Upload folder using huggingface_hub

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: rinna/llama-3-youko-8b
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-200/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "rinna/llama-3-youko-8b",
+  "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": 32,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33f4e8a2a1e4496b969162a49323c6c9dcdc21045f16ee42ab8adeaad391122d
+size 11849545016

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d01be5c5eee4f8163c67469ddc79dd3ab4f0b6097fbb3c20cce5a6e8fb7cfc6
+size 2778493596

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af34d41a387513fe16d2f526704002f5f5013be898bf20077d67118a76362740
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aebbb7b58ad06e49c2e689b08db1c357328a214e1efd61bf12c031a959888e2
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4025764895330113,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002012882447665056,
+      "grad_norm": 22.921390533447266,
+      "learning_rate": 6.5e-06,
+      "loss": 1.3427,
+      "step": 1
+    },
+    {
+      "epoch": 0.004025764895330112,
+      "grad_norm": 14.772722244262695,
+      "learning_rate": 1.3e-05,
+      "loss": 1.3647,
+      "step": 2
+    },
+    {
+      "epoch": 0.006038647342995169,
+      "grad_norm": 11.458742141723633,
+      "learning_rate": 1.9499999999999996e-05,
+      "loss": 1.2841,
+      "step": 3
+    },
+    {
+      "epoch": 0.008051529790660225,
+      "grad_norm": 4.747677326202393,
+      "learning_rate": 2.6e-05,
+      "loss": 1.1644,
+      "step": 4
+    },
+    {
+      "epoch": 0.010064412238325281,
+      "grad_norm": 3.687121629714966,
+      "learning_rate": 3.25e-05,
+      "loss": 1.1084,
+      "step": 5
+    },
+    {
+      "epoch": 0.012077294685990338,
+      "grad_norm": 3.178232431411743,
+      "learning_rate": 3.899999999999999e-05,
+      "loss": 1.0753,
+      "step": 6
+    },
+    {
+      "epoch": 0.014090177133655395,
+      "grad_norm": 2.476033926010132,
+      "learning_rate": 4.5499999999999995e-05,
+      "loss": 1.075,
+      "step": 7
+    },
+    {
+      "epoch": 0.01610305958132045,
+      "grad_norm": 1.9162139892578125,
+      "learning_rate": 5.2e-05,
+      "loss": 1.0195,
+      "step": 8
+    },
+    {
+      "epoch": 0.018115942028985508,
+      "grad_norm": 1.797377109527588,
+      "learning_rate": 5.85e-05,
+      "loss": 0.9884,
+      "step": 9
+    },
+    {
+      "epoch": 0.020128824476650563,
+      "grad_norm": 1.816100835800171,
+      "learning_rate": 6.5e-05,
+      "loss": 0.9945,
+      "step": 10
+    },
+    {
+      "epoch": 0.02214170692431562,
+      "grad_norm": 1.843664526939392,
+      "learning_rate": 6.499932098548219e-05,
+      "loss": 0.8802,
+      "step": 11
+    },
+    {
+      "epoch": 0.024154589371980676,
+      "grad_norm": 1.7202250957489014,
+      "learning_rate": 6.49972839703017e-05,
+      "loss": 0.9833,
+      "step": 12
+    },
+    {
+      "epoch": 0.026167471819645734,
+      "grad_norm": 1.4981484413146973,
+      "learning_rate": 6.499388903957628e-05,
+      "loss": 0.9481,
+      "step": 13
+    },
+    {
+      "epoch": 0.02818035426731079,
+      "grad_norm": 1.4716213941574097,
+      "learning_rate": 6.498913633516483e-05,
+      "loss": 0.8809,
+      "step": 14
+    },
+    {
+      "epoch": 0.030193236714975844,
+      "grad_norm": 1.3817026615142822,
+      "learning_rate": 6.498302605566152e-05,
+      "loss": 0.9264,
+      "step": 15
+    },
+    {
+      "epoch": 0.0322061191626409,
+      "grad_norm": 1.509097695350647,
+      "learning_rate": 6.497555845638748e-05,
+      "loss": 0.8829,
+      "step": 16
+    },
+    {
+      "epoch": 0.03421900161030596,
+      "grad_norm": 1.5498337745666504,
+      "learning_rate": 6.496673384938014e-05,
+      "loss": 0.9227,
+      "step": 17
+    },
+    {
+      "epoch": 0.036231884057971016,
+      "grad_norm": 1.527828574180603,
+      "learning_rate": 6.49565526033802e-05,
+      "loss": 0.9488,
+      "step": 18
+    },
+    {
+      "epoch": 0.038244766505636074,
+      "grad_norm": 1.4578592777252197,
+      "learning_rate": 6.494501514381621e-05,
+      "loss": 0.8845,
+      "step": 19
+    },
+    {
+      "epoch": 0.040257648953301126,
+      "grad_norm": 1.4198046922683716,
+      "learning_rate": 6.493212195278678e-05,
+      "loss": 0.8809,
+      "step": 20
+    },
+    {
+      "epoch": 0.042270531400966184,
+      "grad_norm": 1.4455400705337524,
+      "learning_rate": 6.491787356904047e-05,
+      "loss": 0.8686,
+      "step": 21
+    },
+    {
