commit 133ffdffd76d936c08c949ca2ed0e2a3afd88356
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Thu Oct 22 03:20:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: funeedev/new-ai
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..bc5f30d
--- /dev/null
+++ b/README.md
@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# 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. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **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]
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..7ad7eed
--- /dev/null
+++ b/config.json
@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128001,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128001,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.15.1",
+  "use_cache": false,
+  "vocab_size": 129225
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..5a05ef4
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001
+  ],
+  "pad_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "5.15.1"
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..dfae80e
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd49035dc079301f03ad3d138607f4069f17e2ef5919d4eb7ec6b59af389942a
+size 6431482648
diff --git a/optimizer.pt b/optimizer.pt
new file mode 100644
index 0000000..841ce29
--- /dev/null
+++ b/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de461d08b935356e90f06301c7770f4a1a8ff9656cd9d2fd8080419b54e9cb2
+size 12863131775
diff --git a/rng_state.pth b/rng_state.pth
new file mode 100644
index 0000000..fbfc9df
--- /dev/null
+++ b/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236304ae89e49aae8260113165ee63419b9b745f79120014328a7fa31ed79b42
+size 14645
diff --git a/scheduler.pt b/scheduler.pt
new file mode 100644
index 0000000..57f4e09
--- /dev/null
+++ b/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a0689b278fbf348cf87ee3109abbf3da22265739d730c894018f40d66124d6a
+size 1465
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..45f8859
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b32b76d9e2a8f6afdf223b61694aefcb302ee379940e48fe12a20362ad556e54
+size 17386452
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..385b8b1
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,38 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": [
+    "<lang_th>",
+    "<lang_lkt>",
+    "<regular_numerals>",
+    "<output>",
+    "<lang_en>",
+    "<lang_es>",
+    "<lang_de>",
+    "<lang_it>",
+    "</output>",
+    "<lang_fr>",
+    "<input>",
+    "</input>",
+    "<lang_pt>",
+    "<male>",
+    "<lakota_numerals>",
+    "<female>",
+    "<lang_hi>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "max_length": 256,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "stride": 0,
+  "tokenizer_class": "TokenizersBackend",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
+}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..40238e9
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,2230 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.686420318041414,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0022880677268047136,
+      "grad_norm": 6.5,
+      "learning_rate": 3.8000000000000005e-06,
+      "loss": 0.6426264762878418,
+      "step": 20
+    },
+    {
+      "epoch": 0.004576135453609427,
+      "grad_norm": 10.75,
+      "learning_rate": 7.800000000000002e-06,
+      "loss": 0.624267292022705,
+      "step": 40
+    },
+    {
+      "epoch": 0.00686420318041414,
+      "grad_norm": 10.875,
+      "learning_rate": 1.18e-05,
+      "loss": 0.5983096122741699,
+      "step": 60
+    },
+    {
+      "epoch": 0.009152270907218854,
+      "grad_norm": 5.25,
+      "learning_rate": 1.58e-05,
+      "loss": 0.5892175674438477,
+      "step": 80
+    },
+    {
+      "epoch": 0.011440338634023568,
+      "grad_norm": 6.28125,
+      "learning_rate": 1.98e-05,
+      "loss": 0.5490372180938721,
+      "step": 100
+    },
+    {
+      "epoch": 0.01372840636082828,
+      "grad_norm": 6.9375,
+      "learning_rate": 2.3800000000000003e-05,
+      "loss": 0.5201863765716552,
+      "step": 120
+    },
+    {
+      "epoch": 0.016016474087632994,
+      "grad_norm": 8.5,
+      "learning_rate": 2.78e-05,
+      "loss": 0.49105257987976075,
+      "step": 140
+    },
+    {
+      "epoch": 0.01830454181443771,
+      "grad_norm": 7.25,
+      "learning_rate": 3.180000000000001e-05,
+      "loss": 0.5563832283020019,
+      "step": 160
+    },
+    {
+      "epoch": 0.02059260954124242,
+      "grad_norm": 7.40625,
+      "learning_rate": 3.58e-05,
+      "loss": 0.5139012336730957,
+      "step": 180
+    },
+    {
+      "epoch": 0.022880677268047135,
+      "grad_norm": 6.40625,
+      "learning_rate": 3.9800000000000005e-05,
+      "loss": 0.5116944313049316,
+      "step": 200
+    },
+    {
+      "epoch": 0.025168744994851847,
+      "grad_norm": 6.59375,
+      "learning_rate": 3.99999473871251e-05,
+      "loss": 0.4983517646789551,
+      "step": 220
+    },
+    {
+      "epoch": 0.02745681272165656,
+      "grad_norm": 7.5625,
+      "learning_rate": 3.999977832667593e-05,
+      "loss": 0.5274768352508545,
+      "step": 240
+    },
+    {
+      "epoch": 0.029744880448461273,
+      "grad_norm": 7.40625,
+      "learning_rate": 3.999949267389598e-05,
+      "loss": 0.5368683338165283,
+      "step": 260
+    },
+    {
+      "epoch": 0.03203294817526599,
+      "grad_norm": 6.53125,
+      "learning_rate": 3.999909043045049e-05,
+      "loss": 0.5036589622497558,
+      "step": 280
+    },
+    {
+      "epoch": 0.0343210159020707,
+      "grad_norm": 6.5,
+      "learning_rate": 3.9998571598684426e-05,
+      "loss": 0.5346245288848877,
+      "step": 300
+    },
+    {
+      "epoch": 0.03660908362887542,
+      "grad_norm": 6.78125,
+      "learning_rate": 3.9997936181622414e-05,
+      "loss": 0.5199912071228028,
+      "step": 320
+    },
+    {
+      "epoch": 0.03889715135568013,
+      "grad_norm": 5.9375,
+      "learning_rate": 3.9997184182968725e-05,
+      "loss": 0.49320483207702637,
+      "step": 340
+    },
+    {
+      "epoch": 0.04118521908248484,
+      "grad_norm": 7.15625,
+      "learning_rate": 3.9996315607107277e-05,
+      "loss": 0.47286419868469237,
+      "step": 360
+    },
+    {
+      "epoch": 0.04347328680928955,
+      "grad_norm": 7.84375,
+      "learning_rate": 3.999533045910159e-05,
+      "loss": 0.5770133018493653,
+      "step": 380
+    },
+    {
+      "epoch": 0.04576135453609427,
+      "grad_norm": 8.3125,
+      "learning_rate": 3.9994228744694766e-05,
+      "loss": 0.49772257804870607,
+      "step": 400
+    },
+    {
+      "epoch": 0.04804942226289898,
+      "grad_norm": 6.75,
+      "learning_rate": 3.9993010470309435e-05,
+      "loss": 0.4916713714599609,
+      "step": 420
+    },
+    {
+      "epoch": 0.05033748998970369,
+      "grad_norm": 7.65625,
+      "learning_rate": 3.999167564304776e-05,
+      "loss": 0.5373524188995361,
+      "step": 440
+    },
+    {
+      "epoch": 0.05262555771650841,
+      "grad_norm": 6.875,
+      "learning_rate": 3.999022427069135e-05,
+      "loss": 0.49773292541503905,
+      "step": 460
+    },
+    {
+      "epoch": 0.05491362544331312,
+      "grad_norm": 6.96875,
+      "learning_rate": 3.9988656361701254e-05,
+      "loss": 0.533263874053955,
+      "step": 480
+    },
+    {
+      "epoch": 0.057201693170117834,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.998697192521788e-05,
+      "loss": 0.5005961418151855,
+      "step": 500
+    },
+    {
