "learning_rate": 4.210526315789474e-06,
+      "lm_loss": 1.8286,
+      "loss": 2.4987,
+      "step": 6
+    },
+    {
+      "classification_loss": 0.6698,
+      "epoch": 0.037037037037037035,
+      "grad_norm": 25.650251388549805,
+      "learning_rate": 4.912280701754386e-06,
+      "lm_loss": 1.7178,
+      "loss": 2.3876,
+      "step": 7
+    },
+    {
+      "classification_loss": 0.8098,
+      "epoch": 0.042328042328042326,
+      "grad_norm": 15.184894561767578,
+      "learning_rate": 5.6140350877192985e-06,
+      "lm_loss": 1.6045,
+      "loss": 2.4142,
+      "step": 8
+    },
+    {
+      "classification_loss": 0.6963,
+      "epoch": 0.047619047619047616,
+      "grad_norm": 12.884407997131348,
+      "learning_rate": 6.31578947368421e-06,
+      "lm_loss": 1.372,
+      "loss": 2.0683,
+      "step": 9
+    },
+    {
+      "classification_loss": 0.7149,
+      "epoch": 0.05291005291005291,
+      "grad_norm": 12.367244720458984,
+      "learning_rate": 7.017543859649123e-06,
+      "lm_loss": 1.0866,
+      "loss": 1.8015,
+      "step": 10
+    },
+    {
+      "classification_loss": 0.7124,
+      "epoch": 0.0582010582010582,
+      "grad_norm": 19.37381362915039,
+      "learning_rate": 7.719298245614036e-06,
+      "lm_loss": 0.7991,
+      "loss": 1.5115,
+      "step": 11
+    },
+    {
+      "classification_loss": 0.6034,
+      "epoch": 0.06349206349206349,
+      "grad_norm": 17.332901000976562,
+      "learning_rate": 8.421052631578948e-06,
+      "lm_loss": 0.6295,
+      "loss": 1.2329,
+      "step": 12
+    },
+    {
+      "classification_loss": 0.5687,
+      "epoch": 0.06878306878306878,
+      "grad_norm": 12.365259170532227,
+      "learning_rate": 9.12280701754386e-06,
+      "lm_loss": 0.6126,
+      "loss": 1.1812,
+      "step": 13
+    },
+    {
+      "classification_loss": 0.7166,
+      "epoch": 0.07407407407407407,
+      "grad_norm": 12.777908325195312,
+      "learning_rate": 9.824561403508772e-06,
+      "lm_loss": 0.5857,
+      "loss": 1.3022,
+      "step": 14
+    },
+    {
+      "classification_loss": 0.7863,
+      "epoch": 0.07936507936507936,
+      "grad_norm": 12.364931106567383,
+      "learning_rate": 1.0526315789473684e-05,
+      "lm_loss": 0.4866,
+      "loss": 1.2729,
+      "step": 15
+    },
+    {
+      "classification_loss": 0.6334,
+      "epoch": 0.08465608465608465,
+      "grad_norm": 10.23062515258789,
+      "learning_rate": 1.1228070175438597e-05,
+      "lm_loss": 0.3727,
+      "loss": 1.006,
+      "step": 16
+    },
+    {
+      "classification_loss": 0.5849,
+      "epoch": 0.08994708994708994,
+      "grad_norm": 11.9069185256958,
+      "learning_rate": 1.192982456140351e-05,
+      "lm_loss": 0.2464,
+      "loss": 0.8313,
+      "step": 17
+    },
+    {
+      "classification_loss": 0.6384,
+      "epoch": 0.09523809523809523,
+      "grad_norm": 12.602136611938477,
+      "learning_rate": 1.263157894736842e-05,
+      "lm_loss": 0.2392,
+      "loss": 0.8776,
+      "step": 18
+    },
+    {
+      "classification_loss": 0.67,
+      "epoch": 0.10052910052910052,
+      "grad_norm": 15.037280082702637,
+      "learning_rate": 1.3333333333333333e-05,
+      "lm_loss": 0.1902,
+      "loss": 0.8602,
+      "step": 19
+    },
+    {
+      "classification_loss": 0.6626,
+      "epoch": 0.10582010582010581,
+      "grad_norm": 9.703207015991211,
+      "learning_rate": 1.4035087719298246e-05,
+      "lm_loss": 0.1744,
+      "loss": 0.837,
+      "step": 20
+    },
+    {
+      "classification_loss": 0.6218,
+      "epoch": 0.1111111111111111,
+      "grad_norm": 9.03652572631836,
+      "learning_rate": 1.4736842105263159e-05,
+      "lm_loss": 0.1287,
+      "loss": 0.7505,
+      "step": 21
+    },
+    {
+      "classification_loss": 0.47,
+      "epoch": 0.1164021164021164,
+      "grad_norm": 8.84855842590332,
+      "learning_rate": 1.543859649122807e-05,
+      "lm_loss": 0.0953,
+      "loss": 0.5653,
+      "step": 22
+    },
+    {
+      "classification_loss": 0.6106,
+      "epoch": 0.12169312169312169,
+      "grad_norm": 9.092327117919922,
+      "learning_rate": 1.6140350877192984e-05,
+      "lm_loss": 0.0903,
+      "loss": 0.7009,
+      "step": 23
+    },
+    {
+      "classification_loss": 0.3901,
+      "epoch": 0.12698412698412698,
+      "grad_norm": 10.399832725524902,
+      "learning_rate": 1.6842105263157896e-05,
+      "lm_loss": 0.0447,
+      "loss": 0.4348,
+      "step": 24
+    },
+    {
+      "classification_loss": 0.8788,
+      "epoch": 0.13227513227513227,
+      "grad_norm": 16.038183212280273,
+      "learning_rate": 1.754385964912281e-05,
+      "lm_loss": 0.083,
+      "loss": 0.9618,
+      "step": 25
+    },
+    {
+      "classification_loss": 0.8995,
+      "epoch": 0.13756613756613756,
+      "grad_norm": 17.929433822631836,
+      "learning_rate": 1.824561403508772e-05,
+      "lm_loss": 0.1014,
+      "loss": 1.0009,
+      "step": 26
+    },
+    {
+      "classification_loss": 0.7673,
+      "epoch": 0.14285714285714285,
+      "grad_norm": 11.831334114074707,
+      "learning_rate": 1.894736842105263e-05,
+      "lm_loss": 0.0959,
+      "loss": 0.8631,
+      "step": 27
+    },
+    {
+      "classification_loss": 0.567,
+      "epoch": 0.14814814814814814,
+      "grad_norm": 7.2031073570251465,
+      "learning_rate": 1.9649122807017544e-05,
+      "lm_loss": 0.0559,
+      "loss": 0.6229,
+      "step": 28
+    },
+    {
+      "classification_loss": 0.8024,
+      "epoch": 0.15343915343915343,
+      "grad_norm": 12.598705291748047,
+      "learning_rate": 2.035087719298246e-05,
+      "lm_loss": 0.1079,
+      "loss": 0.9102,
+      "step": 29
+    },
+    {
+      "classification_loss": 0.5282,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 7.753366470336914,
+      "learning_rate": 2.105263157894737e-05,
+      "lm_loss": 0.0315,
+      "loss": 0.5598,
+      "step": 30
+    },
+    {
+      "classification_loss": 0.6261,
+      "epoch": 0.164021164021164,
+      "grad_norm": 8.418317794799805,
+      "learning_rate": 2.1754385964912285e-05,
+      "lm_loss": 0.0626,
+      "loss": 0.6887,
+      "step": 31
+    },