+      "epoch": 0.04428341384863124,
+      "grad_norm": 1.5711616277694702,
+      "learning_rate": 6.490227058795323e-05,
+      "loss": 0.96,
+      "step": 22
+    },
+    {
+      "epoch": 0.046296296296296294,
+      "grad_norm": 1.4603729248046875,
+      "learning_rate": 6.488531366150359e-05,
+      "loss": 0.9026,
+      "step": 23
+    },
+    {
+      "epoch": 0.04830917874396135,
+      "grad_norm": 1.4184608459472656,
+      "learning_rate": 6.48670034982453e-05,
+      "loss": 0.9426,
+      "step": 24
+    },
+    {
+      "epoch": 0.05032206119162641,
+      "grad_norm": 1.4080291986465454,
+      "learning_rate": 6.484734086327788e-05,
+      "loss": 0.8857,
+      "step": 25
+    },
+    {
+      "epoch": 0.05233494363929147,
+      "grad_norm": 1.4739091396331787,
+      "learning_rate": 6.482632657821454e-05,
+      "loss": 0.8897,
+      "step": 26
+    },
+    {
+      "epoch": 0.05434782608695652,
+      "grad_norm": 1.320746898651123,
+      "learning_rate": 6.480396152114787e-05,
+      "loss": 0.8512,
+      "step": 27
+    },
+    {
+      "epoch": 0.05636070853462158,
+      "grad_norm": 1.4142905473709106,
+      "learning_rate": 6.478024662661315e-05,
+      "loss": 0.9459,
+      "step": 28
+    },
+    {
+      "epoch": 0.05837359098228664,
+      "grad_norm": 1.3830432891845703,
+      "learning_rate": 6.47551828855493e-05,
+      "loss": 0.8605,
+      "step": 29
+    },
+    {
+      "epoch": 0.06038647342995169,
+      "grad_norm": 1.3653528690338135,
+      "learning_rate": 6.472877134525753e-05,
+      "loss": 0.8446,
+      "step": 30
+    },
+    {
+      "epoch": 0.06239935587761675,
+      "grad_norm": 1.3041807413101196,
+      "learning_rate": 6.470101310935746e-05,
+      "loss": 0.8407,
+      "step": 31
+    },
+    {
+      "epoch": 0.0644122383252818,
+      "grad_norm": 1.3803820610046387,
+      "learning_rate": 6.467190933774112e-05,
+      "loss": 0.8505,
+      "step": 32
+    },
+    {
+      "epoch": 0.06642512077294686,
+      "grad_norm": 1.3407087326049805,
+      "learning_rate": 6.464146124652441e-05,
+      "loss": 0.794,
+      "step": 33
+    },
+    {
+      "epoch": 0.06843800322061191,
+      "grad_norm": 1.4283268451690674,
+      "learning_rate": 6.460967010799629e-05,
+      "loss": 0.9139,
+      "step": 34
+    },
+    {
+      "epoch": 0.07045088566827697,
+      "grad_norm": 1.3512784242630005,
+      "learning_rate": 6.457653725056568e-05,
+      "loss": 0.807,
+      "step": 35
+    },
+    {
+      "epoch": 0.07246376811594203,
+      "grad_norm": 1.3088512420654297,
+      "learning_rate": 6.454206405870587e-05,
+      "loss": 0.8968,
+      "step": 36
+    },
+    {
+      "epoch": 0.07447665056360708,
+      "grad_norm": 1.2908034324645996,
+      "learning_rate": 6.450625197289675e-05,
+      "loss": 0.8447,
+      "step": 37
+    },
+    {
+      "epoch": 0.07648953301127215,
+      "grad_norm": 1.3444992303848267,
+      "learning_rate": 6.446910248956453e-05,
+      "loss": 0.8891,
+      "step": 38
+    },
+    {
+      "epoch": 0.0785024154589372,
+      "grad_norm": 1.2567275762557983,
+      "learning_rate": 6.443061716101926e-05,
+      "loss": 0.8134,
+      "step": 39
+    },
+    {
+      "epoch": 0.08051529790660225,
+      "grad_norm": 1.3401930332183838,
+      "learning_rate": 6.439079759539e-05,
+      "loss": 0.8751,
+      "step": 40
+    },
+    {
+      "epoch": 0.08252818035426732,
+      "grad_norm": 1.3348793983459473,
+      "learning_rate": 6.434964545655754e-05,
+      "loss": 0.7942,
+      "step": 41
+    },
+    {
+      "epoch": 0.08454106280193237,
+      "grad_norm": 1.311357021331787,
+      "learning_rate": 6.430716246408493e-05,
+      "loss": 0.8461,
+      "step": 42
+    },
+    {
+      "epoch": 0.08655394524959742,
+      "grad_norm": 1.3319345712661743,
+      "learning_rate": 6.426335039314566e-05,
+      "loss": 0.8821,
+      "step": 43
+    },
+    {
+      "epoch": 0.08856682769726248,
+      "grad_norm": 1.304795742034912,
+      "learning_rate": 6.421821107444936e-05,
+      "loss": 0.8655,
+      "step": 44
+    },
+    {
+      "epoch": 0.09057971014492754,
+      "grad_norm": 1.422869086265564,
+      "learning_rate": 6.417174639416547e-05,
+      "loss": 0.9261,
+      "step": 45
+    },
+    {
+      "epoch": 0.09259259259259259,
+      "grad_norm": 1.2931973934173584,
+      "learning_rate": 6.412395829384427e-05,
+      "loss": 0.8157,
+      "step": 46
+    },
+    {
+      "epoch": 0.09460547504025765,
+      "grad_norm": 1.2984646558761597,
+      "learning_rate": 6.407484877033586e-05,
+      "loss": 0.7919,