+      "epoch": 0.057201693170117834,
+      "eval_loss": 0.49823397397994995,
+      "eval_runtime": 30.2696,
+      "eval_samples_per_second": 188.605,
+      "eval_steps_per_second": 5.914,
+      "step": 500
+    },
+    {
+      "epoch": 0.059489760896922546,
+      "grad_norm": 7.625,
+      "learning_rate": 3.998517097106095e-05,
+      "loss": 0.4923041820526123,
+      "step": 520
+    },
+    {
+      "epoch": 0.061777828623727264,
+      "grad_norm": 6.28125,
+      "learning_rate": 3.9983253509729444e-05,
+      "loss": 0.4844370365142822,
+      "step": 540
+    },
+    {
+      "epoch": 0.06406589635053198,
+      "grad_norm": 6.59375,
+      "learning_rate": 3.998121955240157e-05,
+      "loss": 0.47135009765625,
+      "step": 560
+    },
+    {
+      "epoch": 0.0663539640773367,
+      "grad_norm": 6.0625,
+      "learning_rate": 3.997906911093464e-05,
+      "loss": 0.48143815994262695,
+      "step": 580
+    },
+    {
+      "epoch": 0.0686420318041414,
+      "grad_norm": 6.84375,
+      "learning_rate": 3.997680219786504e-05,
+      "loss": 0.4821803569793701,
+      "step": 600
+    },
+    {
+      "epoch": 0.07093009953094612,
+      "grad_norm": 6.375,
+      "learning_rate": 3.997441882640815e-05,
+      "loss": 0.48928041458129884,
+      "step": 620
+    },
+    {
+      "epoch": 0.07321816725775084,
+      "grad_norm": 6.375,
+      "learning_rate": 3.9971919010458276e-05,
+      "loss": 0.5046079158782959,
+      "step": 640
+    },
+    {
+      "epoch": 0.07550623498455554,
+      "grad_norm": 6.46875,
+      "learning_rate": 3.9969302764588536e-05,
+      "loss": 0.4855530261993408,
+      "step": 660
+    },
+    {
+      "epoch": 0.07779430271136026,
+      "grad_norm": 5.46875,
+      "learning_rate": 3.996657010405082e-05,
+      "loss": 0.48481173515319825,
+      "step": 680
+    },
+    {
+      "epoch": 0.08008237043816498,
+      "grad_norm": 6.15625,
+      "learning_rate": 3.9963721044775655e-05,
+      "loss": 0.49315676689147947,
+      "step": 700
+    },
+    {
+      "epoch": 0.08237043816496968,
+      "grad_norm": 6.5,
+      "learning_rate": 3.9960755603372165e-05,
+      "loss": 0.47769804000854493,
+      "step": 720
+    },
+    {
+      "epoch": 0.0846585058917744,
+      "grad_norm": 7.375,
+      "learning_rate": 3.995767379712791e-05,
+      "loss": 0.4881394863128662,
+      "step": 740
+    },
+    {
+      "epoch": 0.0869465736185791,
+      "grad_norm": 82.0,
+      "learning_rate": 3.995447564400884e-05,
+      "loss": 0.5334478378295898,
+      "step": 760
+    },
+    {
+      "epoch": 0.08923464134538382,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.9951161162659184e-05,
+      "loss": 0.4679908275604248,
+      "step": 780
+    },
+    {
+      "epoch": 0.09152270907218854,
+      "grad_norm": 6.0625,
+      "learning_rate": 3.99477303724013e-05,
+      "loss": 0.5155776023864747,
+      "step": 800
+    },
+    {
+      "epoch": 0.09381077679899325,
+      "grad_norm": 7.5,
+      "learning_rate": 3.9944183293235606e-05,
+      "loss": 0.49847941398620604,
+      "step": 820
+    },
+    {
+      "epoch": 0.09609884452579796,
+      "grad_norm": 5.96875,
+      "learning_rate": 3.9940519945840425e-05,
+      "loss": 0.46823701858520506,
+      "step": 840
+    },
+    {
+      "epoch": 0.09838691225260268,
+      "grad_norm": 8.25,
+      "learning_rate": 3.993674035157193e-05,
+      "loss": 0.46818861961364744,
+      "step": 860
+    },
+    {
+      "epoch": 0.10067497997940739,
+      "grad_norm": 6.40625,
+      "learning_rate": 3.993284453246394e-05,
+      "loss": 0.4888922214508057,
+      "step": 880
+    },
+    {
+      "epoch": 0.1029630477062121,
+      "grad_norm": 6.71875,
+      "learning_rate": 3.992883251122783e-05,
+      "loss": 0.47359728813171387,
+      "step": 900
+    },
+    {
+      "epoch": 0.10525111543301682,
+      "grad_norm": 9.4375,
+      "learning_rate": 3.992470431125241e-05,
+      "loss": 0.4473433494567871,
+      "step": 920
+    },
+    {
+      "epoch": 0.10753918315982153,
+      "grad_norm": 6.9375,
+      "learning_rate": 3.9920459956603774e-05,
+      "loss": 0.45462775230407715,
+      "step": 940
+    },
+    {
+      "epoch": 0.10982725088662625,
+      "grad_norm": 7.21875,
+      "learning_rate": 3.9916099472025156e-05,
+      "loss": 0.4780879497528076,
+      "step": 960
+    },
+    {
+      "epoch": 0.11211531861343096,
+      "grad_norm": 6.71875,
+      "learning_rate": 3.991162288293679e-05,
+      "loss": 0.4894602298736572,
+      "step": 980
+    },
+    {
+      "epoch": 0.11440338634023567,
+      "grad_norm": 6.84375,
+      "learning_rate": 3.990703021543576e-05,
+      "loss": 0.485611629486084,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11440338634023567,
+      "eval_loss": 0.46591177582740784,
+      "eval_runtime": 30.1701,
+      "eval_samples_per_second": 189.227,
+      "eval_steps_per_second": 5.933,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11669145406704039,
+      "grad_norm": 5.625,
+      "learning_rate": 3.990232149629585e-05,
+      "loss": 0.4505727291107178,
+      "step": 1020
+    },
+    {
+      "epoch": 0.11897952179384509,
+      "grad_norm": 7.75,
+      "learning_rate": 3.98974967529674e-05,
+      "loss": 0.49631414413452146,
+      "step": 1040
+    },
+    {
+      "epoch": 0.12126758952064981,
+      "grad_norm": 6.34375,
+      "learning_rate": 3.9892556013577116e-05,
+      "loss": 0.44492282867431643,
+      "step": 1060
+    },
+    {
+      "epoch": 0.12355565724745453,
+      "grad_norm": 5.9375,
+      "learning_rate": 3.988749930692794e-05,
+      "loss": 0.4701989650726318,
+      "step": 1080
+    },
+    {
+      "epoch": 0.12584372497425925,
+      "grad_norm": 6.34375,
+      "learning_rate": 3.9882326662498865e-05,
+      "loss": 0.46944456100463866,
+      "step": 1100
+    },
+    {
+      "epoch": 0.12813179270106395,
+      "grad_norm": 8.4375,
+      "learning_rate": 3.987703811044474e-05,
+      "loss": 0.4518393039703369,
+      "step": 1120
+    },
+    {
+      "epoch": 0.13041986042786866,
+      "grad_norm": 6.375,
+      "learning_rate": 3.987163368159616e-05,
+      "loss": 0.46532793045043946,
+      "step": 1140
+    },
+    {
+      "epoch": 0.1327079281546734,
+      "grad_norm": 6.6875,
+      "learning_rate": 3.9866113407459206e-05,
+      "loss": 0.46168131828308107,
+      "step": 1160
+    },
+    {
+      "epoch": 0.1349959958814781,
+      "grad_norm": 5.5625,
+      "learning_rate": 3.9860477320215316e-05,
+      "loss": 0.47213287353515626,
+      "step": 1180
+    },
+    {
+      "epoch": 0.1372840636082828,
+      "grad_norm": 7.15625,
+      "learning_rate": 3.985472545272109e-05,
+      "loss": 0.44578351974487307,
+      "step": 1200
+    },
+    {
+      "epoch": 0.13957213133508753,
+      "grad_norm": 6.46875,
+      "learning_rate": 3.984885783850808e-05,
+      "loss": 0.4133923530578613,
+      "step": 1220
+    },
+    {
+      "epoch": 0.14186019906189223,
+      "grad_norm": 7.0,
+      "learning_rate": 3.98428745117826e-05,
+      "loss": 0.4428842067718506,
+      "step": 1240
+    },
+    {
+      "epoch": 0.14414826678869694,
+      "grad_norm": 6.5625,
+      "learning_rate": 3.9836775507425546e-05,
+      "loss": 0.4295872688293457,
+      "step": 1260
+    },
+    {
+      "epoch": 0.14643633451550167,
+      "grad_norm": 6.875,
+      "learning_rate": 3.9830560860992154e-05,
+      "loss": 0.46291403770446776,
+      "step": 1280
+    },
+    {
