Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,206 @@
+---
+base_model: vidore/colpaligemma-3b-pt-448-base
+library_name: peft
+tags:
+- base_model:adapter:vidore/colpaligemma-3b-pt-448-base
+- lora
+- transformers
+---
+
+# 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 0.16.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "vidore/colpaligemma-3b-pt-448-base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "gaussian",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
+  "task_type": "FEATURE_EXTRACTION",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a7c6d7481d65b1fd7ff420f46584be91513a1fa7a34a43e509ec7f660891fe7
+size 157210936

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d28abfea36ae0775c9ab2aaf730cedb4d6092c2ecf83dd9c15b946da6abffd
+size 314557835

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 1024,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "ColPaliProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04222137ef832c18854ecd27bd6a5d0873ff446d3a29d25768aebbe7278ac743
+size 14853

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b65e71ba7333c2a63f3aad84eecf79ab463a25481ca66c2fd9271f707462992
+size 14853

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bf0c54ec8cafb88588648413211347a9af6f25d8b5fa8b4450af2694caa8b91
+size 1465

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff84f53c290d0348c4e206da6094ef781cf8c0e482fec8b268a996b32257cfd
+size 34600975

trainer_state.json

@@ -0,0 +1,1662 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5955603681645912,
+  "eval_steps": 200,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027070925825663237,
+      "grad_norm": 6.915613174438477,
+      "learning_rate": 4.838709677419355e-06,
+      "loss": 2.216,
+      "step": 10
+    },
+    {
+      "epoch": 0.005414185165132647,
+      "grad_norm": 7.003312587738037,
+      "learning_rate": 1.0215053763440861e-05,
+      "loss": 2.1383,
+      "step": 20
+    },
+    {
+      "epoch": 0.008121277747698972,
+      "grad_norm": 4.456768989562988,
+      "learning_rate": 1.5591397849462366e-05,
+      "loss": 2.1074,
+      "step": 30
+    },
+    {
+      "epoch": 0.010828370330265295,
+      "grad_norm": 6.111919403076172,
+      "learning_rate": 2.0967741935483873e-05,
+      "loss": 1.8664,
+      "step": 40
+    },
+    {
+      "epoch": 0.01353546291283162,
+      "grad_norm": 8.282320022583008,
+      "learning_rate": 2.6344086021505376e-05,
+      "loss": 1.4276,
+      "step": 50
+    },
+    {
+      "epoch": 0.016242555495397944,
+      "grad_norm": 7.404280662536621,
+      "learning_rate": 3.172043010752688e-05,
+      "loss": 0.8648,
+      "step": 60
+    },
+    {
+      "epoch": 0.018949648077964266,
+      "grad_norm": 16.722442626953125,
+      "learning_rate": 3.7096774193548386e-05,
+      "loss": 0.6635,
+      "step": 70
+    },
+    {
+      "epoch": 0.02165674066053059,
+      "grad_norm": 9.628230094909668,
+      "learning_rate": 4.247311827956989e-05,
+      "loss": 0.5382,
+      "step": 80
+    },
+    {
+      "epoch": 0.024363833243096916,
+      "grad_norm": 5.784783840179443,
+      "learning_rate": 4.78494623655914e-05,
+      "loss": 0.4909,
+      "step": 90
+    },
+    {
+      "epoch": 0.02707092582566324,
+      "grad_norm": 9.453276634216309,
+      "learning_rate": 4.991668980838656e-05,
+      "loss": 0.3097,
+      "step": 100
+    },
+    {
+      "epoch": 0.02977801840822956,
+      "grad_norm": 6.05251932144165,
+      "learning_rate": 4.977783948903082e-05,
+      "loss": 0.2938,
+      "step": 110
+    },
+    {
+      "epoch": 0.03248511099079589,
+      "grad_norm": 2.7414932250976562,
+      "learning_rate": 4.963898916967509e-05,
+      "loss": 0.433,
+      "step": 120
+    },
+    {
+      "epoch": 0.03519220357336221,
+      "grad_norm": 9.005271911621094,
+      "learning_rate": 4.950013885031936e-05,
+      "loss": 0.4313,
+      "step": 130
+    },
+    {
+      "epoch": 0.03789929615592853,
+      "grad_norm": 7.538389682769775,
+      "learning_rate": 4.9361288530963625e-05,
+      "loss": 0.3519,
+      "step": 140
+    },
+    {
+      "epoch": 0.040606388738494856,
+      "grad_norm": 6.26092529296875,
+      "learning_rate": 4.9222438211607894e-05,
+      "loss": 0.3581,
+      "step": 150
+    },
+    {
+      "epoch": 0.04331348132106118,
+      "grad_norm": 7.152598857879639,
+      "learning_rate": 4.908358789225215e-05,
+      "loss": 0.3238,
+      "step": 160
+    },
+    {
+      "epoch": 0.0460205739036275,
+      "grad_norm": 6.930057525634766,
+      "learning_rate": 4.894473757289642e-05,
+      "loss": 0.3203,
+      "step": 170
+    },
+    {
+      "epoch": 0.04872766648619383,
+      "grad_norm": 6.083557605743408,
+      "learning_rate": 4.880588725354068e-05,
+      "loss": 0.2912,
+      "step": 180
+    },
+    {
+      "epoch": 0.051434759068760154,
+      "grad_norm": 5.25084114074707,
+      "learning_rate": 4.866703693418495e-05,
+      "loss": 0.3177,
+      "step": 190
+    },
+    {
+      "epoch": 0.05414185165132648,
+      "grad_norm": 5.197162628173828,
+      "learning_rate": 4.852818661482922e-05,
+      "loss": 0.217,
+      "step": 200
+    },
+    {
+      "epoch": 0.05414185165132648,
+      "eval_loss": 0.21044665575027466,
+      "eval_runtime": 38.4472,
+      "eval_samples_per_second": 13.005,
+      "eval_steps_per_second": 0.832,
+      "step": 200
+    },
+    {
+      "epoch": 0.0568489442338928,
+      "grad_norm": 6.816867828369141,
