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 +1,202 @@
+---
+base_model: google/gemma-3-12b-it
+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 0.15.2

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-3-12b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "lm_head",
+    "embed_tokens"
+  ],
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8deab998fe56b392da785dc09ae9da4ea00ea6e236d2f10571d065cacbcb380c
+size 6218252616

added_tokens.json

@@ -0,0 +1,11 @@
+{
+  "</think>": 262152,
+  "</tool_call>": 262145,
+  "</tool_response>": 262146,
+  "</tools>": 262147,
+  "<image_soft_token>": 262144,
+  "<think>": 262151,
+  "<tool_call>": 262148,
+  "<tool_response>": 262149,
+  "<tools>": 262150
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "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:de7941ab450184385f24f8b9583192eeb15a1ec965529705dc24d5018af2e190
+size 33386076

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

trainer_state.json

@@ -0,0 +1,1218 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 168,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005952380952380952,
+      "grad_norm": 9.777442932128906,
+      "learning_rate": 0.0,
+      "loss": 1.0466,
+      "step": 1
+    },
+    {
+      "epoch": 0.011904761904761904,
+      "grad_norm": 9.990398406982422,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 1.0202,
+      "step": 2
+    },
+    {
+      "epoch": 0.017857142857142856,
+      "grad_norm": 4.0702080726623535,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 1.0372,
+      "step": 3
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 3.9334001541137695,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.9981,
+      "step": 4
+    },
+    {
+      "epoch": 0.02976190476190476,
+      "grad_norm": 1.597848653793335,
+      "learning_rate": 2.4242424242424244e-05,
+      "loss": 0.8703,
+      "step": 5
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 1.0396702289581299,
+      "learning_rate": 3.0303030303030306e-05,
+      "loss": 0.8549,
+      "step": 6
+    },
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 1.0887113809585571,
+      "learning_rate": 3.6363636363636364e-05,
+      "loss": 0.8365,
+      "step": 7
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 0.7733088731765747,
+      "learning_rate": 4.242424242424243e-05,
+      "loss": 0.8323,
+      "step": 8
+    },
+    {
+      "epoch": 0.05357142857142857,
+      "grad_norm": 1.1227962970733643,
+      "learning_rate": 4.848484848484849e-05,
+      "loss": 0.789,
+      "step": 9
+    },
+    {
+      "epoch": 0.05952380952380952,
+      "grad_norm": 0.44949159026145935,
+      "learning_rate": 5.4545454545454546e-05,
+      "loss": 0.7831,
+      "step": 10
+    },
+    {
+      "epoch": 0.06547619047619048,
+      "grad_norm": 0.5854464173316956,
+      "learning_rate": 6.060606060606061e-05,
+      "loss": 0.7654,
+      "step": 11
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.8678174018859863,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.7826,
+      "step": 12
+    },
+    {
+      "epoch": 0.07738095238095238,
+      "grad_norm": 0.35696980357170105,
+      "learning_rate": 7.272727272727273e-05,
+      "loss": 0.7699,
+      "step": 13
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.25360599160194397,
+      "learning_rate": 7.878787878787879e-05,
+      "loss": 0.7555,
+      "step": 14
+    },
+    {
+      "epoch": 0.08928571428571429,
+      "grad_norm": 0.2302754670381546,
+      "learning_rate": 8.484848484848486e-05,
+      "loss": 0.7574,
+      "step": 15
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.25597596168518066,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 0.7647,
+      "step": 16
+    },
+    {
+      "epoch": 0.10119047619047619,
+      "grad_norm": 0.22872565686702728,
+      "learning_rate": 9.696969696969698e-05,
+      "loss": 0.729,
+      "step": 17
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 0.1873745173215866,
