Upload folder using huggingface_hub

checkpoint-200/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/gemma-2-27b-bnb-4bit
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

checkpoint-200/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/gemma-2-27b-bnb-4bit",
+  "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": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "o_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:f6cd2090f982b4b3eb81a4780eea79de7cdc76afd38070d06622ce3d18a1b0dc
+size 27247459432

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1412c44daeb0c33f961a9d34ccad021d35c62b667a2398f625df25d0b32036c
+size 6559156088

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb8e13a761d59b362762d6ee820fea31ce0b95fd5dc88a4c162745b069a81dba
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e256c765fa91c74ecd45c527c0ec85ce864683247d7c950fc0d3edf5702d3691
+size 1064

checkpoint-200/trainer_state.json

@@ -0,0 +1,1433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4024144869215292,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002012072434607646,
+      "grad_norm": 46.70955276489258,
+      "learning_rate": 6.5e-06,
+      "loss": 1.4376,
+      "step": 1
+    },
+    {
+      "epoch": 0.004024144869215292,
+      "grad_norm": 25.710079193115234,
+      "learning_rate": 1.3e-05,
+      "loss": 1.2619,
+      "step": 2
+    },
+    {
+      "epoch": 0.006036217303822937,
+      "grad_norm": 26.04344940185547,
+      "learning_rate": 1.9499999999999996e-05,
+      "loss": 1.2208,
+      "step": 3
+    },
+    {
+      "epoch": 0.008048289738430584,
+      "grad_norm": 8.251016616821289,
+      "learning_rate": 2.6e-05,
+      "loss": 1.0171,
+      "step": 4
+    },
+    {
+      "epoch": 0.01006036217303823,
+      "grad_norm": 4.199310302734375,
+      "learning_rate": 3.25e-05,
+      "loss": 0.9699,
+      "step": 5
+    },
+    {
+      "epoch": 0.012072434607645875,
+      "grad_norm": 6.134476661682129,
+      "learning_rate": 3.899999999999999e-05,
+      "loss": 0.9899,
+      "step": 6
+    },
+    {
+      "epoch": 0.014084507042253521,
+      "grad_norm": 4.348274230957031,
+      "learning_rate": 4.5499999999999995e-05,
+      "loss": 0.9959,
+      "step": 7
+    },
+    {
+      "epoch": 0.01609657947686117,
+      "grad_norm": 3.9475340843200684,
+      "learning_rate": 5.2e-05,
+      "loss": 0.8857,
+      "step": 8
+    },
+    {
+      "epoch": 0.018108651911468814,
+      "grad_norm": 3.1918065547943115,
+      "learning_rate": 5.85e-05,
+      "loss": 0.9008,
+      "step": 9
+    },
+    {
+      "epoch": 0.02012072434607646,
+      "grad_norm": 2.7590606212615967,
+      "learning_rate": 6.5e-05,
+      "loss": 0.8703,
+      "step": 10
+    },
+    {
+      "epoch": 0.022132796780684104,
+      "grad_norm": 3.0539116859436035,
+      "learning_rate": 6.499932377117017e-05,
+      "loss": 0.8258,
+      "step": 11
+    },
+    {
+      "epoch": 0.02414486921529175,
+      "grad_norm": 2.821988344192505,
+      "learning_rate": 6.499729511282135e-05,
+      "loss": 0.9071,
+      "step": 12
+    },
+    {
+      "epoch": 0.026156941649899398,
+      "grad_norm": 2.776759147644043,
+      "learning_rate": 6.499391410937425e-05,
+      "loss": 0.8496,
+      "step": 13
+    },
+    {
+      "epoch": 0.028169014084507043,
+      "grad_norm": 2.897883176803589,
+      "learning_rate": 6.498918090152627e-05,
+      "loss": 0.8339,
+      "step": 14
+    },
+    {
+      "epoch": 0.030181086519114688,
+      "grad_norm": 2.511650562286377,
+      "learning_rate": 6.498309568624549e-05,
+      "loss": 0.8398,
+      "step": 15
+    },
+    {
+      "epoch": 0.03219315895372234,
+      "grad_norm": 2.69217848777771,
+      "learning_rate": 6.497565871676255e-05,
+      "loss": 0.8373,
+      "step": 16
+    },
+    {
+      "epoch": 0.03420523138832998,
+      "grad_norm": 2.5202300548553467,
+      "learning_rate": 6.496687030256012e-05,
+      "loss": 0.8418,
+      "step": 17
+    },
+    {
+      "epoch": 0.03621730382293763,
+      "grad_norm": 2.4313321113586426,
+      "learning_rate": 6.495673080935999e-05,
+      "loss": 0.8482,
+      "step": 18
+    },
+    {
+      "epoch": 0.03822937625754527,
+      "grad_norm": 2.278684139251709,
+      "learning_rate": 6.494524065910784e-05,
+      "loss": 0.8059,
+      "step": 19
+    },
+    {
+      "epoch": 0.04024144869215292,
+      "grad_norm": 2.2294907569885254,
+      "learning_rate": 6.493240032995573e-05,
+      "loss": 0.8085,
+      "step": 20
+    },
+    {
+      "epoch": 0.04225352112676056,
+      "grad_norm": 2.446382999420166,