+      "learning_rate": 4.8389336295473484e-05,
+      "loss": 0.3546,
+      "step": 210
+    },
+    {
+      "epoch": 0.05955603681645912,
+      "grad_norm": 5.185015678405762,
+      "learning_rate": 4.825048597611775e-05,
+      "loss": 0.2319,
+      "step": 220
+    },
+    {
+      "epoch": 0.062263129399025445,
+      "grad_norm": 3.9528026580810547,
+      "learning_rate": 4.811163565676201e-05,
+      "loss": 0.2197,
+      "step": 230
+    },
+    {
+      "epoch": 0.06497022198159177,
+      "grad_norm": 6.212977409362793,
+      "learning_rate": 4.797278533740628e-05,
+      "loss": 0.226,
+      "step": 240
+    },
+    {
+      "epoch": 0.0676773145641581,
+      "grad_norm": 2.5513417720794678,
+      "learning_rate": 4.783393501805055e-05,
+      "loss": 0.1603,
+      "step": 250
+    },
+    {
+      "epoch": 0.07038440714672442,
+      "grad_norm": 4.768312931060791,
+      "learning_rate": 4.769508469869481e-05,
+      "loss": 0.2303,
+      "step": 260
+    },
+    {
+      "epoch": 0.07309149972929074,
+      "grad_norm": 4.091211795806885,
+      "learning_rate": 4.7556234379339074e-05,
+      "loss": 0.2353,
+      "step": 270
+    },
+    {
+      "epoch": 0.07579859231185707,
+      "grad_norm": 3.9319090843200684,
+      "learning_rate": 4.741738405998334e-05,
+      "loss": 0.1893,
+      "step": 280
+    },
+    {
+      "epoch": 0.07850568489442339,
+      "grad_norm": 2.9893264770507812,
+      "learning_rate": 4.7278533740627606e-05,
+      "loss": 0.0983,
+      "step": 290
+    },
+    {
+      "epoch": 0.08121277747698971,
+      "grad_norm": 4.845495700836182,
+      "learning_rate": 4.713968342127187e-05,
+      "loss": 0.2001,
+      "step": 300
+    },
+    {
+      "epoch": 0.08391987005955603,
+      "grad_norm": 6.0109968185424805,
+      "learning_rate": 4.700083310191614e-05,
+      "loss": 0.2549,
+      "step": 310
+    },
+    {
+      "epoch": 0.08662696264212236,
+      "grad_norm": 3.424335241317749,
+      "learning_rate": 4.68619827825604e-05,
+      "loss": 0.1977,
+      "step": 320
+    },
+    {
+      "epoch": 0.08933405522468868,
+      "grad_norm": 2.177932024002075,
+      "learning_rate": 4.6723132463204664e-05,
+      "loss": 0.1989,
+      "step": 330
+    },
+    {
+      "epoch": 0.092041147807255,
+      "grad_norm": 4.684967517852783,
+      "learning_rate": 4.6584282143848933e-05,
+      "loss": 0.1908,
+      "step": 340
+    },
+    {
+      "epoch": 0.09474824038982133,
+      "grad_norm": 5.848077774047852,
+      "learning_rate": 4.6445431824493196e-05,
+      "loss": 0.2058,
+      "step": 350
+    },
+    {
+      "epoch": 0.09745533297238766,
+      "grad_norm": 5.5079264640808105,
+      "learning_rate": 4.6306581505137466e-05,
+      "loss": 0.2388,
+      "step": 360
+    },
+    {
+      "epoch": 0.10016242555495398,
+      "grad_norm": 0.791803777217865,
+      "learning_rate": 4.616773118578173e-05,
+      "loss": 0.2027,
+      "step": 370
+    },
+    {
+      "epoch": 0.10286951813752031,
+      "grad_norm": 3.581902503967285,
+      "learning_rate": 4.602888086642599e-05,
+      "loss": 0.144,
+      "step": 380
+    },
+    {
+      "epoch": 0.10557661072008663,
+      "grad_norm": 1.2181485891342163,
+      "learning_rate": 4.589003054707026e-05,
+      "loss": 0.1063,
+      "step": 390
+    },
+    {
+      "epoch": 0.10828370330265295,
+      "grad_norm": 4.920592308044434,
+      "learning_rate": 4.5751180227714523e-05,
+      "loss": 0.2288,
+      "step": 400
+    },
+    {
+      "epoch": 0.10828370330265295,
+      "eval_loss": 0.13153080642223358,
+      "eval_runtime": 39.8777,
+      "eval_samples_per_second": 12.538,
+      "eval_steps_per_second": 0.802,
+      "step": 400
+    },
+    {
+      "epoch": 0.11099079588521928,
+      "grad_norm": 1.773049235343933,
+      "learning_rate": 4.561232990835879e-05,
+      "loss": 0.1495,
+      "step": 410
+    },
+    {
+      "epoch": 0.1136978884677856,
+      "grad_norm": 2.75878643989563,
+      "learning_rate": 4.547347958900306e-05,
+      "loss": 0.1702,
+      "step": 420
+    },
+    {
+      "epoch": 0.11640498105035192,
+      "grad_norm": 1.618165135383606,
+      "learning_rate": 4.533462926964732e-05,
+      "loss": 0.1347,
+      "step": 430
+    },
+    {
+      "epoch": 0.11911207363291824,
+      "grad_norm": 2.071643114089966,
+      "learning_rate": 4.519577895029159e-05,
+      "loss": 0.1637,
+      "step": 440
+    },
+    {
+      "epoch": 0.12181916621548457,
+      "grad_norm": 2.7518310546875,
+      "learning_rate": 4.505692863093585e-05,
+      "loss": 0.1245,
+      "step": 450
+    },
+    {
+      "epoch": 0.12452625879805089,
+      "grad_norm": 6.924583435058594,
+      "learning_rate": 4.491807831158012e-05,
+      "loss": 0.0917,
+      "step": 460
+    },
+    {
+      "epoch": 0.12723335138061723,
+      "grad_norm": 1.4702112674713135,
+      "learning_rate": 4.477922799222438e-05,
+      "loss": 0.153,
+      "step": 470
+    },
+    {
+      "epoch": 0.12994044396318355,
+      "grad_norm": 1.4525381326675415,
+      "learning_rate": 4.464037767286865e-05,
+      "loss": 0.1356,
+      "step": 480
+    },
+    {
+      "epoch": 0.13264753654574987,
+      "grad_norm": 1.5836750268936157,
+      "learning_rate": 4.4501527353512915e-05,
+      "loss": 0.1632,
+      "step": 490
+    },
+    {
+      "epoch": 0.1353546291283162,
+      "grad_norm": 3.392880439758301,
+      "learning_rate": 4.436267703415718e-05,