+      "epoch": 0.14872440224230637,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.982423060871185e-05,
+      "loss": 0.4664064884185791,
+      "step": 1300
+    },
+    {
+      "epoch": 0.15101246996911108,
+      "grad_norm": 6.375,
+      "learning_rate": 3.9817784787487974e-05,
+      "loss": 0.47367167472839355,
+      "step": 1320
+    },
+    {
+      "epoch": 0.1533005376959158,
+      "grad_norm": 7.09375,
+      "learning_rate": 3.9811223434897614e-05,
+      "loss": 0.4251996040344238,
+      "step": 1340
+    },
+    {
+      "epoch": 0.15558860542272052,
+      "grad_norm": 7.0,
+      "learning_rate": 3.980454658919136e-05,
+      "loss": 0.4373781681060791,
+      "step": 1360
+    },
+    {
+      "epoch": 0.15787667314952522,
+      "grad_norm": 6.03125,
+      "learning_rate": 3.979775428929309e-05,
+      "loss": 0.43296031951904296,
+      "step": 1380
+    },
+    {
+      "epoch": 0.16016474087632995,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.979084657479976e-05,
+      "loss": 0.4778231143951416,
+      "step": 1400
+    },
+    {
+      "epoch": 0.16245280860313466,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.9783823485981135e-05,
+      "loss": 0.4472900390625,
+      "step": 1420
+    },
+    {
+      "epoch": 0.16474087632993936,
+      "grad_norm": 5.6875,
+      "learning_rate": 3.977668506377958e-05,
+      "loss": 0.47884697914123536,
+      "step": 1440
+    },
+    {
+      "epoch": 0.16702894405674407,
+      "grad_norm": 7.1875,
+      "learning_rate": 3.976943134980982e-05,
+      "loss": 0.4422747611999512,
+      "step": 1460
+    },
+    {
+      "epoch": 0.1693170117835488,
+      "grad_norm": 5.21875,
+      "learning_rate": 3.97620623863587e-05,
+      "loss": 0.42993454933166503,
+      "step": 1480
+    },
+    {
+      "epoch": 0.1716050795103535,
+      "grad_norm": 6.28125,
+      "learning_rate": 3.9754578216384934e-05,
+      "loss": 0.4534616470336914,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1716050795103535,
+      "eval_loss": 0.437215119600296,
+      "eval_runtime": 30.2268,
+      "eval_samples_per_second": 188.872,
+      "eval_steps_per_second": 5.922,
+      "step": 1500
+    },
+    {
+      "epoch": 0.1738931472371582,
+      "grad_norm": 6.15625,
+      "learning_rate": 3.974697888351883e-05,
+      "loss": 0.41881208419799804,
+      "step": 1520
+    },
+    {
+      "epoch": 0.17618121496396294,
+      "grad_norm": 4.9375,
+      "learning_rate": 3.973926443206208e-05,
+      "loss": 0.43660764694213866,
+      "step": 1540
+    },
+    {
+      "epoch": 0.17846928269076764,
+      "grad_norm": 6.9375,
+      "learning_rate": 3.973143490698749e-05,
+      "loss": 0.4803757190704346,
+      "step": 1560
+    },
+    {
+      "epoch": 0.18075735041757235,
+      "grad_norm": 6.4375,
+      "learning_rate": 3.972349035393868e-05,
+      "loss": 0.43456220626831055,
+      "step": 1580
+    },
+    {
+      "epoch": 0.18304541814437708,
+      "grad_norm": 7.5625,
+      "learning_rate": 3.971543081922986e-05,
+      "loss": 0.4419902801513672,
+      "step": 1600
+    },
+    {
+      "epoch": 0.18533348587118179,
+      "grad_norm": 6.25,
+      "learning_rate": 3.970725634984556e-05,
+      "loss": 0.44153766632080077,
+      "step": 1620
+    },
+    {
+      "epoch": 0.1876215535979865,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.969896699344032e-05,
+      "loss": 0.4365544319152832,
+      "step": 1640
+    },
+    {
+      "epoch": 0.18990962132479122,
+      "grad_norm": 7.125,
+      "learning_rate": 3.969056279833845e-05,
+      "loss": 0.4264547348022461,
+      "step": 1660
+    },
+    {
+      "epoch": 0.19219768905159593,
+      "grad_norm": 5.40625,
+      "learning_rate": 3.968204381353373e-05,
+      "loss": 0.45740342140197754,
+      "step": 1680
+    },
+    {
+      "epoch": 0.19448575677840063,
+      "grad_norm": 7.46875,
+      "learning_rate": 3.9673410088689126e-05,
+      "loss": 0.44994053840637205,
+      "step": 1700
+    },
+    {
+      "epoch": 0.19677382450520536,
+      "grad_norm": 5.3125,
+      "learning_rate": 3.966466167413648e-05,
+      "loss": 0.40054097175598147,
+      "step": 1720
+    },
+    {
+      "epoch": 0.19906189223201007,
+      "grad_norm": 5.96875,
+      "learning_rate": 3.965579862087629e-05,
+      "loss": 0.4518143177032471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.20134995995881477,
+      "grad_norm": 6.4375,
+      "learning_rate": 3.964682098057731e-05,
+      "loss": 0.40816030502319334,
+      "step": 1760
+    },
+    {
+      "epoch": 0.2036380276856195,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.963772880557633e-05,
+      "loss": 0.43303966522216797,
+      "step": 1780
+    },
+    {
+      "epoch": 0.2059260954124242,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.9628522148877826e-05,
+      "loss": 0.4031963348388672,
+      "step": 1800
+    },
+    {
+      "epoch": 0.2082141631392289,
+      "grad_norm": 6.375,
+      "learning_rate": 3.961920106415368e-05,
+      "loss": 0.4320640563964844,
+      "step": 1820
+    },
+    {
+      "epoch": 0.21050223086603365,
+      "grad_norm": 9.375,
+      "learning_rate": 3.960976560574283e-05,
+      "loss": 0.4670876026153564,
+      "step": 1840
+    },
+    {
+      "epoch": 0.21279029859283835,
+      "grad_norm": 6.28125,
+      "learning_rate": 3.9600215828651e-05,
+      "loss": 0.41726031303405764,
+      "step": 1860
+    },
+    {
+      "epoch": 0.21507836631964306,
+      "grad_norm": 5.0625,
+      "learning_rate": 3.959055178855034e-05,
+      "loss": 0.4229582786560059,
+      "step": 1880
+    },
+    {
+      "epoch": 0.2173664340464478,
+      "grad_norm": 5.5,
+      "learning_rate": 3.9580773541779124e-05,
+      "loss": 0.45138072967529297,
+      "step": 1900
+    },
+    {
+      "epoch": 0.2196545017732525,
+      "grad_norm": 6.03125,
+      "learning_rate": 3.957088114534142e-05,
+      "loss": 0.4322213649749756,
+      "step": 1920
+    },
+    {
+      "epoch": 0.2219425695000572,
+      "grad_norm": 7.5,
+      "learning_rate": 3.956087465690674e-05,
+      "loss": 0.44690213203430174,
+      "step": 1940
+    },
+    {
+      "epoch": 0.22423063722686193,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.9550754134809713e-05,
+      "loss": 0.4322388172149658,
+      "step": 1960
+    },
+    {
+      "epoch": 0.22651870495366663,
+      "grad_norm": 6.90625,
+      "learning_rate": 3.954051963804977e-05,
+      "loss": 0.44041857719421384,
+      "step": 1980
+    },
+    {
+      "epoch": 0.22880677268047134,
+      "grad_norm": 5.5,
+      "learning_rate": 3.953017122629075e-05,
+      "loss": 0.3615637540817261,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22880677268047134,
+      "eval_loss": 0.4122261703014374,
+      "eval_runtime": 30.2175,
+      "eval_samples_per_second": 188.93,
+      "eval_steps_per_second": 5.924,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23109484040727604,
+      "grad_norm": 5.78125,
+      "learning_rate": 3.951970895986061e-05,
+      "loss": 0.4221320152282715,
+      "step": 2020
+    },
+    {
+      "epoch": 0.23338290813408077,
+      "grad_norm": 5.09375,
+      "learning_rate": 3.950913289975101e-05,
+      "loss": 0.39341785907745364,
+      "step": 2040
+    },
+    {
+      "epoch": 0.23567097586088548,
+      "grad_norm": 8.625,
+      "learning_rate": 3.949844310761702e-05,
+      "loss": 0.4574568748474121,
+      "step": 2060
+    },
+    {
+      "epoch": 0.23795904358769018,