+      "learning_rate": 6.491821035624218e-05,
+      "loss": 0.8298,
+      "step": 21
+    },
+    {
+      "epoch": 0.04426559356136821,
+      "grad_norm": 2.4150474071502686,
+      "learning_rate": 6.490267132846992e-05,
+      "loss": 0.9265,
+      "step": 22
+    },
+    {
+      "epoch": 0.04627766599597585,
+      "grad_norm": 2.170037269592285,
+      "learning_rate": 6.488578389328129e-05,
+      "loss": 0.8323,
+      "step": 23
+    },
+    {
+      "epoch": 0.0482897384305835,
+      "grad_norm": 2.010956287384033,
+      "learning_rate": 6.486754875343145e-05,
+      "loss": 0.8646,
+      "step": 24
+    },
+    {
+      "epoch": 0.05030181086519115,
+      "grad_norm": 1.8752851486206055,
+      "learning_rate": 6.484796666775895e-05,
+      "loss": 0.8402,
+      "step": 25
+    },
+    {
+      "epoch": 0.052313883299798795,
+      "grad_norm": 1.8610150814056396,
+      "learning_rate": 6.482703845115434e-05,
+      "loss": 0.8256,
+      "step": 26
+    },
+    {
+      "epoch": 0.05432595573440644,
+      "grad_norm": 1.8047019243240356,
+      "learning_rate": 6.480476497452613e-05,
+      "loss": 0.819,
+      "step": 27
+    },
+    {
+      "epoch": 0.056338028169014086,
+      "grad_norm": 1.6434446573257446,
+      "learning_rate": 6.47811471647646e-05,
+      "loss": 0.8671,
+      "step": 28
+    },
+    {
+      "epoch": 0.05835010060362173,
+      "grad_norm": 1.5787513256072998,
+      "learning_rate": 6.475618600470322e-05,
+      "loss": 0.7992,
+      "step": 29
+    },
+    {
+      "epoch": 0.060362173038229376,
+      "grad_norm": 1.4350961446762085,
+      "learning_rate": 6.472988253307773e-05,
+      "loss": 0.7524,
+      "step": 30
+    },
+    {
+      "epoch": 0.06237424547283702,
+      "grad_norm": 1.391878604888916,
+      "learning_rate": 6.470223784448298e-05,
+      "loss": 0.7541,
+      "step": 31
+    },
+    {
+      "epoch": 0.06438631790744467,
+      "grad_norm": 1.4117164611816406,
+      "learning_rate": 6.467325308932728e-05,
+      "loss": 0.7899,
+      "step": 32
+    },
+    {
+      "epoch": 0.06639839034205232,
+      "grad_norm": 1.3123915195465088,
+      "learning_rate": 6.464292947378462e-05,
+      "loss": 0.7402,
+      "step": 33
+    },
+    {
+      "epoch": 0.06841046277665996,
+      "grad_norm": 1.4149091243743896,
+      "learning_rate": 6.46112682597444e-05,
+      "loss": 0.8195,
+      "step": 34
+    },
+    {
+      "epoch": 0.07042253521126761,
+      "grad_norm": 1.2951886653900146,
+      "learning_rate": 6.457827076475899e-05,
+      "loss": 0.7179,
+      "step": 35
+    },
+    {
+      "epoch": 0.07243460764587525,
+      "grad_norm": 1.3390341997146606,
+      "learning_rate": 6.454393836198883e-05,
+      "loss": 0.7973,
+      "step": 36
+    },
+    {
+      "epoch": 0.0744466800804829,
+      "grad_norm": 1.307084560394287,
+      "learning_rate": 6.450827248014535e-05,
+      "loss": 0.7591,
+      "step": 37
+    },
+    {
+      "epoch": 0.07645875251509054,
+      "grad_norm": 1.3605775833129883,
+      "learning_rate": 6.447127460343148e-05,
+      "loss": 0.8085,
+      "step": 38
+    },
+    {
+      "epoch": 0.07847082494969819,
+      "grad_norm": 1.4956183433532715,
+      "learning_rate": 6.443294627147988e-05,
+      "loss": 0.735,
+      "step": 39
+    },
+    {
+      "epoch": 0.08048289738430583,
+      "grad_norm": 1.371940016746521,
+      "learning_rate": 6.439328907928889e-05,
+      "loss": 0.8025,
+      "step": 40
+    },
+    {
+      "epoch": 0.08249496981891348,
+      "grad_norm": 1.4716073274612427,
+      "learning_rate": 6.435230467715615e-05,
+      "loss": 0.7381,
+      "step": 41
+    },
+    {
+      "epoch": 0.08450704225352113,
+      "grad_norm": 1.3676444292068481,
+      "learning_rate": 6.430999477060994e-05,
+      "loss": 0.7601,
+      "step": 42
+    },
+    {
+      "epoch": 0.08651911468812877,
+      "grad_norm": 1.5072672367095947,
+      "learning_rate": 6.426636112033818e-05,
+      "loss": 0.8209,
+      "step": 43
+    },
+    {
+      "epoch": 0.08853118712273642,
+      "grad_norm": 1.3186477422714233,
+      "learning_rate": 6.422140554211511e-05,
+      "loss": 0.777,
+      "step": 44
+    },
+    {
+      "epoch": 0.09054325955734406,
+      "grad_norm": 1.4689198732376099,
+      "learning_rate": 6.417512990672591e-05,
+      "loss": 0.871,
+      "step": 45
+    },
+    {
+      "epoch": 0.0925553319919517,
+      "grad_norm": 1.287394642829895,
+      "learning_rate": 6.412753613988862e-05,
+      "loss": 0.7281,
+      "step": 46
+    },
+    {
+      "epoch": 0.09456740442655935,