+      "loss": 0.2004,
+      "step": 500
+    },
+    {
+      "epoch": 0.13806172171088252,
+      "grad_norm": 1.7115120887756348,
+      "learning_rate": 4.422382671480145e-05,
+      "loss": 0.1089,
+      "step": 510
+    },
+    {
+      "epoch": 0.14076881429344884,
+      "grad_norm": 5.1935811042785645,
+      "learning_rate": 4.408497639544571e-05,
+      "loss": 0.1627,
+      "step": 520
+    },
+    {
+      "epoch": 0.14347590687601516,
+      "grad_norm": 1.8821942806243896,
+      "learning_rate": 4.394612607608998e-05,
+      "loss": 0.1658,
+      "step": 530
+    },
+    {
+      "epoch": 0.1461829994585815,
+      "grad_norm": 7.369962692260742,
+      "learning_rate": 4.380727575673424e-05,
+      "loss": 0.129,
+      "step": 540
+    },
+    {
+      "epoch": 0.1488900920411478,
+      "grad_norm": 6.980068683624268,
+      "learning_rate": 4.3668425437378505e-05,
+      "loss": 0.1077,
+      "step": 550
+    },
+    {
+      "epoch": 0.15159718462371413,
+      "grad_norm": 3.1524200439453125,
+      "learning_rate": 4.3529575118022775e-05,
+      "loss": 0.1809,
+      "step": 560
+    },
+    {
+      "epoch": 0.15430427720628045,
+      "grad_norm": 1.2788898944854736,
+      "learning_rate": 4.339072479866704e-05,
+      "loss": 0.1159,
+      "step": 570
+    },
+    {
+      "epoch": 0.15701136978884678,
+      "grad_norm": 3.4042916297912598,
+      "learning_rate": 4.325187447931131e-05,
+      "loss": 0.1648,
+      "step": 580
+    },
+    {
+      "epoch": 0.1597184623714131,
+      "grad_norm": 1.9807442426681519,
+      "learning_rate": 4.311302415995557e-05,
+      "loss": 0.1419,
+      "step": 590
+    },
+    {
+      "epoch": 0.16242555495397942,
+      "grad_norm": 2.910810708999634,
+      "learning_rate": 4.297417384059983e-05,
+      "loss": 0.1224,
+      "step": 600
+    },
+    {
+      "epoch": 0.16242555495397942,
+      "eval_loss": 0.12276403605937958,
+      "eval_runtime": 41.3732,
+      "eval_samples_per_second": 12.085,
+      "eval_steps_per_second": 0.773,
+      "step": 600
+    },
+    {
+      "epoch": 0.16513264753654575,
+      "grad_norm": 3.0510406494140625,
+      "learning_rate": 4.28353235212441e-05,
+      "loss": 0.1388,
+      "step": 610
+    },
+    {
+      "epoch": 0.16783974011911207,
+      "grad_norm": 3.4809114933013916,
+      "learning_rate": 4.2696473201888365e-05,
+      "loss": 0.1767,
+      "step": 620
+    },
+    {
+      "epoch": 0.1705468327016784,
+      "grad_norm": 0.8834869265556335,
+      "learning_rate": 4.2557622882532634e-05,
+      "loss": 0.1368,
+      "step": 630
+    },
+    {
+      "epoch": 0.17325392528424471,
+      "grad_norm": 4.756887435913086,
+      "learning_rate": 4.24187725631769e-05,
+      "loss": 0.1456,
+      "step": 640
+    },
+    {
+      "epoch": 0.17596101786681104,
+      "grad_norm": 4.665611743927002,
+      "learning_rate": 4.227992224382116e-05,
+      "loss": 0.1507,
+      "step": 650
+    },
+    {
+      "epoch": 0.17866811044937736,
+      "grad_norm": 4.004549503326416,
+      "learning_rate": 4.214107192446543e-05,
+      "loss": 0.1079,
+      "step": 660
+    },
+    {
+      "epoch": 0.18137520303194368,
+      "grad_norm": 5.584454536437988,
+      "learning_rate": 4.200222160510969e-05,
+      "loss": 0.1116,
+      "step": 670
+    },
+    {
+      "epoch": 0.18408229561451,
+      "grad_norm": 6.875036716461182,
+      "learning_rate": 4.186337128575396e-05,
+      "loss": 0.1949,
+      "step": 680
+    },
+    {
+      "epoch": 0.18678938819707633,
+      "grad_norm": 3.8243751525878906,
+      "learning_rate": 4.1724520966398224e-05,
+      "loss": 0.1759,
+      "step": 690
+    },
+    {
+      "epoch": 0.18949648077964265,
+      "grad_norm": 0.9678667783737183,
+      "learning_rate": 4.1585670647042494e-05,
+      "loss": 0.1308,
+      "step": 700
+    },
+    {
+      "epoch": 0.19220357336220897,
+      "grad_norm": 3.1482715606689453,
+      "learning_rate": 4.1446820327686756e-05,
+      "loss": 0.1755,
+      "step": 710
+    },
+    {
+      "epoch": 0.19491066594477532,
+      "grad_norm": 1.77426016330719,
+      "learning_rate": 4.130797000833102e-05,
+      "loss": 0.1097,
+      "step": 720
+    },
+    {
+      "epoch": 0.19761775852734165,
+      "grad_norm": 3.6544015407562256,
+      "learning_rate": 4.116911968897529e-05,
+      "loss": 0.1258,
+      "step": 730
+    },
+    {
+      "epoch": 0.20032485110990797,
+      "grad_norm": 0.3499806225299835,
+      "learning_rate": 4.103026936961955e-05,
+      "loss": 0.1203,
+      "step": 740
+    },
+    {
+      "epoch": 0.2030319436924743,
+      "grad_norm": 1.8539406061172485,
+      "learning_rate": 4.089141905026382e-05,
+      "loss": 0.1,
+      "step": 750
+    },
+    {
+      "epoch": 0.20573903627504062,
+      "grad_norm": 3.3867313861846924,
+      "learning_rate": 4.0752568730908084e-05,
+      "loss": 0.1537,
+      "step": 760
+    },
+    {
+      "epoch": 0.20844612885760694,
+      "grad_norm": 1.560181975364685,
+      "learning_rate": 4.0613718411552346e-05,
+      "loss": 0.1085,
+      "step": 770
+    },
+    {
+      "epoch": 0.21115322144017326,
+      "grad_norm": 4.343753337860107,
+      "learning_rate": 4.0474868092196616e-05,
+      "loss": 0.0756,
+      "step": 780
+    },
+    {
+      "epoch": 0.21386031402273958,
+      "grad_norm": 3.629037857055664,
+      "learning_rate": 4.033601777284088e-05,
+      "loss": 0.1207,
+      "step": 790