+    {
+      "classification_loss": 0.6078,
+      "epoch": 0.1693121693121693,
+      "grad_norm": 10.975348472595215,
+      "learning_rate": 2.2456140350877194e-05,
+      "lm_loss": 0.0661,
+      "loss": 0.6739,
+      "step": 32
+    },
+    {
+      "classification_loss": 0.6152,
+      "epoch": 0.1746031746031746,
+      "grad_norm": 7.836843490600586,
+      "learning_rate": 2.3157894736842107e-05,
+      "lm_loss": 0.0555,
+      "loss": 0.6708,
+      "step": 33
+    },
+    {
+      "classification_loss": 0.6342,
+      "epoch": 0.17989417989417988,
+      "grad_norm": 9.3395414352417,
+      "learning_rate": 2.385964912280702e-05,
+      "lm_loss": 0.0772,
+      "loss": 0.7114,
+      "step": 34
+    },
+    {
+      "classification_loss": 0.5311,
+      "epoch": 0.18518518518518517,
+      "grad_norm": 8.910663604736328,
+      "learning_rate": 2.4561403508771932e-05,
+      "lm_loss": 0.0496,
+      "loss": 0.5807,
+      "step": 35
+    },
+    {
+      "classification_loss": 0.4504,
+      "epoch": 0.19047619047619047,
+      "grad_norm": 8.439433097839355,
+      "learning_rate": 2.526315789473684e-05,
+      "lm_loss": 0.0434,
+      "loss": 0.4937,
+      "step": 36
+    },
+    {
+      "classification_loss": 0.4308,
+      "epoch": 0.19576719576719576,
+      "grad_norm": 9.815783500671387,
+      "learning_rate": 2.5964912280701757e-05,
+      "lm_loss": 0.0391,
+      "loss": 0.4699,
+      "step": 37
+    },
+    {
+      "classification_loss": 0.5369,
+      "epoch": 0.20105820105820105,
+      "grad_norm": 8.448427200317383,
+      "learning_rate": 2.6666666666666667e-05,
+      "lm_loss": 0.0661,
+      "loss": 0.603,
+      "step": 38
+    },
+    {
+      "classification_loss": 0.551,
+      "epoch": 0.20634920634920634,
+      "grad_norm": 9.024697303771973,
+      "learning_rate": 2.7368421052631583e-05,
+      "lm_loss": 0.0627,
+      "loss": 0.6137,
+      "step": 39
+    },
+    {
+      "classification_loss": 0.5113,
+      "epoch": 0.21164021164021163,
+      "grad_norm": 10.45963191986084,
+      "learning_rate": 2.8070175438596492e-05,
+      "lm_loss": 0.0432,
+      "loss": 0.5544,
+      "step": 40
+    },
+    {
+      "classification_loss": 0.5548,
+      "epoch": 0.21693121693121692,
+      "grad_norm": 9.504748344421387,
+      "learning_rate": 2.8771929824561408e-05,
+      "lm_loss": 0.0704,
+      "loss": 0.6252,
+      "step": 41
+    },
+    {
+      "classification_loss": 0.1668,
+      "epoch": 0.2222222222222222,
+      "grad_norm": 6.110610485076904,
+      "learning_rate": 2.9473684210526317e-05,
+      "lm_loss": 0.0104,
+      "loss": 0.1772,
+      "step": 42
+    },
+    {
+      "classification_loss": 0.2372,
+      "epoch": 0.2275132275132275,
+      "grad_norm": 9.717988967895508,
+      "learning_rate": 3.017543859649123e-05,
+      "lm_loss": 0.0401,
+      "loss": 0.2773,
+      "step": 43
+    },
+    {
+      "classification_loss": 0.4028,
+      "epoch": 0.2328042328042328,
+      "grad_norm": 9.197904586791992,
+      "learning_rate": 3.087719298245614e-05,
+      "lm_loss": 0.0687,
+      "loss": 0.4716,
+      "step": 44
+    },
+    {
+      "classification_loss": 0.8087,
+      "epoch": 0.23809523809523808,
+      "grad_norm": 16.595661163330078,
+      "learning_rate": 3.157894736842106e-05,
+      "lm_loss": 0.082,
+      "loss": 0.8907,
+      "step": 45
+    },
+    {
+      "classification_loss": 0.683,
+      "epoch": 0.24338624338624337,
+      "grad_norm": 14.11158561706543,
+      "learning_rate": 3.228070175438597e-05,
+      "lm_loss": 0.0702,
+      "loss": 0.7532,
+      "step": 46
+    },
+    {
+      "classification_loss": 1.045,
+      "epoch": 0.24867724867724866,
+      "grad_norm": 19.863332748413086,
+      "learning_rate": 3.298245614035088e-05,
+      "lm_loss": 0.1122,
+      "loss": 1.1571,
+      "step": 47
+    },
+    {
+      "classification_loss": 0.5931,
+      "epoch": 0.25396825396825395,
+      "grad_norm": 11.521686553955078,
+      "learning_rate": 3.368421052631579e-05,
+      "lm_loss": 0.1241,
+      "loss": 0.7173,
+      "step": 48
+    },
+    {
+      "classification_loss": 0.5617,
+      "epoch": 0.25925925925925924,
+      "grad_norm": 12.246728897094727,
+      "learning_rate": 3.43859649122807e-05,
+      "lm_loss": 0.0858,
+      "loss": 0.6475,
+      "step": 49
+    },
+    {
+      "classification_loss": 0.5201,
+      "epoch": 0.26455026455026454,
+      "grad_norm": 8.966938018798828,
+      "learning_rate": 3.508771929824562e-05,
+      "lm_loss": 0.0585,
+      "loss": 0.5785,
+      "step": 50
+    },
+    {
+      "epoch": 0.26455026455026454,
+      "eval_accuracy": 0.8983050584793091,
+      "eval_auroc": 0.9314866065979004,
+      "eval_classification_loss": 0.32121941447257996,
+      "eval_f1": 0.8604651093482971,
+      "eval_lm_loss": 0.04069896787405014,
+      "eval_loss": 0.3619183897972107,
+      "eval_precision": 0.8283582329750061,
+      "eval_recall": 0.8951612710952759,
+      "eval_runtime": 15.993,
+      "eval_samples_per_second": 22.135,
+      "eval_steps_per_second": 1.438,
+      "step": 50
+    },
+    {
+      "classification_loss": 0.4476,
+      "epoch": 0.2698412698412698,
+      "grad_norm": 10.744962692260742,
+      "learning_rate": 3.578947368421053e-05,
+      "lm_loss": 0.0362,
+      "loss": 0.4839,
+      "step": 51
+    },
+    {
+      "classification_loss": 0.5896,
+      "epoch": 0.2751322751322751,
+      "grad_norm": 15.367817878723145,
+      "learning_rate": 3.649122807017544e-05,
+      "lm_loss": 0.0429,
+      "loss": 0.6325,
+      "step": 52
+    },
+    {
+      "classification_loss": 0.6608,
+      "epoch": 0.2804232804232804,
+      "grad_norm": 16.497859954833984,
+      "learning_rate": 3.719298245614035e-05,
+      "lm_loss": 0.1118,
+      "loss": 0.7726,
+      "step": 53
+    },
+    {
+      "classification_loss": 0.5343,
+      "epoch": 0.2857142857142857,
+      "grad_norm": 10.103208541870117,
+      "learning_rate": 3.789473684210526e-05,
+      "lm_loss": 0.0552,
+      "loss": 0.5895,
+      "step": 54
+    },
+    {
+      "classification_loss": 0.7036,
+      "epoch": 0.291005291005291,