+      "grad_norm": 1.1629823446273804,
+      "learning_rate": 6.407862622217414e-05,
+      "loss": 0.715,
+      "step": 47
+    },
+    {
+      "epoch": 0.096579476861167,
+      "grad_norm": 1.2146556377410889,
+      "learning_rate": 6.402840218892381e-05,
+      "loss": 0.6985,
+      "step": 48
+    },
+    {
+      "epoch": 0.09859154929577464,
+      "grad_norm": 1.3280084133148193,
+      "learning_rate": 6.397686613016466e-05,
+      "loss": 0.8195,
+      "step": 49
+    },
+    {
+      "epoch": 0.1006036217303823,
+      "grad_norm": 1.157867193222046,
+      "learning_rate": 6.392402019052244e-05,
+      "loss": 0.7529,
+      "step": 50
+    },
+    {
+      "epoch": 0.10261569416498995,
+      "grad_norm": 1.1449801921844482,
+      "learning_rate": 6.386986656913242e-05,
+      "loss": 0.7834,
+      "step": 51
+    },
+    {
+      "epoch": 0.10462776659959759,
+      "grad_norm": 1.2190605401992798,
+      "learning_rate": 6.381440751954782e-05,
+      "loss": 0.8203,
+      "step": 52
+    },
+    {
+      "epoch": 0.10663983903420524,
+      "grad_norm": 1.2562769651412964,
+      "learning_rate": 6.375764534964608e-05,
+      "loss": 0.7338,
+      "step": 53
+    },
+    {
+      "epoch": 0.10865191146881288,
+      "grad_norm": 1.1834882497787476,
+      "learning_rate": 6.369958242153278e-05,
+      "loss": 0.7489,
+      "step": 54
+    },
+    {
+      "epoch": 0.11066398390342053,
+      "grad_norm": 1.2381786108016968,
+      "learning_rate": 6.364022115144337e-05,
+      "loss": 0.7537,
+      "step": 55
+    },
+    {
+      "epoch": 0.11267605633802817,
+      "grad_norm": 1.256866693496704,
+      "learning_rate": 6.357956400964259e-05,
+      "loss": 0.7725,
+      "step": 56
+    },
+    {
+      "epoch": 0.11468812877263582,
+      "grad_norm": 1.2332978248596191,
+      "learning_rate": 6.351761352032171e-05,
+      "loss": 0.774,
+      "step": 57
+    },
+    {
+      "epoch": 0.11670020120724346,
+      "grad_norm": 1.3557363748550415,
+      "learning_rate": 6.345437226149345e-05,
+      "loss": 0.7877,
+      "step": 58
+    },
+    {
+      "epoch": 0.11871227364185111,
+      "grad_norm": 1.1381844282150269,
+      "learning_rate": 6.338984286488472e-05,
+      "loss": 0.7152,
+      "step": 59
+    },
+    {
+      "epoch": 0.12072434607645875,
+      "grad_norm": 1.147226095199585,
+      "learning_rate": 6.332402801582716e-05,
+      "loss": 0.7713,
+      "step": 60
+    },
+    {
+      "epoch": 0.1227364185110664,
+      "grad_norm": 1.0942986011505127,
+      "learning_rate": 6.325693045314524e-05,
+      "loss": 0.7446,
+      "step": 61
+    },
+    {
+      "epoch": 0.12474849094567404,
+      "grad_norm": 1.233619213104248,
+      "learning_rate": 6.318855296904246e-05,
+      "loss": 0.8107,
+      "step": 62
+    },
+    {
+      "epoch": 0.1267605633802817,
+      "grad_norm": 1.1866984367370605,
+      "learning_rate": 6.311889840898498e-05,
+      "loss": 0.8206,
+      "step": 63
+    },
+    {
+      "epoch": 0.12877263581488935,
+      "grad_norm": 1.176274061203003,
+      "learning_rate": 6.304796967158343e-05,
+      "loss": 0.7813,
+      "step": 64
+    },
+    {
+      "epoch": 0.13078470824949698,
+      "grad_norm": 1.1214070320129395,
+      "learning_rate": 6.297576970847205e-05,
+      "loss": 0.6908,
+      "step": 65
+    },
+    {
+      "epoch": 0.13279678068410464,
+      "grad_norm": 1.0725229978561401,
+      "learning_rate": 6.290230152418603e-05,
+      "loss": 0.756,
+      "step": 66
+    },
+    {
+      "epoch": 0.13480885311871227,
+      "grad_norm": 1.1194369792938232,
+      "learning_rate": 6.28275681760364e-05,
+      "loss": 0.7766,
+      "step": 67
+    },
+    {
+      "epoch": 0.13682092555331993,
+      "grad_norm": 1.090072512626648,
+      "learning_rate": 6.275157277398282e-05,
+      "loss": 0.7856,
+      "step": 68
+    },
+    {
+      "epoch": 0.13883299798792756,
+      "grad_norm": 1.1602994203567505,
+      "learning_rate": 6.267431848050418e-05,
+      "loss": 0.7597,
+      "step": 69
+    },
+    {
+      "epoch": 0.14084507042253522,
+      "grad_norm": 1.0984241962432861,
+      "learning_rate": 6.259580851046697e-05,
+      "loss": 0.7318,
+      "step": 70
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 1.0639097690582275,
+      "learning_rate": 6.251604613099149e-05,
+      "loss": 0.7265,
+      "step": 71
+    },
+    {
+      "epoch": 0.1448692152917505,
+      "grad_norm": 1.0951672792434692,
+      "learning_rate": 6.243503466131597e-05,
+      "loss": 0.7312,
+      "step": 72
+    },
+    {
+      "epoch": 0.14688128772635814,