+    },
+    {
+      "epoch": 0.2165674066053059,
+      "grad_norm": 2.0169517993927,
+      "learning_rate": 4.019716745348515e-05,
+      "loss": 0.0913,
+      "step": 800
+    },
+    {
+      "epoch": 0.2165674066053059,
+      "eval_loss": 0.11925679445266724,
+      "eval_runtime": 43.8415,
+      "eval_samples_per_second": 11.405,
+      "eval_steps_per_second": 0.73,
+      "step": 800
+    },
+    {
+      "epoch": 0.21927449918787223,
+      "grad_norm": 1.212438941001892,
+      "learning_rate": 4.005831713412941e-05,
+      "loss": 0.0968,
+      "step": 810
+    },
+    {
+      "epoch": 0.22198159177043855,
+      "grad_norm": 2.369439125061035,
+      "learning_rate": 3.9919466814773674e-05,
+      "loss": 0.1065,
+      "step": 820
+    },
+    {
+      "epoch": 0.22468868435300487,
+      "grad_norm": 2.005507469177246,
+      "learning_rate": 3.978061649541794e-05,
+      "loss": 0.1262,
+      "step": 830
+    },
+    {
+      "epoch": 0.2273957769355712,
+      "grad_norm": 7.557380676269531,
+      "learning_rate": 3.9641766176062206e-05,
+      "loss": 0.0766,
+      "step": 840
+    },
+    {
+      "epoch": 0.23010286951813752,
+      "grad_norm": 2.7166643142700195,
+      "learning_rate": 3.9502915856706475e-05,
+      "loss": 0.1746,
+      "step": 850
+    },
+    {
+      "epoch": 0.23280996210070384,
+      "grad_norm": 3.17519211769104,
+      "learning_rate": 3.936406553735074e-05,
+      "loss": 0.1201,
+      "step": 860
+    },
+    {
+      "epoch": 0.23551705468327017,
+      "grad_norm": 2.7503132820129395,
+      "learning_rate": 3.9225215217995e-05,
+      "loss": 0.1404,
+      "step": 870
+    },
+    {
+      "epoch": 0.2382241472658365,
+      "grad_norm": 2.0287389755249023,
+      "learning_rate": 3.9086364898639264e-05,
+      "loss": 0.0795,
+      "step": 880
+    },
+    {
+      "epoch": 0.2409312398484028,
+      "grad_norm": 2.2139947414398193,
+      "learning_rate": 3.894751457928353e-05,
+      "loss": 0.1682,
+      "step": 890
+    },
+    {
+      "epoch": 0.24363833243096913,
+      "grad_norm": 0.06431946903467178,
+      "learning_rate": 3.88086642599278e-05,
+      "loss": 0.0632,
+      "step": 900
+    },
+    {
+      "epoch": 0.24634542501353546,
+      "grad_norm": 3.912949323654175,
+      "learning_rate": 3.8669813940572065e-05,
+      "loss": 0.1254,
+      "step": 910
+    },
+    {
+      "epoch": 0.24905251759610178,
+      "grad_norm": 6.618512153625488,
+      "learning_rate": 3.8530963621216335e-05,
+      "loss": 0.1486,
+      "step": 920
+    },
+    {
+      "epoch": 0.2517596101786681,
+      "grad_norm": 0.78745436668396,
+      "learning_rate": 3.839211330186059e-05,
+      "loss": 0.127,
+      "step": 930
+    },
+    {
+      "epoch": 0.25446670276123445,
+      "grad_norm": 3.2422189712524414,
+      "learning_rate": 3.825326298250486e-05,
+      "loss": 0.1098,
+      "step": 940
+    },
+    {
+      "epoch": 0.25717379534380075,
+      "grad_norm": 2.6565208435058594,
+      "learning_rate": 3.811441266314913e-05,
+      "loss": 0.0979,
+      "step": 950
+    },
+    {
+      "epoch": 0.2598808879263671,
+      "grad_norm": 0.9006327390670776,
+      "learning_rate": 3.797556234379339e-05,
+      "loss": 0.0908,
+      "step": 960
+    },
+    {
+      "epoch": 0.2625879805089334,
+      "grad_norm": 2.5286571979522705,
+      "learning_rate": 3.783671202443766e-05,
+      "loss": 0.1006,
+      "step": 970
+    },
+    {
+      "epoch": 0.26529507309149974,
+      "grad_norm": 3.4348323345184326,
+      "learning_rate": 3.7697861705081925e-05,
+      "loss": 0.1031,
+      "step": 980
+    },
+    {
+      "epoch": 0.26800216567406604,
+      "grad_norm": 4.574017524719238,
+      "learning_rate": 3.755901138572619e-05,
+      "loss": 0.1484,
+      "step": 990
+    },
+    {
+      "epoch": 0.2707092582566324,
+      "grad_norm": 1.7903037071228027,
+      "learning_rate": 3.742016106637046e-05,
+      "loss": 0.0964,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2707092582566324,
+      "eval_loss": 0.12172573804855347,
+      "eval_runtime": 42.6382,
+      "eval_samples_per_second": 11.727,
+      "eval_steps_per_second": 0.75,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2734163508391987,
+      "grad_norm": 4.126545429229736,
+      "learning_rate": 3.728131074701472e-05,
+      "loss": 0.1381,
+      "step": 1010
+    },
+    {
+      "epoch": 0.27612344342176504,
+      "grad_norm": 2.3475353717803955,
+      "learning_rate": 3.714246042765899e-05,
+      "loss": 0.1235,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27883053600433133,
+      "grad_norm": 1.137242078781128,
+      "learning_rate": 3.700361010830325e-05,
+      "loss": 0.1033,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2815376285868977,
+      "grad_norm": 2.257161855697632,
+      "learning_rate": 3.6864759788947515e-05,
+      "loss": 0.1302,
+      "step": 1040
+    },
+    {
+      "epoch": 0.284244721169464,
+      "grad_norm": 8.024300575256348,
+      "learning_rate": 3.672590946959178e-05,
+      "loss": 0.1123,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2869518137520303,
+      "grad_norm": 2.8162035942077637,
+      "learning_rate": 3.658705915023605e-05,
+      "loss": 0.1335,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2896589063345966,
+      "grad_norm": 3.007559299468994,
+      "learning_rate": 3.6448208830880317e-05,
+      "loss": 0.1021,
+      "step": 1070