+      "grad_norm": 15.235865592956543,
+      "learning_rate": 3.859649122807018e-05,
+      "lm_loss": 0.0706,
+      "loss": 0.7742,
+      "step": 55
+    },
+    {
+      "classification_loss": 0.3018,
+      "epoch": 0.2962962962962963,
+      "grad_norm": 9.986725807189941,
+      "learning_rate": 3.929824561403509e-05,
+      "lm_loss": 0.028,
+      "loss": 0.3298,
+      "step": 56
+    },
+    {
+      "classification_loss": 0.2255,
+      "epoch": 0.30158730158730157,
+      "grad_norm": 5.508973121643066,
+      "learning_rate": 4e-05,
+      "lm_loss": 0.014,
+      "loss": 0.2395,
+      "step": 57
+    },
+    {
+      "classification_loss": 0.8275,
+      "epoch": 0.30687830687830686,
+      "grad_norm": 13.436299324035645,
+      "learning_rate": 3.999962054697454e-05,
+      "lm_loss": 0.1098,
+      "loss": 0.9373,
+      "step": 58
+    },
+    {
+      "classification_loss": 1.3698,
+      "epoch": 0.31216931216931215,
+      "grad_norm": 23.956758499145508,
+      "learning_rate": 3.999848220229662e-05,
+      "lm_loss": 0.1758,
+      "loss": 1.5456,
+      "step": 59
+    },
+    {
+      "classification_loss": 0.5866,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 11.431910514831543,
+      "learning_rate": 3.9996585009161056e-05,
+      "lm_loss": 0.0556,
+      "loss": 0.6421,
+      "step": 60
+    },
+    {
+      "classification_loss": 0.4283,
+      "epoch": 0.32275132275132273,
+      "grad_norm": 12.705597877502441,
+      "learning_rate": 3.999392903955744e-05,
+      "lm_loss": 0.0373,
+      "loss": 0.4656,
+      "step": 61
+    },
+    {
+      "classification_loss": 0.5689,
+      "epoch": 0.328042328042328,
+      "grad_norm": 12.244424819946289,
+      "learning_rate": 3.999051439426732e-05,
+      "lm_loss": 0.0649,
+      "loss": 0.6338,
+      "step": 62
+    },
+    {
+      "classification_loss": 0.662,
+      "epoch": 0.3333333333333333,
+      "grad_norm": 23.293601989746094,
+      "learning_rate": 3.9986341202860467e-05,
+      "lm_loss": 0.0678,
+      "loss": 0.7298,
+      "step": 63
+    },
+    {
+      "classification_loss": 0.4212,
+      "epoch": 0.3386243386243386,
+      "grad_norm": 14.655537605285645,
+      "learning_rate": 3.998140962368987e-05,
+      "lm_loss": 0.0411,
+      "loss": 0.4624,
+      "step": 64
+    },
+    {
+      "classification_loss": 0.4347,
+      "epoch": 0.3439153439153439,
+      "grad_norm": 9.236527442932129,
+      "learning_rate": 3.99757198438858e-05,
+      "lm_loss": 0.0334,
+      "loss": 0.4682,
+      "step": 65
+    },
+    {
+      "classification_loss": 0.4239,
+      "epoch": 0.3492063492063492,
+      "grad_norm": 6.273439884185791,
+      "learning_rate": 3.9969272079348685e-05,
+      "lm_loss": 0.0596,
+      "loss": 0.4835,
+      "step": 66
+    },
+    {
+      "classification_loss": 0.2413,
+      "epoch": 0.3544973544973545,
+      "grad_norm": 7.6536359786987305,
+      "learning_rate": 3.9962066574740886e-05,
+      "lm_loss": 0.0107,
+      "loss": 0.2519,
+      "step": 67
+    },
+    {
+      "classification_loss": 0.2787,
+      "epoch": 0.35978835978835977,
+      "grad_norm": 6.183154106140137,
+      "learning_rate": 3.9954103603477465e-05,
+      "lm_loss": 0.0238,
+      "loss": 0.3025,
+      "step": 68
+    },
+    {
+      "classification_loss": 0.4597,
+      "epoch": 0.36507936507936506,
+      "grad_norm": 6.519228935241699,
+      "learning_rate": 3.994538346771576e-05,
+      "lm_loss": 0.0455,
+      "loss": 0.5052,
+      "step": 69
+    },
+    {
+      "classification_loss": 0.3247,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 6.159754276275635,
+      "learning_rate": 3.993590649834398e-05,
+      "lm_loss": 0.0403,
+      "loss": 0.3649,
+      "step": 70
+    },
+    {
+      "classification_loss": 0.5143,
+      "epoch": 0.37566137566137564,
+      "grad_norm": 9.48263931274414,
+      "learning_rate": 3.992567305496859e-05,
+      "lm_loss": 0.0586,
+      "loss": 0.5729,
+      "step": 71
+    },
+    {
+      "classification_loss": 0.9599,
+      "epoch": 0.38095238095238093,
+      "grad_norm": 13.587491035461426,
+      "learning_rate": 3.991468352590069e-05,
+      "lm_loss": 0.1014,
+      "loss": 1.0613,
+      "step": 72
+    },
+    {
+      "classification_loss": 0.2357,
+      "epoch": 0.3862433862433862,
+      "grad_norm": 4.031269550323486,
+      "learning_rate": 3.990293832814129e-05,
+      "lm_loss": 0.0273,
+      "loss": 0.263,
+      "step": 73
+    },
+    {
+      "classification_loss": 0.7618,
+      "epoch": 0.3915343915343915,
+      "grad_norm": 9.462884902954102,
+      "learning_rate": 3.989043790736547e-05,
+      "lm_loss": 0.0755,
+      "loss": 0.8374,
+      "step": 74
+    },
+    {
+      "classification_loss": 0.5417,
+      "epoch": 0.3968253968253968,
+      "grad_norm": 10.55236530303955,
+      "learning_rate": 3.987718273790548e-05,
+      "lm_loss": 0.0666,
+      "loss": 0.6083,
+      "step": 75
+    },
+    {
+      "classification_loss": 0.5999,
+      "epoch": 0.4021164021164021,
+      "grad_norm": 10.495997428894043,
+      "learning_rate": 3.986317332273273e-05,
+      "lm_loss": 0.0624,
+      "loss": 0.6623,
+      "step": 76
+    },
+    {
+      "classification_loss": 0.5918,
+      "epoch": 0.4074074074074074,
+      "grad_norm": 7.395081520080566,
+      "learning_rate": 3.984841019343872e-05,
+      "lm_loss": 0.0542,
+      "loss": 0.646,
+      "step": 77
+    },
+    {
+      "classification_loss": 0.6787,
+      "epoch": 0.4126984126984127,
+      "grad_norm": 10.61036205291748,
+      "learning_rate": 3.983289391021486e-05,
+      "lm_loss": 0.0718,
+      "loss": 0.7506,
+      "step": 78
+    },
+    {
+      "classification_loss": 0.5252,
+      "epoch": 0.41798941798941797,
+      "grad_norm": 11.041518211364746,
+      "learning_rate": 3.9816625061831206e-05,
+      "lm_loss": 0.067,
+      "loss": 0.5922,
+      "step": 79
+    },
+    {
+      "classification_loss": 0.4167,
+      "epoch": 0.42328042328042326,
+      "grad_norm": 8.010622024536133,
+      "learning_rate": 3.9799604265614145e-05,
+      "lm_loss": 0.0396,
+      "loss": 0.4563,