+      "grad_norm": 1.092551827430725,
+      "learning_rate": 6.235277747265828e-05,
+      "loss": 0.7556,
+      "step": 73
+    },
+    {
+      "epoch": 0.1488933601609658,
+      "grad_norm": 1.1054296493530273,
+      "learning_rate": 6.226927798807585e-05,
+      "loss": 0.8489,
+      "step": 74
+    },
+    {
+      "epoch": 0.15090543259557343,
+      "grad_norm": 1.0174497365951538,
+      "learning_rate": 6.218453968232303e-05,
+      "loss": 0.7104,
+      "step": 75
+    },
+    {
+      "epoch": 0.1529175050301811,
+      "grad_norm": 1.146209716796875,
+      "learning_rate": 6.209856608170663e-05,
+      "loss": 0.7276,
+      "step": 76
+    },
+    {
+      "epoch": 0.15492957746478872,
+      "grad_norm": 1.0379316806793213,
+      "learning_rate": 6.201136076393911e-05,
+      "loss": 0.7243,
+      "step": 77
+    },
+    {
+      "epoch": 0.15694164989939638,
+      "grad_norm": 1.0034286975860596,
+      "learning_rate": 6.192292735798967e-05,
+      "loss": 0.7085,
+      "step": 78
+    },
+    {
+      "epoch": 0.158953722334004,
+      "grad_norm": 1.0072968006134033,
+      "learning_rate": 6.183326954393332e-05,
+      "loss": 0.6865,
+      "step": 79
+    },
+    {
+      "epoch": 0.16096579476861167,
+      "grad_norm": 1.0766922235488892,
+      "learning_rate": 6.174239105279768e-05,
+      "loss": 0.7628,
+      "step": 80
+    },
+    {
+      "epoch": 0.16297786720321933,
+      "grad_norm": 1.014816403388977,
+      "learning_rate": 6.16502956664077e-05,
+      "loss": 0.7356,
+      "step": 81
+    },
+    {
+      "epoch": 0.16498993963782696,
+      "grad_norm": 1.055881142616272,
+      "learning_rate": 6.155698721722834e-05,
+      "loss": 0.7763,
+      "step": 82
+    },
+    {
+      "epoch": 0.16700201207243462,
+      "grad_norm": 1.0576510429382324,
+      "learning_rate": 6.146246958820503e-05,
+      "loss": 0.6852,
+      "step": 83
+    },
+    {
+      "epoch": 0.16901408450704225,
+      "grad_norm": 1.2542794942855835,
+      "learning_rate": 6.136674671260213e-05,
+      "loss": 0.7956,
+      "step": 84
+    },
+    {
+      "epoch": 0.1710261569416499,
+      "grad_norm": 1.0826421976089478,
+      "learning_rate": 6.12698225738392e-05,
+      "loss": 0.7285,
+      "step": 85
+    },
+    {
+      "epoch": 0.17303822937625754,
+      "grad_norm": 1.0286874771118164,
+      "learning_rate": 6.11717012053253e-05,
+      "loss": 0.7363,
+      "step": 86
+    },
+    {
+      "epoch": 0.1750503018108652,
+      "grad_norm": 1.1285161972045898,
+      "learning_rate": 6.107238669029108e-05,
+      "loss": 0.7807,
+      "step": 87
+    },
+    {
+      "epoch": 0.17706237424547283,
+      "grad_norm": 2.394617795944214,
+      "learning_rate": 6.0971883161618906e-05,
+      "loss": 0.663,
+      "step": 88
+    },
+    {
+      "epoch": 0.1790744466800805,
+      "grad_norm": 1.0971828699111938,
+      "learning_rate": 6.0870194801670825e-05,
+      "loss": 0.7331,
+      "step": 89
+    },
+    {
+      "epoch": 0.18108651911468812,
+      "grad_norm": 1.0546624660491943,
+      "learning_rate": 6.076732584211459e-05,
+      "loss": 0.7244,
+      "step": 90
+    },
+    {
+      "epoch": 0.18309859154929578,
+      "grad_norm": 1.0969500541687012,
+      "learning_rate": 6.06632805637475e-05,
+      "loss": 0.8122,
+      "step": 91
+    },
+    {
+      "epoch": 0.1851106639839034,
+      "grad_norm": 1.0038318634033203,
+      "learning_rate": 6.055806329631827e-05,
+      "loss": 0.752,
+      "step": 92
+    },
+    {
+      "epoch": 0.18712273641851107,
+      "grad_norm": 1.017544150352478,
+      "learning_rate": 6.045167841834689e-05,
+      "loss": 0.7629,
+      "step": 93
+    },
+    {
+      "epoch": 0.1891348088531187,
+      "grad_norm": 1.0679768323898315,
+      "learning_rate": 6.034413035694237e-05,
+      "loss": 0.7533,
+      "step": 94
+    },
+    {
+      "epoch": 0.19114688128772636,
+      "grad_norm": 1.1002590656280518,
+      "learning_rate": 6.023542358761855e-05,
+      "loss": 0.7566,
+      "step": 95
+    },
+    {
+      "epoch": 0.193158953722334,
+      "grad_norm": 1.0083142518997192,
+      "learning_rate": 6.01255626341078e-05,
+      "loss": 0.6873,
+      "step": 96
+    },
+    {
+      "epoch": 0.19517102615694165,
+      "grad_norm": 1.897566318511963,
+      "learning_rate": 6.0014552068172866e-05,
+      "loss": 0.8056,
+      "step": 97
+    },
+    {
+      "epoch": 0.19718309859154928,
+      "grad_norm": 0.995782732963562,
+      "learning_rate": 5.990239650941649e-05,
+      "loss": 0.7062,
+      "step": 98
+    },
+    {
+      "epoch": 0.19919517102615694,