+    },
+    {
+      "epoch": 0.292365998917163,
+      "grad_norm": 3.705847978591919,
+      "learning_rate": 3.630935851152458e-05,
+      "loss": 0.1044,
+      "step": 1080
+    },
+    {
+      "epoch": 0.29507309149972927,
+      "grad_norm": 3.605656623840332,
+      "learning_rate": 3.617050819216884e-05,
+      "loss": 0.1219,
+      "step": 1090
+    },
+    {
+      "epoch": 0.2977801840822956,
+      "grad_norm": 2.14206600189209,
+      "learning_rate": 3.6031657872813105e-05,
+      "loss": 0.1599,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3004872766648619,
+      "grad_norm": 2.947873830795288,
+      "learning_rate": 3.5892807553457374e-05,
+      "loss": 0.1157,
+      "step": 1110
+    },
+    {
+      "epoch": 0.30319436924742826,
+      "grad_norm": 3.078336715698242,
+      "learning_rate": 3.5753957234101644e-05,
+      "loss": 0.1188,
+      "step": 1120
+    },
+    {
+      "epoch": 0.30590146182999456,
+      "grad_norm": 0.26743820309638977,
+      "learning_rate": 3.5615106914745907e-05,
+      "loss": 0.1042,
+      "step": 1130
+    },
+    {
+      "epoch": 0.3086085544125609,
+      "grad_norm": 3.805241823196411,
+      "learning_rate": 3.547625659539017e-05,
+      "loss": 0.1159,
+      "step": 1140
+    },
+    {
+      "epoch": 0.31131564699512726,
+      "grad_norm": 5.69476318359375,
+      "learning_rate": 3.533740627603443e-05,
+      "loss": 0.1115,
+      "step": 1150
+    },
+    {
+      "epoch": 0.31402273957769355,
+      "grad_norm": 1.543199896812439,
+      "learning_rate": 3.51985559566787e-05,
+      "loss": 0.1228,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3167298321602599,
+      "grad_norm": 6.506993293762207,
+      "learning_rate": 3.5059705637322964e-05,
+      "loss": 0.1327,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3194369247428262,
+      "grad_norm": 4.64252233505249,
+      "learning_rate": 3.4920855317967234e-05,
+      "loss": 0.1452,
+      "step": 1180
+    },
+    {
+      "epoch": 0.32214401732539255,
+      "grad_norm": 1.6929792165756226,
+      "learning_rate": 3.47820049986115e-05,
+      "loss": 0.0785,
+      "step": 1190
+    },
+    {
+      "epoch": 0.32485110990795885,
+      "grad_norm": 4.854442119598389,
+      "learning_rate": 3.464315467925576e-05,
+      "loss": 0.1319,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32485110990795885,
+      "eval_loss": 0.09344498813152313,
+      "eval_runtime": 42.1424,
+      "eval_samples_per_second": 11.865,
+      "eval_steps_per_second": 0.759,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3275582024905252,
+      "grad_norm": 5.581364631652832,
+      "learning_rate": 3.450430435990003e-05,
+      "loss": 0.1049,
+      "step": 1210
+    },
+    {
+      "epoch": 0.3302652950730915,
+      "grad_norm": 2.954586982727051,
+      "learning_rate": 3.436545404054429e-05,
+      "loss": 0.0919,
+      "step": 1220
+    },
+    {
+      "epoch": 0.33297238765565784,
+      "grad_norm": 5.633950233459473,
+      "learning_rate": 3.422660372118856e-05,
+      "loss": 0.1622,
+      "step": 1230
+    },
+    {
+      "epoch": 0.33567948023822414,
+      "grad_norm": 1.8235430717468262,
+      "learning_rate": 3.408775340183283e-05,
+      "loss": 0.1313,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3383865728207905,
+      "grad_norm": 0.5474218726158142,
+      "learning_rate": 3.394890308247709e-05,
+      "loss": 0.0547,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3410936654033568,
+      "grad_norm": 1.9853441715240479,
+      "learning_rate": 3.3810052763121356e-05,
+      "loss": 0.1126,
+      "step": 1260
+    },
+    {
+      "epoch": 0.34380075798592313,
+      "grad_norm": 4.861907482147217,
+      "learning_rate": 3.367120244376562e-05,
+      "loss": 0.1532,
+      "step": 1270
+    },
+    {
+      "epoch": 0.34650785056848943,
+      "grad_norm": 4.035737991333008,
+      "learning_rate": 3.353235212440989e-05,
+      "loss": 0.1483,
+      "step": 1280
+    },
+    {
+      "epoch": 0.3492149431510558,
+      "grad_norm": 2.4256069660186768,
+      "learning_rate": 3.339350180505416e-05,
+      "loss": 0.116,
+      "step": 1290
+    },
+    {
+      "epoch": 0.3519220357336221,
+      "grad_norm": 4.798511505126953,
+      "learning_rate": 3.325465148569842e-05,
+      "loss": 0.1269,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3546291283161884,
+      "grad_norm": 1.485160231590271,
+      "learning_rate": 3.311580116634268e-05,
+      "loss": 0.0906,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3573362208987547,
+      "grad_norm": 2.424042224884033,
+      "learning_rate": 3.2976950846986946e-05,
+      "loss": 0.1337,
+      "step": 1320
+    },
+    {
+      "epoch": 0.36004331348132107,
+      "grad_norm": 3.985996723175049,
+      "learning_rate": 3.2838100527631216e-05,
+      "loss": 0.2552,
+      "step": 1330
+    },
+    {
+      "epoch": 0.36275040606388737,
+      "grad_norm": 1.6792798042297363,
+      "learning_rate": 3.269925020827548e-05,
+      "loss": 0.1659,
+      "step": 1340
+    },
+    {
+      "epoch": 0.3654574986464537,
+      "grad_norm": 1.6179767847061157,
+      "learning_rate": 3.256039988891975e-05,
+      "loss": 0.102,
+      "step": 1350
+    },
+    {
+      "epoch": 0.36816459122902,
+      "grad_norm": 1.6773470640182495,
+      "learning_rate": 3.242154956956401e-05,
+      "loss": 0.0605,
+      "step": 1360
+    },
+    {
+      "epoch": 0.37087168381158636,