+      "grad_norm": 6.84375,
+      "learning_rate": 3.948763964577672e-05,
+      "loss": 0.4047089576721191,
+      "step": 2080
+    },
+    {
+      "epoch": 0.24024711131449492,
+      "grad_norm": 5.0,
+      "learning_rate": 3.947672257721084e-05,
+      "loss": 0.4058550834655762,
+      "step": 2100
+    },
+    {
+      "epoch": 0.24253517904129962,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.9465691965562414e-05,
+      "loss": 0.4057643890380859,
+      "step": 2120
+    },
+    {
+      "epoch": 0.24482324676810432,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.945454787513639e-05,
+      "loss": 0.3887258291244507,
+      "step": 2140
+    },
+    {
+      "epoch": 0.24711131449490906,
+      "grad_norm": 7.9375,
+      "learning_rate": 3.944329037089927e-05,
+      "loss": 0.4331155300140381,
+      "step": 2160
+    },
+    {
+      "epoch": 0.24939938222171376,
+      "grad_norm": 5.46875,
+      "learning_rate": 3.9431919518478696e-05,
+      "loss": 0.3846742630004883,
+      "step": 2180
+    },
+    {
+      "epoch": 0.2516874499485185,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.942043538416313e-05,
+      "loss": 0.41670851707458495,
+      "step": 2200
+    },
+    {
+      "epoch": 0.25397551767532317,
+      "grad_norm": 6.21875,
+      "learning_rate": 3.94088380349014e-05,
+      "loss": 0.4008606433868408,
+      "step": 2220
+    },
+    {
+      "epoch": 0.2562635854021279,
+      "grad_norm": 6.34375,
+      "learning_rate": 3.939712753830236e-05,
+      "loss": 0.4295452117919922,
+      "step": 2240
+    },
+    {
+      "epoch": 0.25855165312893263,
+      "grad_norm": 6.625,
+      "learning_rate": 3.938530396263447e-05,
+      "loss": 0.4197634220123291,
+      "step": 2260
+    },
+    {
+      "epoch": 0.2608397208557373,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.937336737682542e-05,
+      "loss": 0.39091153144836427,
+      "step": 2280
+    },
+    {
+      "epoch": 0.26312778858254204,
+      "grad_norm": 7.0625,
+      "learning_rate": 3.9361317850461674e-05,
+      "loss": 0.4076122283935547,
+      "step": 2300
+    },
+    {
+      "epoch": 0.2654158563093468,
+      "grad_norm": 5.3125,
+      "learning_rate": 3.934915545378815e-05,
+      "loss": 0.41081724166870115,
+      "step": 2320
+    },
+    {
+      "epoch": 0.26770392403615145,
+      "grad_norm": 6.0,
+      "learning_rate": 3.933688025770773e-05,
+      "loss": 0.4181351661682129,
+      "step": 2340
+    },
+    {
+      "epoch": 0.2699919917629562,
+      "grad_norm": 6.625,
+      "learning_rate": 3.93244923337809e-05,
+      "loss": 0.3718965291976929,
+      "step": 2360
+    },
+    {
+      "epoch": 0.2722800594897609,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.93119917542253e-05,
+      "loss": 0.36525521278381345,
+      "step": 2380
+    },
+    {
+      "epoch": 0.2745681272165656,
+      "grad_norm": 7.3125,
+      "learning_rate": 3.9299378591915336e-05,
+      "loss": 0.35721213817596437,
+      "step": 2400
+    },
+    {
+      "epoch": 0.2768561949433703,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.928665292038171e-05,
+      "loss": 0.381751275062561,
+      "step": 2420
+    },
+    {
+      "epoch": 0.27914426267017506,
+      "grad_norm": 7.46875,
+      "learning_rate": 3.9273814813811036e-05,
+      "loss": 0.3843672513961792,
+      "step": 2440
+    },
+    {
+      "epoch": 0.28143233039697974,
+      "grad_norm": 7.0,
+      "learning_rate": 3.9260864347045374e-05,
+      "loss": 0.40488443374633787,
+      "step": 2460
+    },
+    {
+      "epoch": 0.28372039812378447,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.924780159558183e-05,
+      "loss": 0.39438447952270506,
+      "step": 2480
+    },
+    {
+      "epoch": 0.2860084658505892,
+      "grad_norm": 6.1875,
+      "learning_rate": 3.923462663557206e-05,
+      "loss": 0.3016136884689331,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2860084658505892,
+      "eval_loss": 0.38438963890075684,
+      "eval_runtime": 30.2056,
+      "eval_samples_per_second": 189.005,
+      "eval_steps_per_second": 5.926,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2882965335773939,
+      "grad_norm": 5.96875,
+      "learning_rate": 3.92213395438219e-05,
+      "loss": 0.4038406848907471,
+      "step": 2520
+    },
+    {
+      "epoch": 0.2905846013041986,
+      "grad_norm": 4.5,
+      "learning_rate": 3.9207940397790854e-05,
+      "loss": 0.3989222764968872,
+      "step": 2540
+    },
+    {
+      "epoch": 0.29287266903100334,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.919442927559166e-05,
+      "loss": 0.38008391857147217,
+      "step": 2560
+    },
+    {
+      "epoch": 0.295160736757808,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.918080625598986e-05,
+      "loss": 0.3941387891769409,
+      "step": 2580
+    },
+    {
+      "epoch": 0.29744880448461275,
+      "grad_norm": 4.8125,
+      "learning_rate": 3.9167071418403316e-05,
+      "loss": 0.36676874160766604,
+      "step": 2600
+    },
+    {
+      "epoch": 0.2997368722114175,
+      "grad_norm": 4.9375,
+      "learning_rate": 3.9153224842901746e-05,
+      "loss": 0.3845605134963989,
+      "step": 2620
+    },
+    {
+      "epoch": 0.30202493993822216,
+      "grad_norm": 6.40625,
+      "learning_rate": 3.9139266610206276e-05,
+      "loss": 0.3800462245941162,
+      "step": 2640
+    },
+    {
+      "epoch": 0.3043130076650269,
+      "grad_norm": 7.03125,
+      "learning_rate": 3.9125196801688955e-05,
+      "loss": 0.3611100912094116,
+      "step": 2660
+    },
+    {
+      "epoch": 0.3066010753918316,
+      "grad_norm": 6.625,
+      "learning_rate": 3.911101549937227e-05,
+      "loss": 0.3620962142944336,
+      "step": 2680
+    },
+    {
+      "epoch": 0.3088891431186363,
+      "grad_norm": 7.09375,
+      "learning_rate": 3.9096722785928703e-05,
+      "loss": 0.3901801586151123,
+      "step": 2700
+    },
+    {
+      "epoch": 0.31117721084544103,
+      "grad_norm": 6.21875,
+      "learning_rate": 3.908231874468021e-05,
+      "loss": 0.34701924324035643,
+      "step": 2720
+    },
+    {
+      "epoch": 0.31346527857224576,
+      "grad_norm": 6.1875,
+      "learning_rate": 3.906780345959776e-05,
+      "loss": 0.4228227138519287,
+      "step": 2740
+    },
+    {
+      "epoch": 0.31575334629905044,
+      "grad_norm": 4.25,
+      "learning_rate": 3.9053177015300835e-05,
+      "loss": 0.43420991897583006,
+      "step": 2760
+    },
+    {
+      "epoch": 0.3180414140258552,
+      "grad_norm": 5.5,
+      "learning_rate": 3.903843949705695e-05,
+      "loss": 0.35564661026000977,
+      "step": 2780
+    },
+    {
+      "epoch": 0.3203294817526599,
+      "grad_norm": 6.0,
+      "learning_rate": 3.902359099078112e-05,
+      "loss": 0.34250402450561523,
+      "step": 2800
+    },
+    {
+      "epoch": 0.3226175494794646,
+      "grad_norm": 6.59375,
+      "learning_rate": 3.900863158303542e-05,
+      "loss": 0.38572776317596436,
+      "step": 2820
+    },
+    {
+      "epoch": 0.3249056172062693,
+      "grad_norm": 4.15625,
+      "learning_rate": 3.899356136102842e-05,
+      "loss": 0.41805424690246584,
+      "step": 2840
+    },
+    {
+      "epoch": 0.327193684933074,
+      "grad_norm": 5.625,
+      "learning_rate": 3.897838041261471e-05,
+      "loss": 0.3574146509170532,
+      "step": 2860
+    },
+    {
+      "epoch": 0.3294817526598787,
+      "grad_norm": 12.375,
+      "learning_rate": 3.8963088826294376e-05,