+      "learning_rate": 0.00010303030303030303,
+      "loss": 0.714,
+      "step": 18
+    },
+    {
+      "epoch": 0.1130952380952381,
+      "grad_norm": 0.18152189254760742,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.754,
+      "step": 19
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 0.21586984395980835,
+      "learning_rate": 0.00011515151515151516,
+      "loss": 0.7352,
+      "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.2593728303909302,
+      "learning_rate": 0.00012121212121212122,
+      "loss": 0.7023,
+      "step": 21
+    },
+    {
+      "epoch": 0.13095238095238096,
+      "grad_norm": 0.17135585844516754,
+      "learning_rate": 0.00012727272727272728,
+      "loss": 0.7272,
+      "step": 22
+    },
+    {
+      "epoch": 0.13690476190476192,
+      "grad_norm": 0.1786317229270935,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.7325,
+      "step": 23
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.1994478851556778,
+      "learning_rate": 0.0001393939393939394,
+      "loss": 0.735,
+      "step": 24
+    },
+    {
+      "epoch": 0.1488095238095238,
+      "grad_norm": 0.16063907742500305,
+      "learning_rate": 0.00014545454545454546,
+      "loss": 0.7135,
+      "step": 25
+    },
+    {
+      "epoch": 0.15476190476190477,
+      "grad_norm": 0.15729865431785583,
+      "learning_rate": 0.00015151515151515152,
+      "loss": 0.7008,
+      "step": 26
+    },
+    {
+      "epoch": 0.16071428571428573,
+      "grad_norm": 0.13310623168945312,
+      "learning_rate": 0.00015757575757575757,
+      "loss": 0.7205,
+      "step": 27
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.17777495086193085,
+      "learning_rate": 0.00016363636363636366,
+      "loss": 0.7139,
+      "step": 28
+    },
+    {
+      "epoch": 0.17261904761904762,
+      "grad_norm": 0.1588098555803299,
+      "learning_rate": 0.00016969696969696972,
+      "loss": 0.7084,
+      "step": 29
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 0.22337716817855835,
+      "learning_rate": 0.00017575757575757578,
+      "loss": 0.716,
+      "step": 30
+    },
+    {
+      "epoch": 0.18452380952380953,
+      "grad_norm": 0.1471233069896698,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 0.6875,
+      "step": 31
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.26265543699264526,
+      "learning_rate": 0.0001878787878787879,
+      "loss": 0.7153,
+      "step": 32
+    },
+    {
+      "epoch": 0.19642857142857142,
+      "grad_norm": 0.1488102227449417,
+      "learning_rate": 0.00019393939393939395,
+      "loss": 0.7085,
+      "step": 33
+    },
+    {
+      "epoch": 0.20238095238095238,
+      "grad_norm": 0.13356836140155792,
+      "learning_rate": 0.0002,
+      "loss": 0.6814,
+      "step": 34
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.15331007540225983,
+      "learning_rate": 0.00019999462497359466,
+      "loss": 0.6977,
+      "step": 35
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.13369083404541016,
+      "learning_rate": 0.0001999785004721968,
+      "loss": 0.6935,
+      "step": 36
+    },
+    {
+      "epoch": 0.22023809523809523,
+      "grad_norm": 0.1226360872387886,
+      "learning_rate": 0.00019995162822919883,
+      "loss": 0.6949,
+      "step": 37
+    },
+    {
+      "epoch": 0.2261904761904762,
+      "grad_norm": 0.13010923564434052,
+      "learning_rate": 0.00019991401113338104,
+      "loss": 0.6961,
+      "step": 38
+    },
+    {
+      "epoch": 0.23214285714285715,
+      "grad_norm": 0.1279260516166687,
+      "learning_rate": 0.00019986565322860115,
+      "loss": 0.7031,
+      "step": 39
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.13481521606445312,
+      "learning_rate": 0.00019980655971335945,
+      "loss": 0.7104,
+      "step": 40
+    },
+    {
+      "epoch": 0.24404761904761904,
+      "grad_norm": 0.12825317680835724,
+      "learning_rate": 0.00019973673694024,