+      "grad_norm": 0.5299155116081238,
+      "learning_rate": 3.228269925020827e-05,
+      "loss": 0.1454,
+      "step": 1370
+    },
+    {
+      "epoch": 0.37357877639415266,
+      "grad_norm": 2.9945433139801025,
+      "learning_rate": 3.214384893085254e-05,
+      "loss": 0.1168,
+      "step": 1380
+    },
+    {
+      "epoch": 0.376285868976719,
+      "grad_norm": 2.2801761627197266,
+      "learning_rate": 3.2004998611496805e-05,
+      "loss": 0.1413,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3789929615592853,
+      "grad_norm": 2.4864439964294434,
+      "learning_rate": 3.1866148292141075e-05,
+      "loss": 0.1124,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3789929615592853,
+      "eval_loss": 0.08532879501581192,
+      "eval_runtime": 42.5981,
+      "eval_samples_per_second": 11.738,
+      "eval_steps_per_second": 0.751,
+      "step": 1400
+    },
+    {
+      "epoch": 0.38170005414185165,
+      "grad_norm": 3.092496156692505,
+      "learning_rate": 3.1727297972785345e-05,
+      "loss": 0.1108,
+      "step": 1410
+    },
+    {
+      "epoch": 0.38440714672441795,
+      "grad_norm": 2.173140525817871,
+      "learning_rate": 3.15884476534296e-05,
+      "loss": 0.1207,
+      "step": 1420
+    },
+    {
+      "epoch": 0.3871142393069843,
+      "grad_norm": 0.5932335257530212,
+      "learning_rate": 3.144959733407387e-05,
+      "loss": 0.076,
+      "step": 1430
+    },
+    {
+      "epoch": 0.38982133188955065,
+      "grad_norm": 3.7685434818267822,
+      "learning_rate": 3.131074701471813e-05,
+      "loss": 0.1398,
+      "step": 1440
+    },
+    {
+      "epoch": 0.39252842447211694,
+      "grad_norm": 0.32636183500289917,
+      "learning_rate": 3.11718966953624e-05,
+      "loss": 0.1572,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3952355170546833,
+      "grad_norm": 0.13235528767108917,
+      "learning_rate": 3.1033046376006665e-05,
+      "loss": 0.1008,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3979426096372496,
+      "grad_norm": 2.1381213665008545,
+      "learning_rate": 3.0894196056650935e-05,
+      "loss": 0.0962,
+      "step": 1470
+    },
+    {
+      "epoch": 0.40064970221981594,
+      "grad_norm": 4.74404239654541,
+      "learning_rate": 3.07553457372952e-05,
+      "loss": 0.1425,
+      "step": 1480
+    },
+    {
+      "epoch": 0.40335679480238223,
+      "grad_norm": 2.1296935081481934,
+      "learning_rate": 3.061649541793946e-05,
+      "loss": 0.1344,
+      "step": 1490
+    },
+    {
+      "epoch": 0.4060638873849486,
+      "grad_norm": 0.6475437879562378,
+      "learning_rate": 3.047764509858373e-05,
+      "loss": 0.0721,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4087709799675149,
+      "grad_norm": 1.9603205919265747,
+      "learning_rate": 3.0338794779227992e-05,
+      "loss": 0.0785,
+      "step": 1510
+    },
+    {
+      "epoch": 0.41147807255008123,
+      "grad_norm": 1.7050154209136963,
+      "learning_rate": 3.019994445987226e-05,
+      "loss": 0.0957,
+      "step": 1520
+    },
+    {
+      "epoch": 0.4141851651326475,
+      "grad_norm": 1.2879791259765625,
+      "learning_rate": 3.0061094140516528e-05,
+      "loss": 0.0934,
+      "step": 1530
+    },
+    {
+      "epoch": 0.4168922577152139,
+      "grad_norm": 3.113666296005249,
+      "learning_rate": 2.992224382116079e-05,
+      "loss": 0.0995,
+      "step": 1540
+    },
+    {
+      "epoch": 0.41959935029778017,
+      "grad_norm": 3.428565263748169,
+      "learning_rate": 2.9783393501805057e-05,
+      "loss": 0.1517,
+      "step": 1550
+    },
+    {
+      "epoch": 0.4223064428803465,
+      "grad_norm": 3.6910240650177,
+      "learning_rate": 2.964454318244932e-05,
+      "loss": 0.0736,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4250135354629128,
+      "grad_norm": 0.8222328424453735,
+      "learning_rate": 2.9505692863093586e-05,
+      "loss": 0.1011,
+      "step": 1570
+    },
+    {
+      "epoch": 0.42772062804547917,
+      "grad_norm": 4.943286418914795,
+      "learning_rate": 2.9366842543737855e-05,
+      "loss": 0.1063,
+      "step": 1580
+    },
+    {
+      "epoch": 0.43042772062804546,
+      "grad_norm": 2.139016628265381,
+      "learning_rate": 2.9227992224382118e-05,
+      "loss": 0.106,
+      "step": 1590
+    },
+    {
+      "epoch": 0.4331348132106118,
+      "grad_norm": 0.6075900197029114,
+      "learning_rate": 2.9089141905026384e-05,
+      "loss": 0.1133,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4331348132106118,
+      "eval_loss": 0.0865432620048523,
+      "eval_runtime": 40.5041,
+      "eval_samples_per_second": 12.344,
+      "eval_steps_per_second": 0.79,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4358419057931781,
+      "grad_norm": 3.410069704055786,
+      "learning_rate": 2.8950291585670647e-05,
+      "loss": 0.1261,
+      "step": 1610
+    },
+    {
+      "epoch": 0.43854899837574446,
+      "grad_norm": 4.080138206481934,
+      "learning_rate": 2.8811441266314916e-05,
+      "loss": 0.1168,
+      "step": 1620
+    },
+    {
+      "epoch": 0.44125609095831075,
+      "grad_norm": 1.9477506875991821,
+      "learning_rate": 2.8672590946959176e-05,
+      "loss": 0.118,
+      "step": 1630
+    },
+    {
+      "epoch": 0.4439631835408771,
+      "grad_norm": 2.7804646492004395,
+      "learning_rate": 2.8533740627603445e-05,
+      "loss": 0.086,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4466702761234434,