+      "step": 80
+    },
+    {
+      "classification_loss": 0.3161,
+      "epoch": 0.42857142857142855,
+      "grad_norm": 5.370311737060547,
+      "learning_rate": 3.9781832167422926e-05,
+      "lm_loss": 0.032,
+      "loss": 0.348,
+      "step": 81
+    },
+    {
+      "classification_loss": 0.2709,
+      "epoch": 0.43386243386243384,
+      "grad_norm": 7.361512660980225,
+      "learning_rate": 3.976330944162519e-05,
+      "lm_loss": 0.0262,
+      "loss": 0.2971,
+      "step": 82
+    },
+    {
+      "classification_loss": 0.3102,
+      "epoch": 0.43915343915343913,
+      "grad_norm": 5.32011604309082,
+      "learning_rate": 3.974403679107139e-05,
+      "lm_loss": 0.0306,
+      "loss": 0.3408,
+      "step": 83
+    },
+    {
+      "classification_loss": 0.7924,
+      "epoch": 0.4444444444444444,
+      "grad_norm": 13.953025817871094,
+      "learning_rate": 3.972401494706805e-05,
+      "lm_loss": 0.0671,
+      "loss": 0.8596,
+      "step": 84
+    },
+    {
+      "classification_loss": 0.6462,
+      "epoch": 0.4497354497354497,
+      "grad_norm": 8.769445419311523,
+      "learning_rate": 3.970324466935013e-05,
+      "lm_loss": 0.0593,
+      "loss": 0.7056,
+      "step": 85
+    },
+    {
+      "classification_loss": 1.0483,
+      "epoch": 0.455026455026455,
+      "grad_norm": 20.772789001464844,
+      "learning_rate": 3.968172674605209e-05,
+      "lm_loss": 0.1143,
+      "loss": 1.1626,
+      "step": 86
+    },
+    {
+      "classification_loss": 0.6172,
+      "epoch": 0.4603174603174603,
+      "grad_norm": 8.573277473449707,
+      "learning_rate": 3.965946199367804e-05,
+      "lm_loss": 0.0719,
+      "loss": 0.6891,
+      "step": 87
+    },
+    {
+      "classification_loss": 0.4384,
+      "epoch": 0.4656084656084656,
+      "grad_norm": 10.491643905639648,
+      "learning_rate": 3.9636451257070744e-05,
+      "lm_loss": 0.0432,
+      "loss": 0.4816,
+      "step": 88
+    },
+    {
+      "classification_loss": 0.6998,
+      "epoch": 0.4708994708994709,
+      "grad_norm": 12.389782905578613,
+      "learning_rate": 3.9612695409379555e-05,
+      "lm_loss": 0.0842,
+      "loss": 0.784,
+      "step": 89
+    },
+    {
+      "classification_loss": 0.4868,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 16.95037269592285,
+      "learning_rate": 3.958819535202732e-05,
+      "lm_loss": 0.0394,
+      "loss": 0.5262,
+      "step": 90
+    },
+    {
+      "classification_loss": 0.5326,
+      "epoch": 0.48148148148148145,
+      "grad_norm": 16.24233055114746,
+      "learning_rate": 3.9562952014676116e-05,
+      "lm_loss": 0.0326,
+      "loss": 0.5652,
+      "step": 91
+    },
+    {
+      "classification_loss": 0.5912,
+      "epoch": 0.48677248677248675,
+      "grad_norm": 8.411019325256348,
+      "learning_rate": 3.9536966355192016e-05,
+      "lm_loss": 0.059,
+      "loss": 0.6503,
+      "step": 92
+    },
+    {
+      "classification_loss": 0.4194,
+      "epoch": 0.49206349206349204,
+      "grad_norm": 9.523442268371582,
+      "learning_rate": 3.951023935960874e-05,
+      "lm_loss": 0.0503,
+      "loss": 0.4698,
+      "step": 93
+    },
+    {
+      "classification_loss": 0.4555,
+      "epoch": 0.4973544973544973,
+      "grad_norm": 8.235868453979492,
+      "learning_rate": 3.948277204209021e-05,
+      "lm_loss": 0.053,
+      "loss": 0.5085,
+      "step": 94
+    },
+    {
+      "classification_loss": 0.5776,
+      "epoch": 0.5026455026455027,
+      "grad_norm": 7.883787155151367,
+      "learning_rate": 3.94545654448921e-05,
+      "lm_loss": 0.0673,
+      "loss": 0.645,
+      "step": 95
+    },
+    {
+      "classification_loss": 0.3547,
+      "epoch": 0.5079365079365079,
+      "grad_norm": 4.894813537597656,
+      "learning_rate": 3.942562063832228e-05,
+      "lm_loss": 0.0338,
+      "loss": 0.3885,
+      "step": 96
+    },
+    {
+      "classification_loss": 0.6996,
+      "epoch": 0.5132275132275133,
+      "grad_norm": 8.746223449707031,
+      "learning_rate": 3.9395938720700196e-05,
+      "lm_loss": 0.0804,
+      "loss": 0.7801,
+      "step": 97
+    },
+    {
+      "classification_loss": 0.6367,
+      "epoch": 0.5185185185185185,
+      "grad_norm": 9.751365661621094,
+      "learning_rate": 3.936552081831518e-05,
+      "lm_loss": 0.0673,
+      "loss": 0.704,
+      "step": 98
+    },
+    {
+      "classification_loss": 0.7447,
+      "epoch": 0.5238095238095238,
+      "grad_norm": 10.005545616149902,
+      "learning_rate": 3.933436808538375e-05,
+      "lm_loss": 0.0847,
+      "loss": 0.8294,
+      "step": 99
+    },
+    {
+      "classification_loss": 0.3838,
+      "epoch": 0.5291005291005291,
+      "grad_norm": 6.678869247436523,
+      "learning_rate": 3.930248170400578e-05,
+      "lm_loss": 0.0474,
+      "loss": 0.4312,
+      "step": 100
+    },
+    {
+      "epoch": 0.5291005291005291,
+      "eval_accuracy": 0.8700565099716187,
+      "eval_auroc": 0.93075031042099,
+      "eval_classification_loss": 0.37040606141090393,
+      "eval_f1": 0.8391608595848083,
+      "eval_lm_loss": 0.04573189839720726,
+      "eval_loss": 0.4161379635334015,
+      "eval_precision": 0.7407407164573669,
+      "eval_recall": 0.9677419066429138,
+      "eval_runtime": 15.53,
+      "eval_samples_per_second": 22.795,
+      "eval_steps_per_second": 1.481,
+      "step": 100
+    },
+    {
+      "classification_loss": 0.317,
+      "epoch": 0.5343915343915344,
+      "grad_norm": 4.977490425109863,
+      "learning_rate": 3.9269862884119666e-05,
+      "lm_loss": 0.0596,
+      "loss": 0.3766,
+      "step": 101
+    },
+    {
+      "classification_loss": 0.5167,
+      "epoch": 0.5396825396825397,
+      "grad_norm": 5.793409824371338,
+      "learning_rate": 3.923651286345638e-05,
+      "lm_loss": 0.0525,
+      "loss": 0.5692,
+      "step": 102
+    },
+    {
+      "classification_loss": 0.3664,
+      "epoch": 0.544973544973545,
+      "grad_norm": 5.308522701263428,
+      "learning_rate": 3.920243290749257e-05,
+      "lm_loss": 0.0368,
+      "loss": 0.4032,
+      "step": 103
+    },
+    {
+      "classification_loss": 0.3934,