+      "grad_norm": 0.9380747079849243,
+      "learning_rate": 5.97891006250893e-05,
+      "loss": 0.6674,
+      "step": 99
+    },
+    {
+      "epoch": 0.2012072434607646,
+      "grad_norm": 1.0377370119094849,
+      "learning_rate": 5.967466912989547e-05,
+      "loss": 0.7425,
+      "step": 100
+    },
+    {
+      "epoch": 0.20321931589537223,
+      "grad_norm": 0.9492895603179932,
+      "learning_rate": 5.955910678579663e-05,
+      "loss": 0.7232,
+      "step": 101
+    },
+    {
+      "epoch": 0.2052313883299799,
+      "grad_norm": 0.9299039244651794,
+      "learning_rate": 5.9442418401813614e-05,
+      "loss": 0.6996,
+      "step": 102
+    },
+    {
+      "epoch": 0.20724346076458752,
+      "grad_norm": 1.0433120727539062,
+      "learning_rate": 5.932460883382638e-05,
+      "loss": 0.7504,
+      "step": 103
+    },
+    {
+      "epoch": 0.20925553319919518,
+      "grad_norm": 1.02601158618927,
+      "learning_rate": 5.920568298437193e-05,
+      "loss": 0.7691,
+      "step": 104
+    },
+    {
+      "epoch": 0.2112676056338028,
+      "grad_norm": 1.0401028394699097,
+      "learning_rate": 5.90856458024403e-05,
+      "loss": 0.7038,
+      "step": 105
+    },
+    {
+      "epoch": 0.21327967806841047,
+      "grad_norm": 0.9615976214408875,
+      "learning_rate": 5.8964502283268614e-05,
+      "loss": 0.6894,
+      "step": 106
+    },
+    {
+      "epoch": 0.2152917505030181,
+      "grad_norm": 1.0715394020080566,
+      "learning_rate": 5.884225746813317e-05,
+      "loss": 0.762,
+      "step": 107
+    },
+    {
+      "epoch": 0.21730382293762576,
+      "grad_norm": 1.0785269737243652,
+      "learning_rate": 5.871891644413972e-05,
+      "loss": 0.7538,
+      "step": 108
+    },
+    {
+      "epoch": 0.2193158953722334,
+      "grad_norm": 0.9964181780815125,
+      "learning_rate": 5.8594484344011724e-05,
+      "loss": 0.7205,
+      "step": 109
+    },
+    {
+      "epoch": 0.22132796780684105,
+      "grad_norm": 1.0187814235687256,
+      "learning_rate": 5.84689663458768e-05,
+      "loss": 0.6946,
+      "step": 110
+    },
+    {
+      "epoch": 0.22334004024144868,
+      "grad_norm": 0.949118435382843,
+      "learning_rate": 5.834236767305117e-05,
+      "loss": 0.6963,
+      "step": 111
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": 0.9602085947990417,
+      "learning_rate": 5.821469359382237e-05,
+      "loss": 0.7319,
+      "step": 112
+    },
+    {
+      "epoch": 0.22736418511066397,
+      "grad_norm": 0.9620065689086914,
+      "learning_rate": 5.808594942122999e-05,
+      "loss": 0.7442,
+      "step": 113
+    },
+    {
+      "epoch": 0.22937625754527163,
+      "grad_norm": 0.9228153228759766,
+      "learning_rate": 5.795614051284457e-05,
+      "loss": 0.7212,
+      "step": 114
+    },
+    {
+      "epoch": 0.23138832997987926,
+      "grad_norm": 1.029982328414917,
+      "learning_rate": 5.782527227054462e-05,
+      "loss": 0.7445,
+      "step": 115
+    },
+    {
+      "epoch": 0.23340040241448692,
+      "grad_norm": 1.0322256088256836,
+      "learning_rate": 5.769335014029191e-05,
+      "loss": 0.6763,
+      "step": 116
+    },
+    {
+      "epoch": 0.23541247484909456,
+      "grad_norm": 1.071828007698059,
+      "learning_rate": 5.7560379611904754e-05,
+      "loss": 0.7681,
+      "step": 117
+    },
+    {
+      "epoch": 0.23742454728370221,
+      "grad_norm": 1.0592682361602783,
+      "learning_rate": 5.7426366218829596e-05,
+      "loss": 0.7557,
+      "step": 118
+    },
+    {
+      "epoch": 0.23943661971830985,
+      "grad_norm": 1.019776701927185,
+      "learning_rate": 5.729131553791076e-05,
+      "loss": 0.7524,
+      "step": 119
+    },
+    {
+      "epoch": 0.2414486921529175,
+      "grad_norm": 1.0034253597259521,
+      "learning_rate": 5.715523318915832e-05,
+      "loss": 0.7844,
+      "step": 120
+    },
+    {
+      "epoch": 0.24346076458752516,
+      "grad_norm": 1.0709611177444458,
+      "learning_rate": 5.701812483551428e-05,
+      "loss": 0.7771,
+      "step": 121
+    },
+    {
+      "epoch": 0.2454728370221328,
+      "grad_norm": 1.089322805404663,
+      "learning_rate": 5.687999618261688e-05,
+      "loss": 0.7913,
+      "step": 122
+    },
+    {
+      "epoch": 0.24748490945674045,
+      "grad_norm": 0.981561005115509,
+      "learning_rate": 5.6740852978563204e-05,
+      "loss": 0.744,
+      "step": 123
+    },
+    {
+      "epoch": 0.24949698189134809,
+      "grad_norm": 0.9540185928344727,
+      "learning_rate": 5.66007010136699e-05,
+      "loss": 0.7201,
+      "step": 124
+    },
+    {