+      "grad_norm": 0.9319368004798889,
+      "learning_rate": 2.839489030824771e-05,
+      "loss": 0.1907,
+      "step": 1650
+    },
+    {
+      "epoch": 0.44937736870600975,
+      "grad_norm": 0.6775910258293152,
+      "learning_rate": 2.8256039988891974e-05,
+      "loss": 0.1561,
+      "step": 1660
+    },
+    {
+      "epoch": 0.45208446128857604,
+      "grad_norm": 1.9625002145767212,
+      "learning_rate": 2.8117189669536243e-05,
+      "loss": 0.1348,
+      "step": 1670
+    },
+    {
+      "epoch": 0.4547915538711424,
+      "grad_norm": 1.8503785133361816,
+      "learning_rate": 2.7978339350180506e-05,
+      "loss": 0.1543,
+      "step": 1680
+    },
+    {
+      "epoch": 0.4574986464537087,
+      "grad_norm": 0.2912967801094055,
+      "learning_rate": 2.7839489030824772e-05,
+      "loss": 0.0855,
+      "step": 1690
+    },
+    {
+      "epoch": 0.46020573903627504,
+      "grad_norm": 3.9681107997894287,
+      "learning_rate": 2.7700638711469042e-05,
+      "loss": 0.0645,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4629128316188414,
+      "grad_norm": 3.1310055255889893,
+      "learning_rate": 2.75617883921133e-05,
+      "loss": 0.111,
+      "step": 1710
+    },
+    {
+      "epoch": 0.4656199242014077,
+      "grad_norm": 0.8168225288391113,
+      "learning_rate": 2.742293807275757e-05,
+      "loss": 0.0863,
+      "step": 1720
+    },
+    {
+      "epoch": 0.46832701678397404,
+      "grad_norm": 1.4193518161773682,
+      "learning_rate": 2.7284087753401833e-05,
+      "loss": 0.1772,
+      "step": 1730
+    },
+    {
+      "epoch": 0.47103410936654033,
+      "grad_norm": 2.3890655040740967,
+      "learning_rate": 2.71452374340461e-05,
+      "loss": 0.1319,
+      "step": 1740
+    },
+    {
+      "epoch": 0.4737412019491067,
+      "grad_norm": 1.2436351776123047,
+      "learning_rate": 2.7006387114690362e-05,
+      "loss": 0.075,
+      "step": 1750
+    },
+    {
+      "epoch": 0.476448294531673,
+      "grad_norm": 1.5610893964767456,
+      "learning_rate": 2.6867536795334632e-05,
+      "loss": 0.0757,
+      "step": 1760
+    },
+    {
+      "epoch": 0.47915538711423933,
+      "grad_norm": 5.392906188964844,
+      "learning_rate": 2.6728686475978898e-05,
+      "loss": 0.1657,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4818624796968056,
+      "grad_norm": 1.157339096069336,
+      "learning_rate": 2.658983615662316e-05,
+      "loss": 0.0908,
+      "step": 1780
+    },
+    {
+      "epoch": 0.484569572279372,
+      "grad_norm": 2.2501959800720215,
+      "learning_rate": 2.6450985837267427e-05,
+      "loss": 0.0982,
+      "step": 1790
+    },
+    {
+      "epoch": 0.48727666486193827,
+      "grad_norm": 2.779853105545044,
+      "learning_rate": 2.631213551791169e-05,
+      "loss": 0.0733,
+      "step": 1800
+    },
+    {
+      "epoch": 0.48727666486193827,
+      "eval_loss": 0.10408055782318115,
+      "eval_runtime": 40.9974,
+      "eval_samples_per_second": 12.196,
+      "eval_steps_per_second": 0.781,
+      "step": 1800
+    },
+    {
+      "epoch": 0.4899837574445046,
+      "grad_norm": 0.5903124809265137,
+      "learning_rate": 2.617328519855596e-05,
+      "loss": 0.1078,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4926908500270709,
+      "grad_norm": 2.7150614261627197,
+      "learning_rate": 2.6034434879200225e-05,
+      "loss": 0.143,
+      "step": 1820
+    },
+    {
+      "epoch": 0.49539794260963727,
+      "grad_norm": 1.6853638887405396,
+      "learning_rate": 2.5895584559844488e-05,
+      "loss": 0.0694,
+      "step": 1830
+    },
+    {
+      "epoch": 0.49810503519220356,
+      "grad_norm": 2.398505449295044,
+      "learning_rate": 2.5756734240488754e-05,
+      "loss": 0.0983,
+      "step": 1840
+    },
+    {
+      "epoch": 0.5008121277747699,
+      "grad_norm": 1.515865683555603,
+      "learning_rate": 2.5617883921133017e-05,
+      "loss": 0.0916,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5035192203573362,
+      "grad_norm": 2.172353506088257,
+      "learning_rate": 2.5479033601777286e-05,
+      "loss": 0.0996,
+      "step": 1860
+    },
+    {
+      "epoch": 0.5062263129399025,
+      "grad_norm": 0.6916144490242004,
+      "learning_rate": 2.5340183282421552e-05,
+      "loss": 0.0751,
+      "step": 1870
+    },
+    {
+      "epoch": 0.5089334055224689,
+      "grad_norm": 2.9043545722961426,
+      "learning_rate": 2.5201332963065815e-05,
+      "loss": 0.127,
+      "step": 1880
+    },
+    {
+      "epoch": 0.5116404981050352,
+      "grad_norm": 2.2535910606384277,
+      "learning_rate": 2.5062482643710085e-05,
+      "loss": 0.0918,
+      "step": 1890
+    },
+    {
+      "epoch": 0.5143475906876015,
+      "grad_norm": 0.217793807387352,
+      "learning_rate": 2.4923632324354347e-05,
+      "loss": 0.075,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5170546832701678,
+      "grad_norm": 0.3639616072177887,
+      "learning_rate": 2.4784782004998614e-05,
+      "loss": 0.1307,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5197617758527342,
+      "grad_norm": 2.467031240463257,
+      "learning_rate": 2.464593168564288e-05,
+      "loss": 0.084,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5224688684353005,
+      "grad_norm": 1.7595791816711426,
+      "learning_rate": 2.4507081366287142e-05,
+      "loss": 0.1313,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5251759610178668,