+      "step": 47
+    },
+    {
+      "epoch": 0.0966183574879227,
+      "grad_norm": 1.2596486806869507,
+      "learning_rate": 6.402441987570665e-05,
+      "loss": 0.7682,
+      "step": 48
+    },
+    {
+      "epoch": 0.09863123993558776,
+      "grad_norm": 1.3544796705245972,
+      "learning_rate": 6.397267371715368e-05,
+      "loss": 0.9084,
+      "step": 49
+    },
+    {
+      "epoch": 0.10064412238325282,
+      "grad_norm": 1.2623202800750732,
+      "learning_rate": 6.391961245691652e-05,
+      "loss": 0.8482,
+      "step": 50
+    },
+    {
+      "epoch": 0.10265700483091787,
+      "grad_norm": 1.320026159286499,
+      "learning_rate": 6.386523831218689e-05,
+      "loss": 0.8436,
+      "step": 51
+    },
+    {
+      "epoch": 0.10466988727858294,
+      "grad_norm": 1.4064967632293701,
+      "learning_rate": 6.38095535550161e-05,
+      "loss": 0.8962,
+      "step": 52
+    },
+    {
+      "epoch": 0.10668276972624799,
+      "grad_norm": 1.3178116083145142,
+      "learning_rate": 6.375256051222009e-05,
+      "loss": 0.8064,
+      "step": 53
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 1.2729371786117554,
+      "learning_rate": 6.369426156528213e-05,
+      "loss": 0.8338,
+      "step": 54
+    },
+    {
+      "epoch": 0.1107085346215781,
+      "grad_norm": 1.2167425155639648,
+      "learning_rate": 6.363465915025339e-05,
+      "loss": 0.8078,
+      "step": 55
+    },
+    {
+      "epoch": 0.11272141706924316,
+      "grad_norm": 1.3006845712661743,
+      "learning_rate": 6.357375575765108e-05,
+      "loss": 0.8462,
+      "step": 56
+    },
+    {
+      "epoch": 0.11473429951690821,
+      "grad_norm": 1.245822787284851,
+      "learning_rate": 6.351155393235449e-05,
+      "loss": 0.8394,
+      "step": 57
+    },
+    {
+      "epoch": 0.11674718196457327,
+      "grad_norm": 1.2608625888824463,
+      "learning_rate": 6.34480562734985e-05,
+      "loss": 0.8606,
+      "step": 58
+    },
+    {
+      "epoch": 0.11876006441223833,
+      "grad_norm": 1.2614774703979492,
+      "learning_rate": 6.33832654343651e-05,
+      "loss": 0.7633,
+      "step": 59
+    },
+    {
+      "epoch": 0.12077294685990338,
+      "grad_norm": 1.3382893800735474,
+      "learning_rate": 6.331718412227247e-05,
+      "loss": 0.8514,
+      "step": 60
+    },
+    {
+      "epoch": 0.12278582930756844,
+      "grad_norm": 1.2239303588867188,
+      "learning_rate": 6.324981509846189e-05,
+      "loss": 0.8319,
+      "step": 61
+    },
+    {
+      "epoch": 0.1247987117552335,
+      "grad_norm": 1.3828685283660889,
+      "learning_rate": 6.318116117798225e-05,
+      "loss": 0.8683,
+      "step": 62
+    },
+    {
+      "epoch": 0.12681159420289856,
+      "grad_norm": 1.304027795791626,
+      "learning_rate": 6.311122522957255e-05,
+      "loss": 0.887,
+      "step": 63
+    },
+    {
+      "epoch": 0.1288244766505636,
+      "grad_norm": 1.3097902536392212,
+      "learning_rate": 6.304001017554202e-05,
+      "loss": 0.8636,
+      "step": 64
+    },
+    {
+      "epoch": 0.13083735909822866,
+      "grad_norm": 1.281269907951355,
+      "learning_rate": 6.296751899164788e-05,
+      "loss": 0.7537,
+      "step": 65
+    },
+    {
+      "epoch": 0.13285024154589373,
+      "grad_norm": 1.2349010705947876,
+      "learning_rate": 6.289375470697116e-05,
+      "loss": 0.8451,
+      "step": 66
+    },
+    {
+      "epoch": 0.13486312399355876,
+      "grad_norm": 1.2939257621765137,
+      "learning_rate": 6.281872040379001e-05,
+      "loss": 0.8249,
+      "step": 67
+    },
+    {
+      "epoch": 0.13687600644122383,
+      "grad_norm": 1.308341145515442,
+      "learning_rate": 6.274241921745097e-05,
+      "loss": 0.8764,
+      "step": 68
+    },
+    {
+      "epoch": 0.1388888888888889,
+      "grad_norm": 1.311805009841919,
+      "learning_rate": 6.266485433623794e-05,
+      "loss": 0.8308,
+      "step": 69
+    },
+    {
+      "epoch": 0.14090177133655393,
+      "grad_norm": 1.6127303838729858,
+      "learning_rate": 6.258602900123894e-05,
+      "loss": 0.8069,
+      "step": 70
+    },
+    {
+      "epoch": 0.142914653784219,
+      "grad_norm": 1.292090654373169,
+      "learning_rate": 6.250594650621067e-05,
+      "loss": 0.8174,
+      "step": 71
+    },
+    {
+      "epoch": 0.14492753623188406,
+      "grad_norm": 1.256778359413147,
+      "learning_rate": 6.2424610197441e-05,
+      "loss": 0.7956,
+      "step": 72
+    },
+    {
+      "epoch": 0.1469404186795491,
+      "grad_norm": 1.2579149007797241,
+      "learning_rate": 6.23420234736089e-05,