+      "epoch": 0.2515090543259557,
+      "grad_norm": 1.0497649908065796,
+      "learning_rate": 5.645954612023233e-05,
+      "loss": 0.7942,
+      "step": 125
+    },
+    {
+      "epoch": 0.2535211267605634,
+      "grad_norm": 0.9719651341438293,
+      "learning_rate": 5.631739417228178e-05,
+      "loss": 0.7133,
+      "step": 126
+    },
+    {
+      "epoch": 0.25553319919517103,
+      "grad_norm": 0.9591907858848572,
+      "learning_rate": 5.6174251085341044e-05,
+      "loss": 0.7118,
+      "step": 127
+    },
+    {
+      "epoch": 0.2575452716297787,
+      "grad_norm": 0.999717652797699,
+      "learning_rate": 5.603012281617824e-05,
+      "loss": 0.745,
+      "step": 128
+    },
+    {
+      "epoch": 0.2595573440643863,
+      "grad_norm": 0.984555184841156,
+      "learning_rate": 5.5885015362558974e-05,
+      "loss": 0.7398,
+      "step": 129
+    },
+    {
+      "epoch": 0.26156941649899396,
+      "grad_norm": 1.0207607746124268,
+      "learning_rate": 5.573893476299669e-05,
+      "loss": 0.7432,
+      "step": 130
+    },
+    {
+      "epoch": 0.2635814889336016,
+      "grad_norm": 1.0601558685302734,
+      "learning_rate": 5.55918870965014e-05,
+      "loss": 0.7713,
+      "step": 131
+    },
+    {
+      "epoch": 0.2655935613682093,
+      "grad_norm": 1.0741450786590576,
+      "learning_rate": 5.544387848232677e-05,
+      "loss": 0.7851,
+      "step": 132
+    },
+    {
+      "epoch": 0.2676056338028169,
+      "grad_norm": 1.0342241525650024,
+      "learning_rate": 5.5294915079715334e-05,
+      "loss": 0.7593,
+      "step": 133
+    },
+    {
+      "epoch": 0.26961770623742454,
+      "grad_norm": 0.983668863773346,
+      "learning_rate": 5.514500308764235e-05,
+      "loss": 0.7426,
+      "step": 134
+    },
+    {
+      "epoch": 0.2716297786720322,
+      "grad_norm": 0.9781654477119446,
+      "learning_rate": 5.499414874455771e-05,
+      "loss": 0.7306,
+      "step": 135
+    },
+    {
+      "epoch": 0.27364185110663986,
+      "grad_norm": 1.0362467765808105,
+      "learning_rate": 5.48423583281264e-05,
+      "loss": 0.7742,
+      "step": 136
+    },
+    {
+      "epoch": 0.27565392354124746,
+      "grad_norm": 0.9543638229370117,
+      "learning_rate": 5.4689638154967235e-05,
+      "loss": 0.6956,
+      "step": 137
+    },
+    {
+      "epoch": 0.2776659959758551,
+      "grad_norm": 1.0143051147460938,
+      "learning_rate": 5.453599458038998e-05,
+      "loss": 0.7562,
+      "step": 138
+    },
+    {
+      "epoch": 0.2796780684104628,
+      "grad_norm": 0.9799973368644714,
+      "learning_rate": 5.438143399813095e-05,
+      "loss": 0.7326,
+      "step": 139
+    },
+    {
+      "epoch": 0.28169014084507044,
+      "grad_norm": 0.9217185974121094,
+      "learning_rate": 5.422596284008683e-05,
+      "loss": 0.7464,
+      "step": 140
+    },
+    {
+      "epoch": 0.2837022132796781,
+      "grad_norm": 0.8847222328186035,
+      "learning_rate": 5.4069587576047144e-05,
+      "loss": 0.7148,
+      "step": 141
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.8999807834625244,
+      "learning_rate": 5.39123147134249e-05,
+      "loss": 0.7207,
+      "step": 142
+    },
+    {
+      "epoch": 0.28772635814889336,
+      "grad_norm": 0.9449793100357056,
+      "learning_rate": 5.3754150796985895e-05,
+      "loss": 0.738,
+      "step": 143
+    },
+    {
+      "epoch": 0.289738430583501,
+      "grad_norm": 1.1088876724243164,
+      "learning_rate": 5.359510240857628e-05,
+      "loss": 0.7431,
+      "step": 144
+    },
+    {
+      "epoch": 0.2917505030181087,
+      "grad_norm": 0.931364119052887,
+      "learning_rate": 5.343517616684872e-05,
+      "loss": 0.7132,
+      "step": 145
+    },
+    {
+      "epoch": 0.2937625754527163,
+      "grad_norm": 1.0146406888961792,
+      "learning_rate": 5.327437872698691e-05,
+      "loss": 0.7916,
+      "step": 146
+    },
+    {
+      "epoch": 0.29577464788732394,
+      "grad_norm": 1.0176244974136353,
+      "learning_rate": 5.3112716780428674e-05,
+      "loss": 0.7131,
+      "step": 147
+    },
+    {
+      "epoch": 0.2977867203219316,
+      "grad_norm": 0.9973041415214539,
+      "learning_rate": 5.295019705458749e-05,
+      "loss": 0.7689,
+      "step": 148
+    },
+    {
+      "epoch": 0.29979879275653926,
+      "grad_norm": 1.0221103429794312,
+      "learning_rate": 5.278682631257252e-05,
+      "loss": 0.7762,
+      "step": 149
+    },
+    {
+      "epoch": 0.30181086519114686,
+      "grad_norm": 0.9501760601997375,
+      "learning_rate": 5.2622611352907214e-05,
+      "loss": 0.7103,