+      "grad_norm": 1.6658025979995728,
+      "learning_rate": 2.436823104693141e-05,
+      "loss": 0.1204,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5278830536004331,
+      "grad_norm": 4.211353302001953,
+      "learning_rate": 2.4229380727575675e-05,
+      "loss": 0.1387,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5305901461829995,
+      "grad_norm": 1.0122289657592773,
+      "learning_rate": 2.409053040821994e-05,
+      "loss": 0.0633,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5332972387655658,
+      "grad_norm": 3.7922515869140625,
+      "learning_rate": 2.3951680088864207e-05,
+      "loss": 0.0756,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5360043313481321,
+      "grad_norm": 1.1087652444839478,
+      "learning_rate": 2.381282976950847e-05,
+      "loss": 0.0952,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5387114239306985,
+      "grad_norm": 5.007467269897461,
+      "learning_rate": 2.3673979450152736e-05,
+      "loss": 0.1346,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5414185165132648,
+      "grad_norm": 0.10054272413253784,
+      "learning_rate": 2.3535129130797002e-05,
+      "loss": 0.1087,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5414185165132648,
+      "eval_loss": 0.08383670449256897,
+      "eval_runtime": 39.1001,
+      "eval_samples_per_second": 12.788,
+      "eval_steps_per_second": 0.818,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5441256090958311,
+      "grad_norm": 0.11041736602783203,
+      "learning_rate": 2.3396278811441265e-05,
+      "loss": 0.0928,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5468327016783974,
+      "grad_norm": 1.4950013160705566,
+      "learning_rate": 2.3257428492085534e-05,
+      "loss": 0.0658,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5495397942609638,
+      "grad_norm": 0.5610796213150024,
+      "learning_rate": 2.31185781727298e-05,
+      "loss": 0.1099,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5522468868435301,
+      "grad_norm": 2.5905027389526367,
+      "learning_rate": 2.2979727853374063e-05,
+      "loss": 0.0818,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5549539794260964,
+      "grad_norm": 1.3932690620422363,
+      "learning_rate": 2.284087753401833e-05,
+      "loss": 0.0814,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5576610720086627,
+      "grad_norm": 4.6623854637146,
+      "learning_rate": 2.2702027214662595e-05,
+      "loss": 0.0849,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5603681645912291,
+      "grad_norm": 0.45536836981773376,
+      "learning_rate": 2.2563176895306858e-05,
+      "loss": 0.1134,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5630752571737954,
+      "grad_norm": 1.5323799848556519,
+      "learning_rate": 2.2424326575951127e-05,
+      "loss": 0.0767,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5657823497563617,
+      "grad_norm": 2.6839871406555176,
+      "learning_rate": 2.228547625659539e-05,
+      "loss": 0.16,
+      "step": 2090
+    },
+    {
+      "epoch": 0.568489442338928,
+      "grad_norm": 2.929471731185913,
+      "learning_rate": 2.2146625937239656e-05,
+      "loss": 0.0812,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5711965349214944,
+      "grad_norm": 3.792933702468872,
+      "learning_rate": 2.2007775617883922e-05,
+      "loss": 0.0896,
+      "step": 2110
+    },
+    {
+      "epoch": 0.5739036275040607,
+      "grad_norm": 0.5622618198394775,
+      "learning_rate": 2.1868925298528185e-05,
+      "loss": 0.0672,
+      "step": 2120
+    },
+    {
+      "epoch": 0.576610720086627,
+      "grad_norm": 0.7235398888587952,
+      "learning_rate": 2.1730074979172455e-05,
+      "loss": 0.1283,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5793178126691932,
+      "grad_norm": 1.5156288146972656,
+      "learning_rate": 2.159122465981672e-05,
+      "loss": 0.0606,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5820249052517596,
+      "grad_norm": 1.9470716714859009,
+      "learning_rate": 2.1452374340460984e-05,
+      "loss": 0.0725,
+      "step": 2150
+    },
+    {
+      "epoch": 0.584731997834326,
+      "grad_norm": 3.0913169384002686,
+      "learning_rate": 2.131352402110525e-05,
+      "loss": 0.1057,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5874390904168922,
+      "grad_norm": 0.6105153560638428,
+      "learning_rate": 2.1174673701749516e-05,
+      "loss": 0.1056,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5901461829994585,
+      "grad_norm": 6.130599498748779,
+      "learning_rate": 2.103582338239378e-05,
+      "loss": 0.1188,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5928532755820249,
+      "grad_norm": 3.15583872795105,
+      "learning_rate": 2.0896973063038048e-05,
+      "loss": 0.0966,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5955603681645912,
+      "grad_norm": 3.5246055126190186,
+      "learning_rate": 2.075812274368231e-05,
+      "loss": 0.0945,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5955603681645912,
+      "eval_loss": 0.09864608943462372,
+      "eval_runtime": 42.9692,
+      "eval_samples_per_second": 11.636,
+      "eval_steps_per_second": 0.745,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3694,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0608419004638822e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9bb4d622c9cac10340a7a574f4f6c9af9831334a109246469462e782cf87b9a
+size 5777