+      "loss": 0.8267,
+      "step": 73
+    },
+    {
+      "epoch": 0.14895330112721417,
+      "grad_norm": 1.3226171731948853,
+      "learning_rate": 6.225818978564269e-05,
+      "loss": 0.9322,
+      "step": 74
+    },
+    {
+      "epoch": 0.15096618357487923,
+      "grad_norm": 1.1891167163848877,
+      "learning_rate": 6.217311263657565e-05,
+      "loss": 0.7886,
+      "step": 75
+    },
+    {
+      "epoch": 0.1529790660225443,
+      "grad_norm": 1.2481876611709595,
+      "learning_rate": 6.208679558139977e-05,
+      "loss": 0.7832,
+      "step": 76
+    },
+    {
+      "epoch": 0.15499194847020933,
+      "grad_norm": 1.2592449188232422,
+      "learning_rate": 6.199924222691707e-05,
+      "loss": 0.8061,
+      "step": 77
+    },
+    {
+      "epoch": 0.1570048309178744,
+      "grad_norm": 1.250359058380127,
+      "learning_rate": 6.191045623158907e-05,
+      "loss": 0.7942,
+      "step": 78
+    },
+    {
+      "epoch": 0.15901771336553946,
+      "grad_norm": 1.2406524419784546,
+      "learning_rate": 6.182044130538373e-05,
+      "loss": 0.7766,
+      "step": 79
+    },
+    {
+      "epoch": 0.1610305958132045,
+      "grad_norm": 1.2620049715042114,
+      "learning_rate": 6.172920120962052e-05,
+      "loss": 0.8445,
+      "step": 80
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": 1.2618622779846191,
+      "learning_rate": 6.16367397568133e-05,
+      "loss": 0.812,
+      "step": 81
+    },
+    {
+      "epoch": 0.16505636070853463,
+      "grad_norm": 1.2560168504714966,
+      "learning_rate": 6.15430608105109e-05,
+      "loss": 0.8331,
+      "step": 82
+    },
+    {
+      "epoch": 0.16706924315619967,
+      "grad_norm": 1.2386751174926758,
+      "learning_rate": 6.144816828513576e-05,
+      "loss": 0.7318,
+      "step": 83
+    },
+    {
+      "epoch": 0.16908212560386474,
+      "grad_norm": 1.3558485507965088,
+      "learning_rate": 6.135206614582031e-05,
+      "loss": 0.8476,
+      "step": 84
+    },
+    {
+      "epoch": 0.1710950080515298,
+      "grad_norm": 1.2461968660354614,
+      "learning_rate": 6.125475840824137e-05,
+      "loss": 0.8012,
+      "step": 85
+    },
+    {
+      "epoch": 0.17310789049919484,
+      "grad_norm": 1.2398920059204102,
+      "learning_rate": 6.115624913845225e-05,
+      "loss": 0.8033,
+      "step": 86
+    },
+    {
+      "epoch": 0.1751207729468599,
+      "grad_norm": 1.3263791799545288,
+      "learning_rate": 6.105654245271292e-05,
+      "loss": 0.8511,
+      "step": 87
+    },
+    {
+      "epoch": 0.17713365539452497,
+      "grad_norm": 1.2072999477386475,
+      "learning_rate": 6.095564251731795e-05,
+      "loss": 0.7478,
+      "step": 88
+    },
+    {
+      "epoch": 0.17914653784219,
+      "grad_norm": 1.287801742553711,
+      "learning_rate": 6.085355354842249e-05,
+      "loss": 0.8152,
+      "step": 89
+    },
+    {
+      "epoch": 0.18115942028985507,
+      "grad_norm": 1.2826151847839355,
+      "learning_rate": 6.0750279811866046e-05,
+      "loss": 0.7918,
+      "step": 90
+    },
+    {
+      "epoch": 0.18317230273752014,
+      "grad_norm": 1.276780605316162,
+      "learning_rate": 6.0645825622994254e-05,
+      "loss": 0.8774,
+      "step": 91
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 1.2205020189285278,
+      "learning_rate": 6.0540195346478515e-05,
+      "loss": 0.8398,
+      "step": 92
+    },
+    {
+      "epoch": 0.18719806763285024,
+      "grad_norm": 1.2247477769851685,
+      "learning_rate": 6.043339339613371e-05,
+      "loss": 0.8322,
+      "step": 93
+    },
+    {
+      "epoch": 0.1892109500805153,
+      "grad_norm": 1.3282443284988403,
+      "learning_rate": 6.0325424234733656e-05,
+      "loss": 0.8003,
+      "step": 94
+    },
+    {
+      "epoch": 0.19122383252818034,
+      "grad_norm": 1.3472024202346802,
+      "learning_rate": 6.0216292373824696e-05,
+      "loss": 0.8305,
+      "step": 95
+    },
+    {
+      "epoch": 0.1932367149758454,
+      "grad_norm": 1.2812607288360596,
+      "learning_rate": 6.010600237353716e-05,
+      "loss": 0.7657,
+      "step": 96
+    },
+    {
+      "epoch": 0.19524959742351047,
+      "grad_norm": 1.2958053350448608,
+      "learning_rate": 5.999455884239483e-05,
+      "loss": 0.869,
+      "step": 97
+    },
+    {
+      "epoch": 0.1972624798711755,
+      "grad_norm": 1.2021034955978394,
+      "learning_rate": 5.988196643712235e-05,
+      "loss": 0.7798,
+      "step": 98
+    },
+    {
+      "epoch": 0.19927536231884058,
+      "grad_norm": 1.2430065870285034,
+      "learning_rate": 5.976822986245067e-05,