+      "epoch": 0.5502645502645502,
+      "grad_norm": 5.193403244018555,
+      "learning_rate": 3.916762430940245e-05,
+      "lm_loss": 0.0431,
+      "loss": 0.4365,
+      "step": 104
+    },
+    {
+      "classification_loss": 0.5176,
+      "epoch": 0.5555555555555556,
+      "grad_norm": 6.1582417488098145,
+      "learning_rate": 3.913208839000882e-05,
+      "lm_loss": 0.054,
+      "loss": 0.5716,
+      "step": 105
+    },
+    {
+      "classification_loss": 0.2793,
+      "epoch": 0.5608465608465608,
+      "grad_norm": 4.8112359046936035,
+      "learning_rate": 3.9095826497732894e-05,
+      "lm_loss": 0.0276,
+      "loss": 0.3069,
+      "step": 106
+    },
+    {
+      "classification_loss": 0.5567,
+      "epoch": 0.5661375661375662,
+      "grad_norm": 11.405841827392578,
+      "learning_rate": 3.9058840008543136e-05,
+      "lm_loss": 0.0422,
+      "loss": 0.5989,
+      "step": 107
+    },
+    {
+      "classification_loss": 0.743,
+      "epoch": 0.5714285714285714,
+      "grad_norm": 7.794854164123535,
+      "learning_rate": 3.9021130325903076e-05,
+      "lm_loss": 0.0612,
+      "loss": 0.8042,
+      "step": 108
+    },
+    {
+      "classification_loss": 0.2738,
+      "epoch": 0.5767195767195767,
+      "grad_norm": 5.324756622314453,
+      "learning_rate": 3.898269888071803e-05,
+      "lm_loss": 0.0325,
+      "loss": 0.3063,
+      "step": 109
+    },
+    {
+      "classification_loss": 0.4425,
+      "epoch": 0.582010582010582,
+      "grad_norm": 8.351327896118164,
+      "learning_rate": 3.894354713128081e-05,
+      "lm_loss": 0.0522,
+      "loss": 0.4947,
+      "step": 110
+    },
+    {
+      "classification_loss": 0.419,
+      "epoch": 0.5873015873015873,
+      "grad_norm": 5.21488618850708,
+      "learning_rate": 3.89036765632164e-05,
+      "lm_loss": 0.0345,
+      "loss": 0.4535,
+      "step": 111
+    },
+    {
+      "classification_loss": 0.5999,
+      "epoch": 0.5925925925925926,
+      "grad_norm": 7.710854530334473,
+      "learning_rate": 3.886308868942555e-05,
+      "lm_loss": 0.0519,
+      "loss": 0.6518,
+      "step": 112
+    },
+    {
+      "classification_loss": 0.4637,
+      "epoch": 0.5978835978835979,
+      "grad_norm": 5.4215850830078125,
+      "learning_rate": 3.882178505002743e-05,
+      "lm_loss": 0.0509,
+      "loss": 0.5146,
+      "step": 113
+    },
+    {
+      "classification_loss": 0.402,
+      "epoch": 0.6031746031746031,
+      "grad_norm": 4.375611782073975,
+      "learning_rate": 3.877976721230114e-05,
+      "lm_loss": 0.0434,
+      "loss": 0.4455,
+      "step": 114
+    },
+    {
+      "classification_loss": 0.4535,
+      "epoch": 0.6084656084656085,
+      "grad_norm": 8.165907859802246,
+      "learning_rate": 3.8737036770626215e-05,
+      "lm_loss": 0.0434,
+      "loss": 0.4969,
+      "step": 115
+    },
+    {
+      "classification_loss": 0.6316,
+      "epoch": 0.6137566137566137,
+      "grad_norm": 8.169610977172852,
+      "learning_rate": 3.8693595346422216e-05,
+      "lm_loss": 0.065,
+      "loss": 0.6967,
+      "step": 116
+    },
+    {
+      "classification_loss": 0.6539,
+      "epoch": 0.6190476190476191,
+      "grad_norm": 9.205584526062012,
+      "learning_rate": 3.864944458808712e-05,
+      "lm_loss": 0.0611,
+      "loss": 0.715,
+      "step": 117
+    },
+    {
+      "classification_loss": 0.3923,
+      "epoch": 0.6243386243386243,
+      "grad_norm": 4.229909896850586,
+      "learning_rate": 3.860458617093481e-05,
+      "lm_loss": 0.0409,
+      "loss": 0.4332,
+      "step": 118
+    },
+    {
+      "classification_loss": 0.6024,
+      "epoch": 0.6296296296296297,
+      "grad_norm": 7.795385837554932,
+      "learning_rate": 3.85590217971315e-05,
+      "lm_loss": 0.0687,
+      "loss": 0.6711,
+      "step": 119
+    },
+    {
+      "classification_loss": 0.7778,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 14.413529396057129,
+      "learning_rate": 3.851275319563113e-05,
+      "lm_loss": 0.1123,
+      "loss": 0.8901,
+      "step": 120
+    },
+    {
+      "classification_loss": 0.6812,
+      "epoch": 0.6402116402116402,
+      "grad_norm": 7.452106475830078,
+      "learning_rate": 3.846578212210979e-05,
+      "lm_loss": 0.076,
+      "loss": 0.7573,
+      "step": 121
+    },
+    {
+      "classification_loss": 0.2687,
+      "epoch": 0.6455026455026455,
+      "grad_norm": 3.9474825859069824,
+      "learning_rate": 3.841811035889908e-05,
+      "lm_loss": 0.0276,
+      "loss": 0.2963,
+      "step": 122
+    },
+    {
+      "classification_loss": 0.3593,
+      "epoch": 0.6507936507936508,
+      "grad_norm": 4.684298515319824,
+      "learning_rate": 3.836973971491847e-05,
+      "lm_loss": 0.0289,
+      "loss": 0.3882,
+      "step": 123
+    },
+    {
+      "classification_loss": 0.4461,
+      "epoch": 0.656084656084656,
+      "grad_norm": 4.967252731323242,
+      "learning_rate": 3.832067202560668e-05,
+      "lm_loss": 0.0395,
+      "loss": 0.4856,
+      "step": 124
+    },
+    {
+      "classification_loss": 0.5545,
+      "epoch": 0.6613756613756614,
+      "grad_norm": 5.953970909118652,
+      "learning_rate": 3.827090915285202e-05,
+      "lm_loss": 0.0641,
+      "loss": 0.6185,
+      "step": 125
+    },
+    {
+      "classification_loss": 0.5184,
+      "epoch": 0.6666666666666666,
+      "grad_norm": 7.034300327301025,
+      "learning_rate": 3.822045298492177e-05,
+      "lm_loss": 0.0836,
+      "loss": 0.602,
+      "step": 126
+    },
+    {
+      "classification_loss": 0.5116,
+      "epoch": 0.671957671957672,
+      "grad_norm": 7.100449562072754,
+      "learning_rate": 3.8169305436390474e-05,
+      "lm_loss": 0.0455,
+      "loss": 0.5571,
+      "step": 127
+    },
+    {
+      "classification_loss": 0.6806,
+      "epoch": 0.6772486772486772,
+      "grad_norm": 9.678451538085938,
+      "learning_rate": 3.8117468448067345e-05,
+      "lm_loss": 0.0689,
+      "loss": 0.7496,
+      "step": 128
+    },
+    {
+      "classification_loss": 0.3966,
+      "epoch": 0.6825396825396826,
+      "grad_norm": 5.198436260223389,
+      "learning_rate": 3.806494398692258e-05,