+      "loss": 0.3900667428970337,
+      "step": 2880
+    },
+    {
+      "epoch": 0.33176982038668346,
+      "grad_norm": 7.3125,
+      "learning_rate": 3.894768669121249e-05,
+      "loss": 0.4149120807647705,
+      "step": 2900
+    },
+    {
+      "epoch": 0.33405788811348813,
+      "grad_norm": 6.625,
+      "learning_rate": 3.89321740971586e-05,
+      "loss": 0.3962269306182861,
+      "step": 2920
+    },
+    {
+      "epoch": 0.33634595584029287,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.8916551134566165e-05,
+      "loss": 0.36723995208740234,
+      "step": 2940
+    },
+    {
+      "epoch": 0.3386340235670976,
+      "grad_norm": 4.65625,
+      "learning_rate": 3.890081789451209e-05,
+      "loss": 0.34161853790283203,
+      "step": 2960
+    },
+    {
+      "epoch": 0.3409220912939023,
+      "grad_norm": 5.75,
+      "learning_rate": 3.888497446871615e-05,
+      "loss": 0.3627434968948364,
+      "step": 2980
+    },
+    {
+      "epoch": 0.343210159020707,
+      "grad_norm": 5.78125,
+      "learning_rate": 3.886902094954045e-05,
+      "loss": 0.3574451684951782,
+      "step": 3000
+    },
+    {
+      "epoch": 0.343210159020707,
+      "eval_loss": 0.35939544439315796,
+      "eval_runtime": 30.2418,
+      "eval_samples_per_second": 188.779,
+      "eval_steps_per_second": 5.919,
+      "step": 3000
+    },
+    {
+      "epoch": 0.34549822674751174,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.885295742998893e-05,
+      "loss": 0.36277873516082765,
+      "step": 3020
+    },
+    {
+      "epoch": 0.3477862944743164,
+      "grad_norm": 5.875,
+      "learning_rate": 3.883678400370679e-05,
+      "loss": 0.35874600410461427,
+      "step": 3040
+    },
+    {
+      "epoch": 0.35007436220112115,
+      "grad_norm": 6.71875,
+      "learning_rate": 3.882050076497994e-05,
+      "loss": 0.381546950340271,
+      "step": 3060
+    },
+    {
+      "epoch": 0.3523624299279259,
+      "grad_norm": 6.4375,
+      "learning_rate": 3.8804107808734484e-05,
+      "loss": 0.3525323629379272,
+      "step": 3080
+    },
+    {
+      "epoch": 0.35465049765473056,
+      "grad_norm": 5.65625,
+      "learning_rate": 3.878760523053612e-05,
+      "loss": 0.33940017223358154,
+      "step": 3100
+    },
+    {
+      "epoch": 0.3569385653815353,
+      "grad_norm": 8.125,
+      "learning_rate": 3.877099312658961e-05,
+      "loss": 0.36605474948883054,
+      "step": 3120
+    },
+    {
+      "epoch": 0.35922663310834,
+      "grad_norm": 4.875,
+      "learning_rate": 3.875427159373824e-05,
+      "loss": 0.3694122552871704,
+      "step": 3140
+    },
+    {
+      "epoch": 0.3615147008351447,
+      "grad_norm": 6.375,
+      "learning_rate": 3.87374407294632e-05,
+      "loss": 0.3674943923950195,
+      "step": 3160
+    },
+    {
+      "epoch": 0.36380276856194943,
+      "grad_norm": 6.71875,
+      "learning_rate": 3.8720500631883065e-05,
+      "loss": 0.3545408010482788,
+      "step": 3180
+    },
+    {
+      "epoch": 0.36609083628875416,
+      "grad_norm": 4.875,
+      "learning_rate": 3.8703451399753214e-05,
+      "loss": 0.40555591583251954,
+      "step": 3200
+    },
+    {
+      "epoch": 0.36837890401555884,
+      "grad_norm": 6.28125,
+      "learning_rate": 3.868629313246522e-05,
+      "loss": 0.3536318302154541,
+      "step": 3220
+    },
+    {
+      "epoch": 0.37066697174236357,
+      "grad_norm": 5.25,
+      "learning_rate": 3.866902593004632e-05,
+      "loss": 0.3295443058013916,
+      "step": 3240
+    },
+    {
+      "epoch": 0.3729550394691683,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.86516498931588e-05,
+      "loss": 0.3561116933822632,
+      "step": 3260
+    },
+    {
+      "epoch": 0.375243107195973,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.863416512309941e-05,
+      "loss": 0.3372109651565552,
+      "step": 3280
+    },
+    {
+      "epoch": 0.3775311749227777,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.861657172179877e-05,
+      "loss": 0.33488657474517824,
+      "step": 3300
+    },
+    {
+      "epoch": 0.37981924264958244,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.859886979182083e-05,
+      "loss": 0.38349094390869143,
+      "step": 3320
+    },
+    {
+      "epoch": 0.3821073103763871,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.858105943636218e-05,
+      "loss": 0.35571937561035155,
+      "step": 3340
+    },
+    {
+      "epoch": 0.38439537810319185,
+      "grad_norm": 4.3125,
+      "learning_rate": 3.8563140759251514e-05,
+      "loss": 0.3834290742874146,
+      "step": 3360
+    },
+    {
+      "epoch": 0.3866834458299966,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.8545113864949e-05,
+      "loss": 0.363328218460083,
+      "step": 3380
+    },
+    {
+      "epoch": 0.38897151355680126,
+      "grad_norm": 6.71875,
+      "learning_rate": 3.85269788585457e-05,
+      "loss": 0.37751829624176025,
+      "step": 3400
+    },
+    {
+      "epoch": 0.391259581283606,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.8508735845762915e-05,
+      "loss": 0.3730382204055786,
+      "step": 3420
+    },
+    {
+      "epoch": 0.3935476490104107,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.849038493295158e-05,
+      "loss": 0.35955142974853516,
+      "step": 3440
+    },
+    {
+      "epoch": 0.3958357167372154,
+      "grad_norm": 6.09375,
+      "learning_rate": 3.847192622709168e-05,
+      "loss": 0.33784122467041017,
+      "step": 3460
+    },
+    {
+      "epoch": 0.39812378446402014,
+      "grad_norm": 5.28125,
+      "learning_rate": 3.8453359835791575e-05,
+      "loss": 0.3487513303756714,
+      "step": 3480
+    },
+    {
+      "epoch": 0.40041185219082487,
+      "grad_norm": 4.84375,
+      "learning_rate": 3.843468586728741e-05,
+      "loss": 0.3142927885055542,
+      "step": 3500
+    },
+    {
+      "epoch": 0.40041185219082487,
+      "eval_loss": 0.33844611048698425,
+      "eval_runtime": 30.0065,
+      "eval_samples_per_second": 190.259,
+      "eval_steps_per_second": 5.965,
+      "step": 3500
+    },
+    {
+      "epoch": 0.40269991991762955,
+      "grad_norm": 4.75,
+      "learning_rate": 3.8415904430442476e-05,
+      "loss": 0.36830241680145265,
+      "step": 3520
+    },
+    {
+      "epoch": 0.4049879876444343,
+      "grad_norm": 4.09375,
+      "learning_rate": 3.839701563474655e-05,
+      "loss": 0.34973118305206297,
+      "step": 3540
+    },
+    {
+      "epoch": 0.407276055371239,
+      "grad_norm": 5.90625,
+      "learning_rate": 3.837801959031528e-05,
+      "loss": 0.33515794277191163,
+      "step": 3560
+    },
+    {
+      "epoch": 0.4095641230980437,
+      "grad_norm": 6.03125,
+      "learning_rate": 3.8358916407889576e-05,
+      "loss": 0.3506049871444702,
+      "step": 3580
+    },
+    {
+      "epoch": 0.4118521908248484,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.833970619883488e-05,
+      "loss": 0.35467545986175536,
+      "step": 3600
+    },
+    {
+      "epoch": 0.41414025855165315,
+      "grad_norm": 4.75,
+      "learning_rate": 3.832038907514058e-05,
+      "loss": 0.3314668655395508,
+      "step": 3620
+    },
+    {
+      "epoch": 0.4164283262784578,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.8300965149419365e-05,
+      "loss": 0.3230182647705078,
+      "step": 3640
+    },
+    {
+      "epoch": 0.41871639400526256,
+      "grad_norm": 5.40625,
+      "learning_rate": 3.8281434534906526e-05,
+      "loss": 0.3343541622161865,