+      "loss": 0.7496,
+      "step": 99
+    },
+    {
+      "epoch": 0.20128824476650564,
+      "grad_norm": 1.2749730348587036,
+      "learning_rate": 5.9653353870920434e-05,
+      "loss": 0.831,
+      "step": 100
+    },
+    {
+      "epoch": 0.20330112721417068,
+      "grad_norm": 1.2621365785598755,
+      "learning_rate": 5.953734326268337e-05,
+      "loss": 0.8051,
+      "step": 101
+    },
+    {
+      "epoch": 0.20531400966183574,
+      "grad_norm": 1.1950538158416748,
+      "learning_rate": 5.94202028853018e-05,
+      "loss": 0.7866,
+      "step": 102
+    },
+    {
+      "epoch": 0.2073268921095008,
+      "grad_norm": 1.3278518915176392,
+      "learning_rate": 5.930193763354597e-05,
+      "loss": 0.8374,
+      "step": 103
+    },
+    {
+      "epoch": 0.20933977455716588,
+      "grad_norm": 1.281888484954834,
+      "learning_rate": 5.91825524491896e-05,
+      "loss": 0.8255,
+      "step": 104
+    },
+    {
+      "epoch": 0.2113526570048309,
+      "grad_norm": 1.270607352256775,
+      "learning_rate": 5.906205232080336e-05,
+      "loss": 0.7782,
+      "step": 105
+    },
+    {
+      "epoch": 0.21336553945249598,
+      "grad_norm": 1.2177718877792358,
+      "learning_rate": 5.894044228354644e-05,
+      "loss": 0.7506,
+      "step": 106
+    },
+    {
+      "epoch": 0.21537842190016104,
+      "grad_norm": 1.247755765914917,
+      "learning_rate": 5.88177274189561e-05,
+      "loss": 0.8135,
+      "step": 107
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 1.2848960161209106,
+      "learning_rate": 5.869391285473541e-05,
+      "loss": 0.8259,
+      "step": 108
+    },
+    {
+      "epoch": 0.21940418679549115,
+      "grad_norm": 1.197343349456787,
+      "learning_rate": 5.856900376453892e-05,
+      "loss": 0.7872,
+      "step": 109
+    },
+    {
+      "epoch": 0.2214170692431562,
+      "grad_norm": 1.2160040140151978,
+      "learning_rate": 5.844300536775651e-05,
+      "loss": 0.7725,
+      "step": 110
+    },
+    {
+      "epoch": 0.22342995169082125,
+      "grad_norm": 1.2862228155136108,
+      "learning_rate": 5.831592292929532e-05,
+      "loss": 0.7808,
+      "step": 111
+    },
+    {
+      "epoch": 0.22544283413848631,
+      "grad_norm": 1.2369639873504639,
+      "learning_rate": 5.818776175935967e-05,
+      "loss": 0.7898,
+      "step": 112
+    },
+    {
+      "epoch": 0.22745571658615138,
+      "grad_norm": 1.2040680646896362,
+      "learning_rate": 5.805852721322927e-05,
+      "loss": 0.8068,
+      "step": 113
+    },
+    {
+      "epoch": 0.22946859903381642,
+      "grad_norm": 1.28532075881958,
+      "learning_rate": 5.792822469103539e-05,
+      "loss": 0.8117,
+      "step": 114
+    },
+    {
+      "epoch": 0.23148148148148148,
+      "grad_norm": 1.2590646743774414,
+      "learning_rate": 5.7796859637535194e-05,
+      "loss": 0.7806,
+      "step": 115
+    },
+    {
+      "epoch": 0.23349436392914655,
+      "grad_norm": 1.223161220550537,
+      "learning_rate": 5.76644375418843e-05,
+      "loss": 0.7477,
+      "step": 116
+    },
+    {
+      "epoch": 0.23550724637681159,
+      "grad_norm": 1.2891532182693481,
+      "learning_rate": 5.753096393740734e-05,
+      "loss": 0.8055,
+      "step": 117
+    },
+    {
+      "epoch": 0.23752012882447665,
+      "grad_norm": 1.352499008178711,
+      "learning_rate": 5.739644440136678e-05,
+      "loss": 0.8192,
+      "step": 118
+    },
+    {
+      "epoch": 0.23953301127214172,
+      "grad_norm": 1.2987629175186157,
+      "learning_rate": 5.726088455472989e-05,
+      "loss": 0.8279,
+      "step": 119
+    },
+    {
+      "epoch": 0.24154589371980675,
+      "grad_norm": 1.2705352306365967,
+      "learning_rate": 5.7124290061933827e-05,
+      "loss": 0.826,
+      "step": 120
+    },
+    {
+      "epoch": 0.24355877616747182,
+      "grad_norm": 1.3219701051712036,
+      "learning_rate": 5.698666663064896e-05,
+      "loss": 0.8321,
+      "step": 121
+    },
+    {
+      "epoch": 0.24557165861513688,
+      "grad_norm": 1.3087178468704224,
+      "learning_rate": 5.6848020011540414e-05,
+      "loss": 0.8629,
+      "step": 122
+    },
+    {
+      "epoch": 0.24758454106280192,
+      "grad_norm": 1.2457053661346436,
+      "learning_rate": 5.670835599802768e-05,
+      "loss": 0.8092,
+      "step": 123
+    },
+    {
+      "epoch": 0.249597423510467,
+      "grad_norm": 1.2432583570480347,
+      "learning_rate": 5.656768042604265e-05,
+      "loss": 0.7889,
+      "step": 124
+    },
+    {
+      "epoch": 0.25161030595813205,