+      "lm_loss": 0.0461,
+      "loss": 0.4427,
+      "step": 129
+    },
+    {
+      "classification_loss": 0.4291,
+      "epoch": 0.6878306878306878,
+      "grad_norm": 5.229558944702148,
+      "learning_rate": 3.801173404601275e-05,
+      "lm_loss": 0.0354,
+      "loss": 0.4645,
+      "step": 130
+    },
+    {
+      "classification_loss": 0.429,
+      "epoch": 0.6931216931216931,
+      "grad_norm": 4.4721455574035645,
+      "learning_rate": 3.7957840644405164e-05,
+      "lm_loss": 0.0489,
+      "loss": 0.4779,
+      "step": 131
+    },
+    {
+      "classification_loss": 0.5577,
+      "epoch": 0.6984126984126984,
+      "grad_norm": 5.873918056488037,
+      "learning_rate": 3.790326582710125e-05,
+      "lm_loss": 0.0595,
+      "loss": 0.6172,
+      "step": 132
+    },
+    {
+      "classification_loss": 0.4751,
+      "epoch": 0.7037037037037037,
+      "grad_norm": 5.666612148284912,
+      "learning_rate": 3.784801166495896e-05,
+      "lm_loss": 0.0501,
+      "loss": 0.5252,
+      "step": 133
+    },
+    {
+      "classification_loss": 0.3547,
+      "epoch": 0.708994708994709,
+      "grad_norm": 4.493051528930664,
+      "learning_rate": 3.77920802546142e-05,
+      "lm_loss": 0.0364,
+      "loss": 0.3911,
+      "step": 134
+    },
+    {
+      "classification_loss": 0.4999,
+      "epoch": 0.7142857142857143,
+      "grad_norm": 6.651557922363281,
+      "learning_rate": 3.773547371840124e-05,
+      "lm_loss": 0.0428,
+      "loss": 0.5427,
+      "step": 135
+    },
+    {
+      "classification_loss": 0.3249,
+      "epoch": 0.7195767195767195,
+      "grad_norm": 5.5701985359191895,
+      "learning_rate": 3.7678194204272246e-05,
+      "lm_loss": 0.0275,
+      "loss": 0.3524,
+      "step": 136
+    },
+    {
+      "classification_loss": 0.553,
+      "epoch": 0.7248677248677249,
+      "grad_norm": 6.871671676635742,
+      "learning_rate": 3.7620243885715695e-05,
+      "lm_loss": 0.0569,
+      "loss": 0.61,
+      "step": 137
+    },
+    {
+      "classification_loss": 0.3173,
+      "epoch": 0.7301587301587301,
+      "grad_norm": 3.8207015991210938,
+      "learning_rate": 3.756162496167396e-05,
+      "lm_loss": 0.0298,
+      "loss": 0.3471,
+      "step": 138
+    },
+    {
+      "classification_loss": 0.2213,
+      "epoch": 0.7354497354497355,
+      "grad_norm": 4.471009731292725,
+      "learning_rate": 3.750233965645985e-05,
+      "lm_loss": 0.0273,
+      "loss": 0.2486,
+      "step": 139
+    },
+    {
+      "classification_loss": 0.277,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 4.64603853225708,
+      "learning_rate": 3.744239021967222e-05,
+      "lm_loss": 0.0258,
+      "loss": 0.3028,
+      "step": 140
+    },
+    {
+      "classification_loss": 0.6027,
+      "epoch": 0.746031746031746,
+      "grad_norm": 8.339837074279785,
+      "learning_rate": 3.738177892611057e-05,
+      "lm_loss": 0.0561,
+      "loss": 0.6588,
+      "step": 141
+    },
+    {
+      "classification_loss": 0.8025,
+      "epoch": 0.7513227513227513,
+      "grad_norm": 11.05119514465332,
+      "learning_rate": 3.732050807568878e-05,
+      "lm_loss": 0.0623,
+      "loss": 0.8648,
+      "step": 142
+    },
+    {
+      "classification_loss": 0.7122,
+      "epoch": 0.7566137566137566,
+      "grad_norm": 9.975105285644531,
+      "learning_rate": 3.72585799933478e-05,
+      "lm_loss": 0.0644,
+      "loss": 0.7766,
+      "step": 143
+    },
+    {
+      "classification_loss": 0.3115,
+      "epoch": 0.7619047619047619,
+      "grad_norm": 5.718208312988281,
+      "learning_rate": 3.719599702896745e-05,
+      "lm_loss": 0.0328,
+      "loss": 0.3443,
+      "step": 144
+    },
+    {
+      "classification_loss": 0.4022,
+      "epoch": 0.7671957671957672,
+      "grad_norm": 6.724981784820557,
+      "learning_rate": 3.713276155727726e-05,
+      "lm_loss": 0.0337,
+      "loss": 0.4359,
+      "step": 145
+    },
+    {
+      "classification_loss": 0.5227,
+      "epoch": 0.7724867724867724,
+      "grad_norm": 8.479836463928223,
+      "learning_rate": 3.706887597776632e-05,
+      "lm_loss": 0.0441,
+      "loss": 0.5668,
+      "step": 146
+    },
+    {
+      "classification_loss": 0.2577,
+      "epoch": 0.7777777777777778,
+      "grad_norm": 4.008189678192139,
+      "learning_rate": 3.700434271459229e-05,
+      "lm_loss": 0.0275,
+      "loss": 0.2853,
+      "step": 147
+    },
+    {
+      "classification_loss": 0.564,
+      "epoch": 0.783068783068783,
+      "grad_norm": 6.004014492034912,
+      "learning_rate": 3.6939164216489345e-05,
+      "lm_loss": 0.0526,
+      "loss": 0.6166,
+      "step": 148
+    },
+    {
+      "classification_loss": 0.4274,
+      "epoch": 0.7883597883597884,
+      "grad_norm": 4.825228214263916,
+      "learning_rate": 3.687334295667533e-05,
+      "lm_loss": 0.0396,
+      "loss": 0.467,
+      "step": 149
+    },
+    {
+      "classification_loss": 0.4864,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 8.514625549316406,
+      "learning_rate": 3.680688143275786e-05,
+      "lm_loss": 0.0408,
+      "loss": 0.5272,
+      "step": 150
+    },
+    {
+      "epoch": 0.7936507936507936,
+      "eval_accuracy": 0.8813559412956238,
+      "eval_auroc": 0.9317671656608582,
+      "eval_classification_loss": 0.4037400186061859,
+      "eval_f1": 0.8489208817481995,
+      "eval_lm_loss": 0.03990057483315468,
+      "eval_loss": 0.4436405301094055,
+      "eval_precision": 0.7662337422370911,
+      "eval_recall": 0.9516128897666931,
+      "eval_runtime": 15.5269,
+      "eval_samples_per_second": 22.799,
+      "eval_steps_per_second": 1.481,
+      "step": 150
+    },
+    {
+      "classification_loss": 0.4105,
+      "epoch": 0.798941798941799,
+      "grad_norm": 5.878465175628662,
+      "learning_rate": 3.673978216663956e-05,
+      "lm_loss": 0.0416,
+      "loss": 0.452,
+      "step": 151
+    },
+    {
+      "classification_loss": 0.6657,
+      "epoch": 0.8042328042328042,
+      "grad_norm": 5.658477306365967,
+      "learning_rate": 3.667204770442239e-05,
+      "lm_loss": 0.0655,
+      "loss": 0.7312,
+      "step": 152
+    },
+    {