+      "step": 3660
+    },
+    {
+      "epoch": 0.4210044617320673,
+      "grad_norm": 6.84375,
+      "learning_rate": 3.826179734545931e-05,
+      "loss": 0.35220818519592284,
+      "step": 3680
+    },
+    {
+      "epoch": 0.42329252945887197,
+      "grad_norm": 5.71875,
+      "learning_rate": 3.824205369555627e-05,
+      "loss": 0.36062824726104736,
+      "step": 3700
+    },
+    {
+      "epoch": 0.4255805971856767,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.82222037002966e-05,
+      "loss": 0.33077096939086914,
+      "step": 3720
+    },
+    {
+      "epoch": 0.42786866491248143,
+      "grad_norm": 5.3125,
+      "learning_rate": 3.820224747539944e-05,
+      "loss": 0.3369954347610474,
+      "step": 3740
+    },
+    {
+      "epoch": 0.4301567326392861,
+      "grad_norm": 5.46875,
+      "learning_rate": 3.8182185137203204e-05,
+      "loss": 0.34046459197998047,
+      "step": 3760
+    },
+    {
+      "epoch": 0.43244480036609084,
+      "grad_norm": 5.59375,
+      "learning_rate": 3.816201680266494e-05,
+      "loss": 0.34078967571258545,
+      "step": 3780
+    },
+    {
+      "epoch": 0.4347328680928956,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.814174258935962e-05,
+      "loss": 0.30267925262451173,
+      "step": 3800
+    },
+    {
+      "epoch": 0.43702093581970025,
+      "grad_norm": 6.09375,
+      "learning_rate": 3.8121362615479415e-05,
+      "loss": 0.34900689125061035,
+      "step": 3820
+    },
+    {
+      "epoch": 0.439309003546505,
+      "grad_norm": 6.375,
+      "learning_rate": 3.81008769998331e-05,
+      "loss": 0.3361180067062378,
+      "step": 3840
+    },
+    {
+      "epoch": 0.4415970712733097,
+      "grad_norm": 5.21875,
+      "learning_rate": 3.8080285861845264e-05,
+      "loss": 0.39550442695617677,
+      "step": 3860
+    },
+    {
+      "epoch": 0.4438851390001144,
+      "grad_norm": 6.875,
+      "learning_rate": 3.805958932155568e-05,
+      "loss": 0.33666133880615234,
+      "step": 3880
+    },
+    {
+      "epoch": 0.4461732067269191,
+      "grad_norm": 4.8125,
+      "learning_rate": 3.803878749961859e-05,
+      "loss": 0.327386212348938,
+      "step": 3900
+    },
+    {
+      "epoch": 0.44846127445372386,
+      "grad_norm": 5.0,
+      "learning_rate": 3.801788051730197e-05,
+      "loss": 0.3226013660430908,
+      "step": 3920
+    },
+    {
+      "epoch": 0.45074934218052853,
+      "grad_norm": 5.46875,
+      "learning_rate": 3.799686849648687e-05,
+      "loss": 0.30485124588012696,
+      "step": 3940
+    },
+    {
+      "epoch": 0.45303740990733327,
+      "grad_norm": 5.21875,
+      "learning_rate": 3.797575155966667e-05,
+      "loss": 0.3843498229980469,
+      "step": 3960
+    },
+    {
+      "epoch": 0.45532547763413794,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.795452982994638e-05,
+      "loss": 0.338079833984375,
+      "step": 3980
+    },
+    {
+      "epoch": 0.4576135453609427,
+      "grad_norm": 5.9375,
+      "learning_rate": 3.79332034310419e-05,
+      "loss": 0.34974188804626466,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4576135453609427,
+      "eval_loss": 0.322843998670578,
+      "eval_runtime": 29.9966,
+      "eval_samples_per_second": 190.322,
+      "eval_steps_per_second": 5.967,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4599016130877474,
+      "grad_norm": 5.9375,
+      "learning_rate": 3.791177248727937e-05,
+      "loss": 0.32091717720031737,
+      "step": 4020
+    },
+    {
+      "epoch": 0.4621896808145521,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.7890237123594324e-05,
+      "loss": 0.3131709098815918,
+      "step": 4040
+    },
+    {
+      "epoch": 0.4644777485413568,
+      "grad_norm": 7.8125,
+      "learning_rate": 3.786859746553108e-05,
+      "loss": 0.32413904666900634,
+      "step": 4060
+    },
+    {
+      "epoch": 0.46676581626816155,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.784685363924196e-05,
+      "loss": 0.31159143447875975,
+      "step": 4080
+    },
+    {
+      "epoch": 0.4690538839949662,
+      "grad_norm": 5.375,
+      "learning_rate": 3.7825005771486504e-05,
+      "loss": 0.29379317760467527,
+      "step": 4100
+    },
+    {
+      "epoch": 0.47134195172177096,
+      "grad_norm": 9.8125,
+      "learning_rate": 3.780305398963085e-05,
+      "loss": 0.35498270988464353,
+      "step": 4120
+    },
+    {
+      "epoch": 0.4736300194485757,
+      "grad_norm": 4.84375,
+      "learning_rate": 3.778099842164687e-05,
+      "loss": 0.32257239818572997,
+      "step": 4140
+    },
+    {
+      "epoch": 0.47591808717538037,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.7758839196111494e-05,
+      "loss": 0.3335160732269287,
+      "step": 4160
+    },
+    {
+      "epoch": 0.4782061549021851,
+      "grad_norm": 15.125,
+      "learning_rate": 3.7736576442205945e-05,
+      "loss": 0.31457839012145994,
+      "step": 4180
+    },
+    {
+      "epoch": 0.48049422262898983,
+      "grad_norm": 9.125,
+      "learning_rate": 3.7714210289714975e-05,
+      "loss": 0.3553635120391846,
+      "step": 4200
+    },
+    {
+      "epoch": 0.4827822903557945,
+      "grad_norm": 5.875,
+      "learning_rate": 3.7691740869026124e-05,
+      "loss": 0.3590611219406128,
+      "step": 4220
+    },
+    {
+      "epoch": 0.48507035808259924,
+      "grad_norm": 5.71875,
+      "learning_rate": 3.766916831112895e-05,
+      "loss": 0.31765313148498536,
+      "step": 4240
+    },
+    {
+      "epoch": 0.487358425809404,
+      "grad_norm": 5.75,
+      "learning_rate": 3.764649274761427e-05,
+      "loss": 0.3202390670776367,
+      "step": 4260
+    },
+    {
+      "epoch": 0.48964649353620865,
+      "grad_norm": 5.40625,
+      "learning_rate": 3.762371431067339e-05,
+      "loss": 0.328578519821167,
+      "step": 4280
+    },
+    {
+      "epoch": 0.4919345612630134,
+      "grad_norm": 4.375,
+      "learning_rate": 3.760083313309733e-05,
+      "loss": 0.3006050825119019,
+      "step": 4300
+    },
+    {
+      "epoch": 0.4942226289898181,
+      "grad_norm": 7.8125,
+      "learning_rate": 3.757784934827606e-05,
+      "loss": 0.33105781078338625,
+      "step": 4320
+    },
+    {
+      "epoch": 0.4965106967166228,
+      "grad_norm": 4.5,
+      "learning_rate": 3.755476309019773e-05,
+      "loss": 0.3076121091842651,
+      "step": 4340
+    },
+    {
+      "epoch": 0.4987987644434275,
+      "grad_norm": 5.0,
+      "learning_rate": 3.753157449344784e-05,
+      "loss": 0.2989222288131714,
+      "step": 4360
+    },
+    {
+      "epoch": 0.5010868321702322,
+      "grad_norm": 6.03125,
+      "learning_rate": 3.750828369320853e-05,
+      "loss": 0.3798956871032715,
+      "step": 4380
+    },
+    {
+      "epoch": 0.503374899897037,
+      "grad_norm": 4.84375,
+      "learning_rate": 3.7484890825257746e-05,
+      "loss": 0.3018073081970215,
+      "step": 4400
+    },
+    {
+      "epoch": 0.5056629676238417,
+      "grad_norm": 4.75,
+      "learning_rate": 3.746139602596844e-05,
+      "loss": 0.3374150037765503,
+      "step": 4420
+    },
+    {
+      "epoch": 0.5079510353506463,
+      "grad_norm": 5.875,
+      "learning_rate": 3.74377994323078e-05,
+      "loss": 0.3430293321609497,
+      "step": 4440
+    },
+    {
+      "epoch": 0.5102391030774511,
+      "grad_norm": 5.5625,
+      "learning_rate": 3.741410118183644e-05,
+      "loss": 0.32674498558044435,
+      "step": 4460
+    },
+    {
+      "epoch": 0.5125271708042558,