+      "grad_norm": 1.3183501958847046,
+      "learning_rate": 5.6425999173785643e-05,
+      "loss": 0.8554,
+      "step": 125
+    },
+    {
+      "epoch": 0.2536231884057971,
+      "grad_norm": 1.2189457416534424,
+      "learning_rate": 5.628331816147989e-05,
+      "loss": 0.7932,
+      "step": 126
+    },
+    {
+      "epoch": 0.2556360708534622,
+      "grad_norm": 1.143637776374817,
+      "learning_rate": 5.6139643351124076e-05,
+      "loss": 0.7668,
+      "step": 127
+    },
+    {
+      "epoch": 0.2576489533011272,
+      "grad_norm": 1.1862376928329468,
+      "learning_rate": 5.5994980746243264e-05,
+      "loss": 0.8165,
+      "step": 128
+    },
+    {
+      "epoch": 0.25966183574879226,
+      "grad_norm": 1.1560195684432983,
+      "learning_rate": 5.5849336391637995e-05,
+      "loss": 0.8122,
+      "step": 129
+    },
+    {
+      "epoch": 0.2616747181964573,
+      "grad_norm": 1.2094959020614624,
+      "learning_rate": 5.5702716373131716e-05,
+      "loss": 0.7955,
+      "step": 130
+    },
+    {
+      "epoch": 0.2636876006441224,
+      "grad_norm": 1.2558305263519287,
+      "learning_rate": 5.5555126817316515e-05,
+      "loss": 0.8399,
+      "step": 131
+    },
+    {
+      "epoch": 0.26570048309178745,
+      "grad_norm": 1.297591209411621,
+      "learning_rate": 5.540657389129707e-05,
+      "loss": 0.8398,
+      "step": 132
+    },
+    {
+      "epoch": 0.2677133655394525,
+      "grad_norm": 1.3282864093780518,
+      "learning_rate": 5.525706380243297e-05,
+      "loss": 0.8156,
+      "step": 133
+    },
+    {
+      "epoch": 0.26972624798711753,
+      "grad_norm": 1.3417863845825195,
+      "learning_rate": 5.510660279807935e-05,
+      "loss": 0.8105,
+      "step": 134
+    },
+    {
+      "epoch": 0.2717391304347826,
+      "grad_norm": 1.2470736503601074,
+      "learning_rate": 5.495519716532585e-05,
+      "loss": 0.7849,
+      "step": 135
+    },
+    {
+      "epoch": 0.27375201288244766,
+      "grad_norm": 1.2911748886108398,
+      "learning_rate": 5.480285323073384e-05,
+      "loss": 0.836,
+      "step": 136
+    },
+    {
+      "epoch": 0.2757648953301127,
+      "grad_norm": 1.2390037775039673,
+      "learning_rate": 5.464957736007215e-05,
+      "loss": 0.7556,
+      "step": 137
+    },
+    {
+      "epoch": 0.2777777777777778,
+      "grad_norm": 1.2093883752822876,
+      "learning_rate": 5.449537595805101e-05,
+      "loss": 0.8173,
+      "step": 138
+    },
+    {
+      "epoch": 0.27979066022544286,
+      "grad_norm": 1.2018241882324219,
+      "learning_rate": 5.434025546805447e-05,
+      "loss": 0.7983,
+      "step": 139
+    },
+    {
+      "epoch": 0.28180354267310787,
+      "grad_norm": 1.2486872673034668,
+      "learning_rate": 5.418422237187113e-05,
+      "loss": 0.813,
+      "step": 140
+    },
+    {
+      "epoch": 0.28381642512077293,
+      "grad_norm": 1.1954402923583984,
+      "learning_rate": 5.4027283189423296e-05,
+      "loss": 0.7999,
+      "step": 141
+    },
+    {
+      "epoch": 0.285829307568438,
+      "grad_norm": 1.1647478342056274,
+      "learning_rate": 5.386944447849457e-05,
+      "loss": 0.7872,
+      "step": 142
+    },
+    {
+      "epoch": 0.28784219001610306,
+      "grad_norm": 1.3171889781951904,
+      "learning_rate": 5.371071283445577e-05,
+      "loss": 0.8074,
+      "step": 143
+    },
+    {
+      "epoch": 0.2898550724637681,
+      "grad_norm": 1.3020223379135132,
+      "learning_rate": 5.355109488998941e-05,
+      "loss": 0.8068,
+      "step": 144
+    },
+    {
+      "epoch": 0.2918679549114332,
+      "grad_norm": 1.1892728805541992,
+      "learning_rate": 5.339059731481252e-05,
+      "loss": 0.7863,
+      "step": 145
+    },
+    {
+      "epoch": 0.2938808373590982,
+      "grad_norm": 1.2545976638793945,
+      "learning_rate": 5.322922681539793e-05,
+      "loss": 0.8486,
+      "step": 146
+    },
+    {
+      "epoch": 0.29589371980676327,
+      "grad_norm": 1.1874210834503174,
+      "learning_rate": 5.3066990134694086e-05,
+      "loss": 0.7702,
+      "step": 147
+    },
+    {
+      "epoch": 0.29790660225442833,
+      "grad_norm": 1.2464886903762817,
+      "learning_rate": 5.2903894051843204e-05,
+      "loss": 0.8313,
+      "step": 148
+    },
+    {
+      "epoch": 0.2999194847020934,
+      "grad_norm": 1.3062876462936401,
+      "learning_rate": 5.2739945381898095e-05,
+      "loss": 0.8076,
+      "step": 149
+    },
+    {
+      "epoch": 0.30193236714975846,
+      "grad_norm": 1.2185595035552979,
+      "learning_rate": 5.2575150975537353e-05,
+      "loss": 0.7585,