+      "classification_loss": 0.3666,
+      "epoch": 0.8095238095238095,
+      "grad_norm": 7.839348316192627,
+      "learning_rate": 3.6603680616311013e-05,
+      "lm_loss": 0.0375,
+      "loss": 0.4041,
+      "step": 153
+    },
+    {
+      "classification_loss": 0.3906,
+      "epoch": 0.8148148148148148,
+      "grad_norm": 4.447023868560791,
+      "learning_rate": 3.653468349651527e-05,
+      "lm_loss": 0.0338,
+      "loss": 0.4244,
+      "step": 154
+    },
+    {
+      "classification_loss": 0.3549,
+      "epoch": 0.8201058201058201,
+      "grad_norm": 3.7753591537475586,
+      "learning_rate": 3.646505896315175e-05,
+      "lm_loss": 0.0427,
+      "loss": 0.3976,
+      "step": 155
+    },
+    {
+      "classification_loss": 0.5758,
+      "epoch": 0.8253968253968254,
+      "grad_norm": 5.476145267486572,
+      "learning_rate": 3.639480965814443e-05,
+      "lm_loss": 0.0619,
+      "loss": 0.6376,
+      "step": 156
+    },
+    {
+      "classification_loss": 0.4419,
+      "epoch": 0.8306878306878307,
+      "grad_norm": 4.684837341308594,
+      "learning_rate": 3.632393824712444e-05,
+      "lm_loss": 0.0543,
+      "loss": 0.4962,
+      "step": 157
+    },
+    {
+      "classification_loss": 0.3925,
+      "epoch": 0.8359788359788359,
+      "grad_norm": 5.519379615783691,
+      "learning_rate": 3.625244741932892e-05,
+      "lm_loss": 0.0363,
+      "loss": 0.4288,
+      "step": 158
+    },
+    {
+      "classification_loss": 0.4306,
+      "epoch": 0.8412698412698413,
+      "grad_norm": 4.434086322784424,
+      "learning_rate": 3.6180339887498953e-05,
+      "lm_loss": 0.0424,
+      "loss": 0.4731,
+      "step": 159
+    },
+    {
+      "classification_loss": 0.4753,
+      "epoch": 0.8465608465608465,
+      "grad_norm": 4.594567775726318,
+      "learning_rate": 3.610761838777665e-05,
+      "lm_loss": 0.0528,
+      "loss": 0.5281,
+      "step": 160
+    },
+    {
+      "classification_loss": 0.4848,
+      "epoch": 0.8518518518518519,
+      "grad_norm": 7.448020935058594,
+      "learning_rate": 3.6034285679601334e-05,
+      "lm_loss": 0.0618,
+      "loss": 0.5466,
+      "step": 161
+    },
+    {
+      "classification_loss": 0.1928,
+      "epoch": 0.8571428571428571,
+      "grad_norm": 6.5110931396484375,
+      "learning_rate": 3.5960344545604796e-05,
+      "lm_loss": 0.0124,
+      "loss": 0.2053,
+      "step": 162
+    },
+    {
+      "classification_loss": 0.3206,
+      "epoch": 0.8624338624338624,
+      "grad_norm": 4.479043006896973,
+      "learning_rate": 3.588579779150572e-05,
+      "lm_loss": 0.0355,
+      "loss": 0.3561,
+      "step": 163
+    },
+    {
+      "classification_loss": 0.2145,
+      "epoch": 0.8677248677248677,
+      "grad_norm": 6.838748931884766,
+      "learning_rate": 3.581064824600327e-05,
+      "lm_loss": 0.0209,
+      "loss": 0.2354,
+      "step": 164
+    },
+    {
+      "classification_loss": 0.5187,
+      "epoch": 0.873015873015873,
+      "grad_norm": 7.051374912261963,
+      "learning_rate": 3.573489876066967e-05,
+      "lm_loss": 0.0476,
+      "loss": 0.5662,
+      "step": 165
+    },
+    {
+      "classification_loss": 0.4017,
+      "epoch": 0.8783068783068783,
+      "grad_norm": 5.828752517700195,
+      "learning_rate": 3.565855220984206e-05,
+      "lm_loss": 0.0468,
+      "loss": 0.4484,
+      "step": 166
+    },
+    {
+      "classification_loss": 0.2539,
+      "epoch": 0.8835978835978836,
+      "grad_norm": 7.273751735687256,
+      "learning_rate": 3.558161149051341e-05,
+      "lm_loss": 0.0206,
+      "loss": 0.2745,
+      "step": 167
+    },
+    {
+      "classification_loss": 0.8012,
+      "epoch": 0.8888888888888888,
+      "grad_norm": 9.21143627166748,
+      "learning_rate": 3.55040795222226e-05,
+      "lm_loss": 0.0898,
+      "loss": 0.891,
+      "step": 168
+    },
+    {
+      "classification_loss": 0.1164,
+      "epoch": 0.8941798941798942,
+      "grad_norm": 4.1860032081604,
+      "learning_rate": 3.542595924694362e-05,
+      "lm_loss": 0.013,
+      "loss": 0.1294,
+      "step": 169
+    },
+    {
+      "classification_loss": 0.5173,
+      "epoch": 0.8994708994708994,
+      "grad_norm": 7.0001301765441895,
+      "learning_rate": 3.534725362897394e-05,
+      "lm_loss": 0.0479,
+      "loss": 0.5651,
+      "step": 170
+    },
+    {
+      "classification_loss": 0.2549,
+      "epoch": 0.9047619047619048,
+      "grad_norm": 7.007653713226318,
+      "learning_rate": 3.526796565482206e-05,
+      "lm_loss": 0.0301,
+      "loss": 0.285,
+      "step": 171
+    },
+    {
+      "classification_loss": 0.4568,
+      "epoch": 0.91005291005291,
+      "grad_norm": 5.752516746520996,
+      "learning_rate": 3.5188098333094145e-05,
+      "lm_loss": 0.0573,
+      "loss": 0.5141,
+      "step": 172
+    },
+    {
+      "classification_loss": 0.7478,
+      "epoch": 0.9153439153439153,
+      "grad_norm": 8.939093589782715,
+      "learning_rate": 3.5107654694379873e-05,
+      "lm_loss": 0.0759,
+      "loss": 0.8238,
+      "step": 173
+    },
+    {
+      "classification_loss": 0.5309,
+      "epoch": 0.9206349206349206,
+      "grad_norm": 5.358952522277832,
+      "learning_rate": 3.502663779113747e-05,
+      "lm_loss": 0.0571,
+      "loss": 0.588,
+      "step": 174
+    },
+    {
+      "classification_loss": 0.8604,
+      "epoch": 0.9259259259259259,
+      "grad_norm": 9.570755958557129,
+      "learning_rate": 3.494505069757782e-05,
+      "lm_loss": 0.0792,
+      "loss": 0.9396,
+      "step": 175
+    },
+    {
+      "classification_loss": 0.489,
+      "epoch": 0.9312169312169312,
+      "grad_norm": 7.282289981842041,
+      "learning_rate": 3.4862896509547886e-05,
+      "lm_loss": 0.0456,
+      "loss": 0.5346,
+      "step": 176
+    },
+    {
+      "classification_loss": 0.4567,
+      "epoch": 0.9365079365079365,
+      "grad_norm": 6.593536853790283,
+      "learning_rate": 3.478017834441319e-05,
+      "lm_loss": 0.0574,
+      "loss": 0.5142,
+      "step": 177
+    },
+    {
+      "classification_loss": 0.329,
+      "epoch": 0.9417989417989417,
+      "grad_norm": 6.121315002441406,