+      "grad_norm": 5.65625,
+      "learning_rate": 3.739030141270762e-05,
+      "loss": 0.30865979194641113,
+      "step": 4480
+    },
+    {
+      "epoch": 0.5148152385310605,
+      "grad_norm": 6.03125,
+      "learning_rate": 3.736640026366638e-05,
+      "loss": 0.30393574237823484,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5148152385310605,
+      "eval_loss": 0.3075600862503052,
+      "eval_runtime": 30.0781,
+      "eval_samples_per_second": 189.806,
+      "eval_steps_per_second": 5.951,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5171033062578653,
+      "grad_norm": 4.96875,
+      "learning_rate": 3.734239787404883e-05,
+      "loss": 0.314531946182251,
+      "step": 4520
+    },
+    {
+      "epoch": 0.51939137398467,
+      "grad_norm": 5.84375,
+      "learning_rate": 3.731829438378122e-05,
+      "loss": 0.3059818983078003,
+      "step": 4540
+    },
+    {
+      "epoch": 0.5216794417114746,
+      "grad_norm": 3.84375,
+      "learning_rate": 3.7294089933379224e-05,
+      "loss": 0.3077605485916138,
+      "step": 4560
+    },
+    {
+      "epoch": 0.5239675094382794,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.726978466394708e-05,
+      "loss": 0.2715317249298096,
+      "step": 4580
+    },
+    {
+      "epoch": 0.5262555771650841,
+      "grad_norm": 4.625,
+      "learning_rate": 3.7245378717176746e-05,
+      "loss": 0.2984918594360352,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5285436448918888,
+      "grad_norm": 5.75,
+      "learning_rate": 3.722087223534711e-05,
+      "loss": 0.30134124755859376,
+      "step": 4620
+    },
+    {
+      "epoch": 0.5308317126186936,
+      "grad_norm": 4.96875,
+      "learning_rate": 3.719626536132315e-05,
+      "loss": 0.325078558921814,
+      "step": 4640
+    },
+    {
+      "epoch": 0.5331197803454982,
+      "grad_norm": 4.3125,
+      "learning_rate": 3.7171558238555114e-05,
+      "loss": 0.3142669200897217,
+      "step": 4660
+    },
+    {
+      "epoch": 0.5354078480723029,
+      "grad_norm": 5.625,
+      "learning_rate": 3.714675101107761e-05,
+      "loss": 0.34218482971191405,
+      "step": 4680
+    },
+    {
+      "epoch": 0.5376959157991077,
+      "grad_norm": 5.78125,
+      "learning_rate": 3.71218438235089e-05,
+      "loss": 0.2848149299621582,
+      "step": 4700
+    },
+    {
+      "epoch": 0.5399839835259124,
+      "grad_norm": 6.375,
+      "learning_rate": 3.709683682104993e-05,
+      "loss": 0.33511455059051515,
+      "step": 4720
+    },
+    {
+      "epoch": 0.542272051252717,
+      "grad_norm": 5.125,
+      "learning_rate": 3.7071730149483556e-05,
+      "loss": 0.2954577922821045,
+      "step": 4740
+    },
+    {
+      "epoch": 0.5445601189795218,
+      "grad_norm": 4.75,
+      "learning_rate": 3.7046523955173665e-05,
+      "loss": 0.27104208469390867,
+      "step": 4760
+    },
+    {
+      "epoch": 0.5468481867063265,
+      "grad_norm": 4.75,
+      "learning_rate": 3.7021218385064335e-05,
+      "loss": 0.3379020690917969,
+      "step": 4780
+    },
+    {
+      "epoch": 0.5491362544331312,
+      "grad_norm": 5.4375,
+      "learning_rate": 3.699581358667897e-05,
+      "loss": 0.29814877510070803,
+      "step": 4800
+    },
+    {
+      "epoch": 0.551424322159936,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.697030970811945e-05,
+      "loss": 0.28858444690704343,
+      "step": 4820
+    },
+    {
+      "epoch": 0.5537123898867407,
+      "grad_norm": 4.625,
+      "learning_rate": 3.694470689806524e-05,
+      "loss": 0.3282477378845215,
+      "step": 4840
+    },
+    {
+      "epoch": 0.5560004576135453,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.6919005305772576e-05,
+      "loss": 0.33788108825683594,
+      "step": 4860
+    },
+    {
+      "epoch": 0.5582885253403501,
+      "grad_norm": 5.03125,
+      "learning_rate": 3.6893205081073536e-05,
+      "loss": 0.30228707790374754,
+      "step": 4880
+    },
+    {
+      "epoch": 0.5605765930671548,
+      "grad_norm": 4.46875,
+      "learning_rate": 3.686730637437521e-05,
+      "loss": 0.3006527185440063,
+      "step": 4900
+    },
+    {
+      "epoch": 0.5628646607939595,
+      "grad_norm": 4.4375,
+      "learning_rate": 3.6841309336658795e-05,
+      "loss": 0.2690931558609009,
+      "step": 4920
+    },
+    {
+      "epoch": 0.5651527285207643,
+      "grad_norm": 4.1875,
+      "learning_rate": 3.681521411947874e-05,
+      "loss": 0.30734207630157473,
+      "step": 4940
+    },
+    {
+      "epoch": 0.5674407962475689,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.678902087496183e-05,
+      "loss": 0.2901519775390625,
+      "step": 4960
+    },
+    {
+      "epoch": 0.5697288639743736,
+      "grad_norm": 5.25,
+      "learning_rate": 3.676272975580633e-05,
+      "loss": 0.2794654130935669,
+      "step": 4980
+    },
+    {
+      "epoch": 0.5720169317011784,
+      "grad_norm": 5.25,
+      "learning_rate": 3.6736340915281094e-05,
+      "loss": 0.2785376310348511,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5720169317011784,
+      "eval_loss": 0.29227501153945923,
+      "eval_runtime": 30.1094,
+      "eval_samples_per_second": 189.609,
+      "eval_steps_per_second": 5.945,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5743049994279831,
+      "grad_norm": 7.46875,
+      "learning_rate": 3.670985450722464e-05,
+      "loss": 0.3043736457824707,
+      "step": 5020
+    },
+    {
+      "epoch": 0.5765930671547878,
+      "grad_norm": 10.6875,
+      "learning_rate": 3.668327068604428e-05,
+      "loss": 0.266217041015625,
+      "step": 5040
+    },
+    {
+      "epoch": 0.5788811348815925,
+      "grad_norm": 6.0625,
+      "learning_rate": 3.665658960671521e-05,
+      "loss": 0.32198433876037597,
+      "step": 5060
+    },
+    {
+      "epoch": 0.5811692026083972,
+      "grad_norm": 5.5,
+      "learning_rate": 3.662981142477963e-05,
+      "loss": 0.3342748641967773,
+      "step": 5080
+    },
+    {
+      "epoch": 0.5834572703352019,
+      "grad_norm": 4.71875,
+      "learning_rate": 3.66029362963458e-05,
+      "loss": 0.30125606060028076,
+      "step": 5100
+    },
+    {
+      "epoch": 0.5857453380620067,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.657596437808714e-05,
+      "loss": 0.31322171688079836,
+      "step": 5120
+    },
+    {
+      "epoch": 0.5880334057888114,
+      "grad_norm": 4.625,
+      "learning_rate": 3.6548895827241336e-05,
+      "loss": 0.3061929702758789,
+      "step": 5140
+    },
+    {
+      "epoch": 0.590321473515616,
+      "grad_norm": 5.125,
+      "learning_rate": 3.652173080160941e-05,
+      "loss": 0.29476490020751955,
+      "step": 5160
+    },
+    {
+      "epoch": 0.5926095412424208,
+      "grad_norm": 3.671875,
+      "learning_rate": 3.649446945955481e-05,
+      "loss": 0.2932231664657593,
+      "step": 5180
+    },
+    {
+      "epoch": 0.5948976089692255,
+      "grad_norm": 5.125,
+      "learning_rate": 3.6467111960002455e-05,
+      "loss": 0.2834190607070923,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5971856766960302,
+      "grad_norm": 4.90625,
+      "learning_rate": 3.643965846243784e-05,
+      "loss": 0.3238036632537842,
+      "step": 5220
+    },
+    {
+      "epoch": 0.599473744422835,
+      "grad_norm": 4.1875,
+      "learning_rate": 3.641210912690612e-05,
+      "loss": 0.2880073308944702,
+      "step": 5240
+    },
+    {
+      "epoch": 0.6017618121496396,
+      "grad_norm": 4.375,