+      "step": 150
+    },
+    {
+      "epoch": 0.30394524959742353,
+      "grad_norm": 1.1846880912780762,
+      "learning_rate": 5.240951771877909e-05,
+      "loss": 0.7762,
+      "step": 151
+    },
+    {
+      "epoch": 0.3059581320450886,
+      "grad_norm": 1.1666184663772583,
+      "learning_rate": 5.224305253269321e-05,
+      "loss": 0.7539,
+      "step": 152
+    },
+    {
+      "epoch": 0.3079710144927536,
+      "grad_norm": 1.2293246984481812,
+      "learning_rate": 5.207576237311223e-05,
+      "loss": 0.8013,
+      "step": 153
+    },
+    {
+      "epoch": 0.30998389694041867,
+      "grad_norm": 1.184094786643982,
+      "learning_rate": 5.1907654230340546e-05,
+      "loss": 0.7686,
+      "step": 154
+    },
+    {
+      "epoch": 0.31199677938808373,
+      "grad_norm": 1.1998686790466309,
+      "learning_rate": 5.1738735128862465e-05,
+      "loss": 0.7596,
+      "step": 155
+    },
+    {
+      "epoch": 0.3140096618357488,
+      "grad_norm": 1.1767568588256836,
+      "learning_rate": 5.156901212704858e-05,
+      "loss": 0.7535,
+      "step": 156
+    },
+    {
+      "epoch": 0.31602254428341386,
+      "grad_norm": 1.1981345415115356,
+      "learning_rate": 5.139849231686086e-05,
+      "loss": 0.7971,
+      "step": 157
+    },
+    {
+      "epoch": 0.31803542673107893,
+      "grad_norm": 1.2676053047180176,
+      "learning_rate": 5.122718282355635e-05,
+      "loss": 0.7575,
+      "step": 158
+    },
+    {
+      "epoch": 0.32004830917874394,
+      "grad_norm": 1.2075040340423584,
+      "learning_rate": 5.105509080538939e-05,
+      "loss": 0.8187,
+      "step": 159
+    },
+    {
+      "epoch": 0.322061191626409,
+      "grad_norm": 1.2567739486694336,
+      "learning_rate": 5.08822234533125e-05,
+      "loss": 0.7754,
+      "step": 160
+    },
+    {
+      "epoch": 0.32407407407407407,
+      "grad_norm": 1.1478137969970703,
+      "learning_rate": 5.0708587990675954e-05,
+      "loss": 0.7744,
+      "step": 161
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 1.2385374307632446,
+      "learning_rate": 5.05341916729259e-05,
+      "loss": 0.7852,
+      "step": 162
+    },
+    {
+      "epoch": 0.3280998389694042,
+      "grad_norm": 1.2898869514465332,
+      "learning_rate": 5.035904178730119e-05,
+      "loss": 0.8475,
+      "step": 163
+    },
+    {
+      "epoch": 0.33011272141706927,
+      "grad_norm": 1.2359830141067505,
+      "learning_rate": 5.018314565252893e-05,
+      "loss": 0.8417,
+      "step": 164
+    },
+    {
+      "epoch": 0.3321256038647343,
+      "grad_norm": 1.224368929862976,
+      "learning_rate": 5.00065106185186e-05,
+      "loss": 0.7904,
+      "step": 165
+    },
+    {
+      "epoch": 0.33413848631239934,
+      "grad_norm": 1.229744553565979,
+      "learning_rate": 4.9829144066054964e-05,
+      "loss": 0.7969,
+      "step": 166
+    },
+    {
+      "epoch": 0.3361513687600644,
+      "grad_norm": 1.1933088302612305,
+      "learning_rate": 4.9651053406489656e-05,
+      "loss": 0.7646,
+      "step": 167
+    },
+    {
+      "epoch": 0.33816425120772947,
+      "grad_norm": 1.2042123079299927,
+      "learning_rate": 4.9472246081431494e-05,
+      "loss": 0.779,
+      "step": 168
+    },
+    {
+      "epoch": 0.34017713365539454,
+      "grad_norm": 1.1418585777282715,
+      "learning_rate": 4.9292729562435545e-05,
+      "loss": 0.7586,
+      "step": 169
+    },
+    {
+      "epoch": 0.3421900161030596,
+      "grad_norm": 1.2688250541687012,
+      "learning_rate": 4.9112511350690876e-05,
+      "loss": 0.7275,
+      "step": 170
+    },
+    {
+      "epoch": 0.3442028985507246,
+      "grad_norm": 1.1605274677276611,
+      "learning_rate": 4.893159897670716e-05,
+      "loss": 0.7784,
+      "step": 171
+    },
+    {
+      "epoch": 0.3462157809983897,
+      "grad_norm": 1.1853288412094116,
+      "learning_rate": 4.874999999999999e-05,
+      "loss": 0.7872,
+      "step": 172
+    },
+    {
+      "epoch": 0.34822866344605474,
+      "grad_norm": 1.180342197418213,
+      "learning_rate": 4.856772200877502e-05,
+      "loss": 0.7877,
+      "step": 173
+    },
+    {
+      "epoch": 0.3502415458937198,
+      "grad_norm": 1.1545747518539429,
+      "learning_rate": 4.838477261961083e-05,
+      "loss": 0.7554,
+      "step": 174
+    },
+    {
+      "epoch": 0.3522544283413849,
+      "grad_norm": 1.4341752529144287,
+      "learning_rate": 4.820115947714075e-05,
+      "loss": 0.7872,
+      "step": 175
+    },
+    {
+      "epoch": 0.35426731078904994,
+      "grad_norm": 1.254834532737732,