+      "step": 150
+    },
+    {
+      "epoch": 0.3038229376257545,
+      "grad_norm": 0.9289485216140747,
+      "learning_rate": 5.245755900924631e-05,
+      "loss": 0.6982,
+      "step": 151
+    },
+    {
+      "epoch": 0.3058350100603622,
+      "grad_norm": 1.4150779247283936,
+      "learning_rate": 5.2291676150091576e-05,
+      "loss": 0.7035,
+      "step": 152
+    },
+    {
+      "epoch": 0.30784708249496984,
+      "grad_norm": 0.9871881008148193,
+      "learning_rate": 5.2124969678505864e-05,
+      "loss": 0.7388,
+      "step": 153
+    },
+    {
+      "epoch": 0.30985915492957744,
+      "grad_norm": 0.9766415357589722,
+      "learning_rate": 5.195744653182594e-05,
+      "loss": 0.7142,
+      "step": 154
+    },
+    {
+      "epoch": 0.3118712273641851,
+      "grad_norm": 0.9838590621948242,
+      "learning_rate": 5.178911368137373e-05,
+      "loss": 0.6978,
+      "step": 155
+    },
+    {
+      "epoch": 0.31388329979879276,
+      "grad_norm": 0.9251114726066589,
+      "learning_rate": 5.1619978132166254e-05,
+      "loss": 0.6737,
+      "step": 156
+    },
+    {
+      "epoch": 0.3158953722334004,
+      "grad_norm": 0.9593889117240906,
+      "learning_rate": 5.145004692262411e-05,
+      "loss": 0.7233,
+      "step": 157
+    },
+    {
+      "epoch": 0.317907444668008,
+      "grad_norm": 0.9678305387496948,
+      "learning_rate": 5.127932712427851e-05,
+      "loss": 0.702,
+      "step": 158
+    },
+    {
+      "epoch": 0.3199195171026157,
+      "grad_norm": 0.9605986475944519,
+      "learning_rate": 5.110782584147718e-05,
+      "loss": 0.7678,
+      "step": 159
+    },
+    {
+      "epoch": 0.32193158953722334,
+      "grad_norm": 0.9980550408363342,
+      "learning_rate": 5.093555021108849e-05,
+      "loss": 0.7299,
+      "step": 160
+    },
+    {
+      "epoch": 0.323943661971831,
+      "grad_norm": 0.9018529057502747,
+      "learning_rate": 5.0762507402204637e-05,
+      "loss": 0.7109,
+      "step": 161
+    },
+    {
+      "epoch": 0.32595573440643866,
+      "grad_norm": 1.1389586925506592,
+      "learning_rate": 5.058870461584322e-05,
+      "loss": 0.7371,
+      "step": 162
+    },
+    {
+      "epoch": 0.32796780684104626,
+      "grad_norm": 1.0409871339797974,
+      "learning_rate": 5.0414149084647644e-05,
+      "loss": 0.8062,
+      "step": 163
+    },
+    {
+      "epoch": 0.3299798792756539,
+      "grad_norm": 0.9527642130851746,
+      "learning_rate": 5.0238848072586037e-05,
+      "loss": 0.7692,
+      "step": 164
+    },
+    {
+      "epoch": 0.3319919517102616,
+      "grad_norm": 0.9563398361206055,
+      "learning_rate": 5.0062808874649074e-05,
+      "loss": 0.737,
+      "step": 165
+    },
+    {
+      "epoch": 0.33400402414486924,
+      "grad_norm": 1.0413488149642944,
+      "learning_rate": 4.9886038816546355e-05,
+      "loss": 0.7503,
+      "step": 166
+    },
+    {
+      "epoch": 0.33601609657947684,
+      "grad_norm": 0.9624356031417847,
+      "learning_rate": 4.970854525440152e-05,
+      "loss": 0.7034,
+      "step": 167
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 0.9548975229263306,
+      "learning_rate": 4.9530335574446196e-05,
+      "loss": 0.7213,
+      "step": 168
+    },
+    {
+      "epoch": 0.34004024144869216,
+      "grad_norm": 0.8841491937637329,
+      "learning_rate": 4.9351417192712596e-05,
+      "loss": 0.685,
+      "step": 169
+    },
+    {
+      "epoch": 0.3420523138832998,
+      "grad_norm": 0.989604115486145,
+      "learning_rate": 4.917179755472491e-05,
+      "loss": 0.6952,
+      "step": 170
+    },
+    {
+      "epoch": 0.3440643863179074,
+      "grad_norm": 0.8883060216903687,
+      "learning_rate": 4.899148413518942e-05,
+      "loss": 0.697,
+      "step": 171
+    },
+    {
+      "epoch": 0.3460764587525151,
+      "grad_norm": 0.8740846514701843,
+      "learning_rate": 4.881048443768356e-05,
+      "loss": 0.7045,
+      "step": 172
+    },
+    {
+      "epoch": 0.34808853118712274,
+      "grad_norm": 0.8820964097976685,
+      "learning_rate": 4.862880599434353e-05,
+      "loss": 0.7007,
+      "step": 173
+    },
+    {
+      "epoch": 0.3501006036217304,
+      "grad_norm": 0.882949709892273,
+      "learning_rate": 4.844645636555094e-05,
+      "loss": 0.693,
+      "step": 174
+    },
+    {
+      "epoch": 0.352112676056338,
+      "grad_norm": 0.952804684638977,
+      "learning_rate": 4.8263443139618176e-05,
+      "loss": 0.7319,
+      "step": 175
+    },
+    {
+      "epoch": 0.35412474849094566,
+      "grad_norm": 0.9323515295982361,
+      "learning_rate": 4.8079773932472584e-05,