+      "learning_rate": 3.638446411401113e-05,
+      "loss": 0.2787164688110352,
+      "step": 5260
+    },
+    {
+      "epoch": 0.6040498798764443,
+      "grad_norm": 4.96875,
+      "learning_rate": 3.635672358491448e-05,
+      "loss": 0.28207404613494874,
+      "step": 5280
+    },
+    {
+      "epoch": 0.6063379476032491,
+      "grad_norm": 7.0625,
+      "learning_rate": 3.63288877013346e-05,
+      "loss": 0.31008429527282716,
+      "step": 5300
+    },
+    {
+      "epoch": 0.6086260153300538,
+      "grad_norm": 5.28125,
+      "learning_rate": 3.6300956625545836e-05,
+      "loss": 0.3173093557357788,
+      "step": 5320
+    },
+    {
+      "epoch": 0.6109140830568585,
+      "grad_norm": 4.3125,
+      "learning_rate": 3.6272930520377434e-05,
+      "loss": 0.2883350372314453,
+      "step": 5340
+    },
+    {
+      "epoch": 0.6132021507836632,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.624480954921266e-05,
+      "loss": 0.3079493522644043,
+      "step": 5360
+    },
+    {
+      "epoch": 0.6154902185104679,
+      "grad_norm": 4.9375,
+      "learning_rate": 3.6216593875987815e-05,
+      "loss": 0.30201876163482666,
+      "step": 5380
+    },
+    {
+      "epoch": 0.6177782862372726,
+      "grad_norm": 5.8125,
+      "learning_rate": 3.618828366519127e-05,
+      "loss": 0.27506444454193113,
+      "step": 5400
+    },
+    {
+      "epoch": 0.6200663539640774,
+      "grad_norm": 5.1875,
+      "learning_rate": 3.6159879081862524e-05,
+      "loss": 0.2849998950958252,
+      "step": 5420
+    },
+    {
+      "epoch": 0.6223544216908821,
+      "grad_norm": 3.296875,
+      "learning_rate": 3.613138029159125e-05,
+      "loss": 0.256860089302063,
+      "step": 5440
+    },
+    {
+      "epoch": 0.6246424894176867,
+      "grad_norm": 4.1875,
+      "learning_rate": 3.610278746051631e-05,
+      "loss": 0.26427302360534666,
+      "step": 5460
+    },
+    {
+      "epoch": 0.6269305571444915,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.607410075532478e-05,
+      "loss": 0.24430880546569825,
+      "step": 5480
+    },
+    {
+      "epoch": 0.6292186248712962,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.6045320343251015e-05,
+      "loss": 0.3006285190582275,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6292186248712962,
+      "eval_loss": 0.2767653167247772,
+      "eval_runtime": 30.1767,
+      "eval_samples_per_second": 189.186,
+      "eval_steps_per_second": 5.932,
+      "step": 5500
+    },
+    {
+      "epoch": 0.6315066925981009,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.6016446392075636e-05,
+      "loss": 0.3013110637664795,
+      "step": 5520
+    },
+    {
+      "epoch": 0.6337947603249057,
+      "grad_norm": 6.6875,
+      "learning_rate": 3.598747907012458e-05,
+      "loss": 0.2936428070068359,
+      "step": 5540
+    },
+    {
+      "epoch": 0.6360828280517103,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.595841854626809e-05,
+      "loss": 0.2893106698989868,
+      "step": 5560
+    },
+    {
+      "epoch": 0.638370895778515,
+      "grad_norm": 5.0625,
+      "learning_rate": 3.5929264989919745e-05,
+      "loss": 0.2925205945968628,
+      "step": 5580
+    },
+    {
+      "epoch": 0.6406589635053198,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.590001857103551e-05,
+      "loss": 0.29573826789855956,
+      "step": 5600
+    },
+    {
+      "epoch": 0.6429470312321245,
+      "grad_norm": 5.3125,
+      "learning_rate": 3.587067946011265e-05,
+      "loss": 0.28630809783935546,
+      "step": 5620
+    },
+    {
+      "epoch": 0.6452350989589292,
+      "grad_norm": 3.640625,
+      "learning_rate": 3.5841247828188856e-05,
+      "loss": 0.26862502098083496,
+      "step": 5640
+    },
+    {
+      "epoch": 0.647523166685734,
+      "grad_norm": 5.375,
+      "learning_rate": 3.5811723846841136e-05,
+      "loss": 0.2666471004486084,
+      "step": 5660
+    },
+    {
+      "epoch": 0.6498112344125386,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.5782107688184905e-05,
+      "loss": 0.2828779935836792,
+      "step": 5680
+    },
+    {
+      "epoch": 0.6520993021393433,
+      "grad_norm": 5.75,
+      "learning_rate": 3.575239952487291e-05,
+      "loss": 0.2601483345031738,
+      "step": 5700
+    },
+    {
+      "epoch": 0.654387369866148,
+      "grad_norm": 4.3125,
+      "learning_rate": 3.572259953009428e-05,
+      "loss": 0.261041522026062,
+      "step": 5720
+    },
+    {
+      "epoch": 0.6566754375929528,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.569270787757348e-05,
+      "loss": 0.26867046356201174,
+      "step": 5740
+    },
+    {
+      "epoch": 0.6589635053197574,
+      "grad_norm": 8.9375,
+      "learning_rate": 3.5662724741569314e-05,
+      "loss": 0.26578536033630373,
+      "step": 5760
+    },
+    {
+      "epoch": 0.6612515730465621,
+      "grad_norm": 7.15625,
+      "learning_rate": 3.5632650296873906e-05,
+      "loss": 0.2661498785018921,
+      "step": 5780
+    },
+    {
+      "epoch": 0.6635396407733669,
+      "grad_norm": 4.75,
+      "learning_rate": 3.5602484718811674e-05,
+      "loss": 0.27622816562652586,
+      "step": 5800
+    },
+    {
+      "epoch": 0.6658277085001716,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.557222818323833e-05,
+      "loss": 0.2716834545135498,
+      "step": 5820
+    },
+    {
+      "epoch": 0.6681157762269763,
+      "grad_norm": 3.515625,
+      "learning_rate": 3.5541880866539816e-05,
+      "loss": 0.2630940914154053,
+      "step": 5840
+    },
+    {
+      "epoch": 0.670403843953781,
+      "grad_norm": 4.46875,
+      "learning_rate": 3.5511442945631325e-05,
+      "loss": 0.2714268922805786,
+      "step": 5860
+    },
+    {
+      "epoch": 0.6726919116805857,
+      "grad_norm": 4.59375,
+      "learning_rate": 3.548091459795622e-05,
+      "loss": 0.2755922794342041,
+      "step": 5880
+    },
+    {
+      "epoch": 0.6749799794073904,
+      "grad_norm": 5.25,
+      "learning_rate": 3.545029600148504e-05,
+      "loss": 0.2945363759994507,
+      "step": 5900
+    },
+    {
+      "epoch": 0.6772680471341952,
+      "grad_norm": 5.75,
+      "learning_rate": 3.541958733471444e-05,
+      "loss": 0.2770261287689209,
+      "step": 5920
+    },
+    {
+      "epoch": 0.6795561148609999,
+      "grad_norm": 4.5,
+      "learning_rate": 3.5388788776666156e-05,
+      "loss": 0.24069409370422362,
+      "step": 5940
+    },
+    {
+      "epoch": 0.6818441825878045,
+      "grad_norm": 3.859375,
+      "learning_rate": 3.5357900506885965e-05,
+      "loss": 0.25673096179962157,
+      "step": 5960
+    },
+    {
+      "epoch": 0.6841322503146093,
+      "grad_norm": 6.3125,
+      "learning_rate": 3.532692270544262e-05,
+      "loss": 0.2766316652297974,
+      "step": 5980
+    },
+    {
+      "epoch": 0.686420318041414,
+      "grad_norm": 6.40625,
+      "learning_rate": 3.529585555292683e-05,
+      "loss": 0.280531120300293,
+      "step": 6000
+    },
+    {
+      "epoch": 0.686420318041414,
+      "eval_loss": 0.26804906129837036,
+      "eval_runtime": 30.2398,
+      "eval_samples_per_second": 188.791,
+      "eval_steps_per_second": 5.919,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 26223,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.660515177467085e+17,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..f3f788a
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:748ff9c049ba3649944f9bab1587574826137332d2e496fc4eab362a0deb8c87
+size 5201