+      "learning_rate": 4.801689025373334e-05,
+      "loss": 0.8164,
+      "step": 176
+    },
+    {
+      "epoch": 0.35628019323671495,
+      "grad_norm": 1.18601393699646,
+      "learning_rate": 4.783197264917187e-05,
+      "loss": 0.7879,
+      "step": 177
+    },
+    {
+      "epoch": 0.35829307568438,
+      "grad_norm": 1.2259867191314697,
+      "learning_rate": 4.764641439033251e-05,
+      "loss": 0.8213,
+      "step": 178
+    },
+    {
+      "epoch": 0.3603059581320451,
+      "grad_norm": 1.2177544832229614,
+      "learning_rate": 4.746022323086153e-05,
+      "loss": 0.7674,
+      "step": 179
+    },
+    {
+      "epoch": 0.36231884057971014,
+      "grad_norm": 1.2497576475143433,
+      "learning_rate": 4.7273406950851265e-05,
+      "loss": 0.7512,
+      "step": 180
+    },
+    {
+      "epoch": 0.3643317230273752,
+      "grad_norm": 1.192671537399292,
+      "learning_rate": 4.708597335651502e-05,
+      "loss": 0.7917,
+      "step": 181
+    },
+    {
+      "epoch": 0.3663446054750403,
+      "grad_norm": 1.2135677337646484,
+      "learning_rate": 4.689793027986089e-05,
+      "loss": 0.7944,
+      "step": 182
+    },
+    {
+      "epoch": 0.36835748792270534,
+      "grad_norm": 1.2164232730865479,
+      "learning_rate": 4.670928557836452e-05,
+      "loss": 0.762,
+      "step": 183
+    },
+    {
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.175716757774353,
+      "learning_rate": 4.6520047134640736e-05,
+      "loss": 0.7313,
+      "step": 184
+    },
+    {
+      "epoch": 0.3723832528180354,
+      "grad_norm": 1.2479422092437744,
+      "learning_rate": 4.633022285611418e-05,
+      "loss": 0.831,
+      "step": 185
+    },
+    {
+      "epoch": 0.3743961352657005,
+      "grad_norm": 1.2672486305236816,
+      "learning_rate": 4.613982067468894e-05,
+      "loss": 0.7899,
+      "step": 186
+    },
+    {
+      "epoch": 0.37640901771336555,
+      "grad_norm": 1.3110653162002563,
+      "learning_rate": 4.594884854641702e-05,
+      "loss": 0.7759,
+      "step": 187
+    },
+    {
+      "epoch": 0.3784219001610306,
+      "grad_norm": 1.2542824745178223,
+      "learning_rate": 4.575731445116596e-05,
+      "loss": 0.785,
+      "step": 188
+    },
+    {
+      "epoch": 0.3804347826086957,
+      "grad_norm": 1.144977331161499,
+      "learning_rate": 4.55652263922854e-05,
+      "loss": 0.7398,
+      "step": 189
+    },
+    {
+      "epoch": 0.3824476650563607,
+      "grad_norm": 1.1065174341201782,
+      "learning_rate": 4.537259239627259e-05,
+      "loss": 0.7622,
+      "step": 190
+    },
+    {
+      "epoch": 0.38446054750402575,
+      "grad_norm": 1.227591872215271,
+      "learning_rate": 4.5179420512437075e-05,
+      "loss": 0.7603,
+      "step": 191
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 1.2493457794189453,
+      "learning_rate": 4.498571881256432e-05,
+      "loss": 0.7863,
+      "step": 192
+    },
+    {
+      "epoch": 0.3884863123993559,
+      "grad_norm": 1.3239022493362427,
+      "learning_rate": 4.479149539057838e-05,
+      "loss": 0.849,
+      "step": 193
+    },
+    {
+      "epoch": 0.39049919484702095,
+      "grad_norm": 1.2450414896011353,
+      "learning_rate": 4.4596758362203775e-05,
+      "loss": 0.7802,
+      "step": 194
+    },
+    {
+      "epoch": 0.392512077294686,
+      "grad_norm": 1.3064862489700317,
+      "learning_rate": 4.44015158646263e-05,
+      "loss": 0.7597,
+      "step": 195
+    },
+    {
+      "epoch": 0.394524959742351,
+      "grad_norm": 1.2286595106124878,
+      "learning_rate": 4.4205776056153084e-05,
+      "loss": 0.7863,
+      "step": 196
+    },
+    {
+      "epoch": 0.3965378421900161,
+      "grad_norm": 1.1941579580307007,
+      "learning_rate": 4.4009547115871594e-05,
+      "loss": 0.7199,
+      "step": 197
+    },
+    {
+      "epoch": 0.39855072463768115,
+      "grad_norm": 1.2539899349212646,
+      "learning_rate": 4.3812837243307933e-05,
+      "loss": 0.7807,
+      "step": 198
+    },
+    {
+      "epoch": 0.4005636070853462,
+      "grad_norm": 1.2592153549194336,
+      "learning_rate": 4.3615654658084234e-05,
+      "loss": 0.7657,
+      "step": 199
+    },
+    {
+      "epoch": 0.4025764895330113,
+      "grad_norm": 1.1356335878372192,
+      "learning_rate": 4.341800759957512e-05,
+      "loss": 0.6915,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 496,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 2.3568924723196723e+17,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d099daa3926570d9e2501eaac78896812191b5c803506c6b4dc9b531482a17b
+size 5112