+      "loss": 0.7206,
+      "step": 176
+    },
+    {
+      "epoch": 0.3561368209255533,
+      "grad_norm": 1.0918467044830322,
+      "learning_rate": 4.78954563873396e-05,
+      "loss": 0.7152,
+      "step": 177
+    },
+    {
+      "epoch": 0.358148893360161,
+      "grad_norm": 2.0716049671173096,
+      "learning_rate": 4.7710498174424614e-05,
+      "loss": 0.7769,
+      "step": 178
+    },
+    {
+      "epoch": 0.36016096579476864,
+      "grad_norm": 0.9245615601539612,
+      "learning_rate": 4.7524906990593844e-05,
+      "loss": 0.7085,
+      "step": 179
+    },
+    {
+      "epoch": 0.36217303822937624,
+      "grad_norm": 1.0692616701126099,
+      "learning_rate": 4.7338690559054004e-05,
+      "loss": 0.6948,
+      "step": 180
+    },
+    {
+      "epoch": 0.3641851106639839,
+      "grad_norm": 0.8987394571304321,
+      "learning_rate": 4.71518566290309e-05,
+      "loss": 0.7167,
+      "step": 181
+    },
+    {
+      "epoch": 0.36619718309859156,
+      "grad_norm": 0.946850061416626,
+      "learning_rate": 4.6964412975447e-05,
+      "loss": 0.7227,
+      "step": 182
+    },
+    {
+      "epoch": 0.3682092555331992,
+      "grad_norm": 0.9121927618980408,
+      "learning_rate": 4.6776367398597846e-05,
+      "loss": 0.6868,
+      "step": 183
+    },
+    {
+      "epoch": 0.3702213279678068,
+      "grad_norm": 0.8747940063476562,
+      "learning_rate": 4.658772772382744e-05,
+      "loss": 0.6797,
+      "step": 184
+    },
+    {
+      "epoch": 0.3722334004024145,
+      "grad_norm": 0.9101600646972656,
+      "learning_rate": 4.639850180120268e-05,
+      "loss": 0.7636,
+      "step": 185
+    },
+    {
+      "epoch": 0.37424547283702214,
+      "grad_norm": 0.9515472054481506,
+      "learning_rate": 4.620869750518656e-05,
+      "loss": 0.7357,
+      "step": 186
+    },
+    {
+      "epoch": 0.3762575452716298,
+      "grad_norm": 0.9573916792869568,
+      "learning_rate": 4.60183227343106e-05,
+      "loss": 0.7303,
+      "step": 187
+    },
+    {
+      "epoch": 0.3782696177062374,
+      "grad_norm": 0.942021369934082,
+      "learning_rate": 4.582738541084612e-05,
+      "loss": 0.709,
+      "step": 188
+    },
+    {
+      "epoch": 0.38028169014084506,
+      "grad_norm": 0.8716509342193604,
+      "learning_rate": 4.5635893480474474e-05,
+      "loss": 0.6681,
+      "step": 189
+    },
+    {
+      "epoch": 0.3822937625754527,
+      "grad_norm": 0.8702856302261353,
+      "learning_rate": 4.544385491195658e-05,
+      "loss": 0.6902,
+      "step": 190
+    },
+    {
+      "epoch": 0.3843058350100604,
+      "grad_norm": 0.9312735795974731,
+      "learning_rate": 4.525127769680109e-05,
+      "loss": 0.6895,
+      "step": 191
+    },
+    {
+      "epoch": 0.386317907444668,
+      "grad_norm": 0.9693159461021423,
+      "learning_rate": 4.505816984893203e-05,
+      "loss": 0.7286,
+      "step": 192
+    },
+    {
+      "epoch": 0.38832997987927564,
+      "grad_norm": 1.0244489908218384,
+      "learning_rate": 4.486453940435518e-05,
+      "loss": 0.7899,
+      "step": 193
+    },
+    {
+      "epoch": 0.3903420523138833,
+      "grad_norm": 0.970856249332428,
+      "learning_rate": 4.46703944208237e-05,
+      "loss": 0.7176,
+      "step": 194
+    },
+    {
+      "epoch": 0.39235412474849096,
+      "grad_norm": 0.9749726057052612,
+      "learning_rate": 4.447574297750281e-05,
+      "loss": 0.6914,
+      "step": 195
+    },
+    {
+      "epoch": 0.39436619718309857,
+      "grad_norm": 0.9390575885772705,
+      "learning_rate": 4.428059317463363e-05,
+      "loss": 0.7125,
+      "step": 196
+    },
+    {
+      "epoch": 0.3963782696177062,
+      "grad_norm": 0.9480944871902466,
+      "learning_rate": 4.4084953133196e-05,
+      "loss": 0.681,
+      "step": 197
+    },
+    {
+      "epoch": 0.3983903420523139,
+      "grad_norm": 0.9078746438026428,
+      "learning_rate": 4.388883099457064e-05,
+      "loss": 0.6917,
+      "step": 198
+    },
+    {
+      "epoch": 0.40040241448692154,
+      "grad_norm": 0.9508323073387146,
+      "learning_rate": 4.369223492020026e-05,
+      "loss": 0.7082,
+      "step": 199
+    },
+    {
+      "epoch": 0.4024144869215292,
+      "grad_norm": 0.8641968965530396,
+      "learning_rate": 4.3495173091249974e-05,
+      "loss": 0.6343,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 497,
+  "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": 9.14849080860672e+17,
+  "train_batch_size": 15,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05ae03ee70ba5876b3caf4bbc7280e0ee8c8b2ace354431732afbb1143dd28b5
+size 5112