+      "learning_rate": 3.4696899340939517e-05,
+      "lm_loss": 0.0372,
+      "loss": 0.3662,
+      "step": 178
+    },
+    {
+      "classification_loss": 0.4779,
+      "epoch": 0.9470899470899471,
+      "grad_norm": 6.270368576049805,
+      "learning_rate": 3.4613062659173865e-05,
+      "lm_loss": 0.0542,
+      "loss": 0.5321,
+      "step": 179
+    },
+    {
+      "classification_loss": 0.6646,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 7.001364231109619,
+      "learning_rate": 3.452867148032449e-05,
+      "lm_loss": 0.0641,
+      "loss": 0.7287,
+      "step": 180
+    },
+    {
+      "classification_loss": 0.3869,
+      "epoch": 0.9576719576719577,
+      "grad_norm": 4.298563003540039,
+      "learning_rate": 3.4443729006640186e-05,
+      "lm_loss": 0.0346,
+      "loss": 0.4216,
+      "step": 181
+    },
+    {
+      "classification_loss": 0.4179,
+      "epoch": 0.9629629629629629,
+      "grad_norm": 4.519134044647217,
+      "learning_rate": 3.435823846128884e-05,
+      "lm_loss": 0.0425,
+      "loss": 0.4604,
+      "step": 182
+    },
+    {
+      "classification_loss": 0.5921,
+      "epoch": 0.9682539682539683,
+      "grad_norm": 5.8256916999816895,
+      "learning_rate": 3.427220308823505e-05,
+      "lm_loss": 0.0601,
+      "loss": 0.6522,
+      "step": 183
+    },
+    {
+      "classification_loss": 0.383,
+      "epoch": 0.9735449735449735,
+      "grad_norm": 4.641335964202881,
+      "learning_rate": 3.418562615211707e-05,
+      "lm_loss": 0.0435,
+      "loss": 0.4265,
+      "step": 184
+    },
+    {
+      "classification_loss": 0.3616,
+      "epoch": 0.9788359788359788,
+      "grad_norm": 4.482592582702637,
+      "learning_rate": 3.409851093812295e-05,
+      "lm_loss": 0.032,
+      "loss": 0.3936,
+      "step": 185
+    },
+    {
+      "classification_loss": 0.6806,
+      "epoch": 0.9841269841269841,
+      "grad_norm": 5.762667655944824,
+      "learning_rate": 3.401086075186582e-05,
+      "lm_loss": 0.061,
+      "loss": 0.7416,
+      "step": 186
+    },
+    {
+      "classification_loss": 0.3452,
+      "epoch": 0.9894179894179894,
+      "grad_norm": 5.030579566955566,
+      "learning_rate": 3.392267891925854e-05,
+      "lm_loss": 0.0322,
+      "loss": 0.3774,
+      "step": 187
+    },
+    {
+      "classification_loss": 0.1775,
+      "epoch": 0.9947089947089947,
+      "grad_norm": 3.0634727478027344,
+      "learning_rate": 3.383396878638741e-05,
+      "lm_loss": 0.0224,
+      "loss": 0.1999,
+      "step": 188
+    },
+    {
+      "classification_loss": 0.2488,
+      "epoch": 1.0,
+      "grad_norm": 6.196967124938965,
+      "learning_rate": 3.374473371938526e-05,
+      "lm_loss": 0.021,
+      "loss": 0.2698,
+      "step": 189
+    },
+    {
+      "classification_loss": 0.6167,
+      "epoch": 1.0052910052910053,
+      "grad_norm": 7.134896278381348,
+      "learning_rate": 3.365497710430371e-05,
+      "lm_loss": 0.0709,
+      "loss": 0.6876,
+      "step": 190
+    },
+    {
+      "classification_loss": 0.2399,
+      "epoch": 1.0105820105820107,
+      "grad_norm": 5.862342834472656,
+      "learning_rate": 3.356470234698468e-05,
+      "lm_loss": 0.0159,
+      "loss": 0.2558,
+      "step": 191
+    },
+    {
+      "classification_loss": 0.3992,
+      "epoch": 1.0158730158730158,
+      "grad_norm": 4.166635513305664,
+      "learning_rate": 3.347391287293115e-05,
+      "lm_loss": 0.0494,
+      "loss": 0.4485,
+      "step": 192
+    },
+    {
+      "classification_loss": 0.0891,
+      "epoch": 1.0211640211640212,
+      "grad_norm": 2.7699098587036133,
+      "learning_rate": 3.3382612127177166e-05,
+      "lm_loss": 0.0064,
+      "loss": 0.0956,
+      "step": 193
+    },
+    {
+      "classification_loss": 0.6035,
+      "epoch": 1.0264550264550265,
+      "grad_norm": 6.711143970489502,
+      "learning_rate": 3.329080357415716e-05,
+      "lm_loss": 0.0677,
+      "loss": 0.6712,
+      "step": 194
+    },
+    {
+      "classification_loss": 0.4115,
+      "epoch": 1.0317460317460316,
+      "grad_norm": 4.826721668243408,
+      "learning_rate": 3.319849069757446e-05,
+      "lm_loss": 0.0396,
+      "loss": 0.4511,
+      "step": 195
+    },
+    {
+      "classification_loss": 0.3025,
+      "epoch": 1.037037037037037,
+      "grad_norm": 4.070664882659912,
+      "learning_rate": 3.310567700026908e-05,
+      "lm_loss": 0.0294,
+      "loss": 0.3319,
+      "step": 196
+    },
+    {
+      "classification_loss": 0.2767,
+      "epoch": 1.0423280423280423,
+      "grad_norm": 5.486062049865723,
+      "learning_rate": 3.301236600408484e-05,
+      "lm_loss": 0.0329,
+      "loss": 0.3097,
+      "step": 197
+    },
+    {
+      "classification_loss": 0.4176,
+      "epoch": 1.0476190476190477,
+      "grad_norm": 4.901826858520508,
+      "learning_rate": 3.291856124973575e-05,
+      "lm_loss": 0.0482,
+      "loss": 0.4658,
+      "step": 198
+    },
+    {
+      "classification_loss": 0.5174,
+      "epoch": 1.052910052910053,
+      "grad_norm": 5.271239757537842,
+      "learning_rate": 3.282426629667157e-05,
+      "lm_loss": 0.0517,
+      "loss": 0.5692,
+      "step": 199
+    },
+    {
+      "classification_loss": 0.3984,
+      "epoch": 1.0582010582010581,
+      "grad_norm": 4.809482574462891,
+      "learning_rate": 3.272948472294283e-05,
+      "lm_loss": 0.0345,
+      "loss": 0.4328,
+      "step": 200
+    },
+    {
+      "epoch": 1.0582010582010581,
+      "eval_accuracy": 0.8898305296897888,
+      "eval_auroc": 0.9264024496078491,
+      "eval_classification_loss": 0.42330121994018555,
+      "eval_f1": 0.8592057824134827,
+      "eval_lm_loss": 0.0521097332239151,
+      "eval_loss": 0.4754108786582947,
+      "eval_precision": 0.7777777910232544,
+      "eval_recall": 0.9596773982048035,
+      "eval_runtime": 15.5476,
+      "eval_samples_per_second": 22.769,
+      "eval_steps_per_second": 1.479,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 567,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.0885255820288e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cac22c6c9f17a1b17e84574adfe2f0d1e026b2160bbc6100073119b9e307415
+size 7992