+      "loss": 0.6988,
+      "step": 41
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.12685425579547882,
+      "learning_rate": 0.0001996561924152278,
+      "loss": 0.6881,
+      "step": 42
+    },
+    {
+      "epoch": 0.25595238095238093,
+      "grad_norm": 0.12878207862377167,
+      "learning_rate": 0.0001995649347969019,
+      "loss": 0.7119,
+      "step": 43
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 0.14662198722362518,
+      "learning_rate": 0.00019946297389550433,
+      "loss": 0.6934,
+      "step": 44
+    },
+    {
+      "epoch": 0.26785714285714285,
+      "grad_norm": 0.12851360440254211,
+      "learning_rate": 0.0001993503206718859,
+      "loss": 0.6927,
+      "step": 45
+    },
+    {
+      "epoch": 0.27380952380952384,
+      "grad_norm": 0.12815622985363007,
+      "learning_rate": 0.00019922698723632767,
+      "loss": 0.6959,
+      "step": 46
+    },
+    {
+      "epoch": 0.27976190476190477,
+      "grad_norm": 0.13864649832248688,
+      "learning_rate": 0.00019909298684723904,
+      "loss": 0.6948,
+      "step": 47
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.13679292798042297,
+      "learning_rate": 0.00019894833390973266,
+      "loss": 0.6738,
+      "step": 48
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.13636942207813263,
+      "learning_rate": 0.0001987930439740757,
+      "loss": 0.6801,
+      "step": 49
+    },
+    {
+      "epoch": 0.2976190476190476,
+      "grad_norm": 0.1284656971693039,
+      "learning_rate": 0.0001986271337340182,
+      "loss": 0.6966,
+      "step": 50
+    },
+    {
+      "epoch": 0.30357142857142855,
+      "grad_norm": 0.14213284850120544,
+      "learning_rate": 0.0001984506210249986,
+      "loss": 0.7011,
+      "step": 51
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 0.1259792149066925,
+      "learning_rate": 0.00019826352482222638,
+      "loss": 0.6949,
+      "step": 52
+    },
+    {
+      "epoch": 0.31547619047619047,
+      "grad_norm": 0.14440137147903442,
+      "learning_rate": 0.0001980658652386421,
+      "loss": 0.6697,
+      "step": 53
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.13951236009597778,
+      "learning_rate": 0.00019785766352275542,
+      "loss": 0.6847,
+      "step": 54
+    },
+    {
+      "epoch": 0.3273809523809524,
+      "grad_norm": 0.14412100613117218,
+      "learning_rate": 0.00019763894205636072,
+      "loss": 0.6996,
+      "step": 55
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.1487567126750946,
+      "learning_rate": 0.00019740972435213115,
+      "loss": 0.6855,
+      "step": 56
+    },
+    {
+      "epoch": 0.3392857142857143,
+      "grad_norm": 0.1544160693883896,
+      "learning_rate": 0.00019717003505109095,
+      "loss": 0.6944,
+      "step": 57
+    },
+    {
+      "epoch": 0.34523809523809523,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019691989991996663,
+      "loss": 0.6903,
+      "step": 58
+    },
+    {
+      "epoch": 0.35119047619047616,
+      "grad_norm": 0.16976267099380493,
+      "learning_rate": 0.00019665934584841682,
+      "loss": 0.6904,
+      "step": 59
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.9541064500808716,
+      "learning_rate": 0.00019638840084614182,
+      "loss": 0.7448,
+      "step": 60
+    },
+    {
+      "epoch": 0.3630952380952381,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019610709403987246,
+      "loss": 0.7507,
+      "step": 61
+    },
+    {
+      "epoch": 0.36904761904761907,
+      "grad_norm": NaN,
+      "learning_rate": 0.000195815455670239,
+      "loss": 0.7467,
+      "step": 62
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.7270437479019165,
+      "learning_rate": 0.0001955135170885202,
+      "loss": 0.7404,
+      "step": 63
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019520131075327298,
+      "loss": 0.7636,
+      "step": 64
+    },
+    {
+      "epoch": 0.3869047619047619,
+      "grad_norm": 0.9643076658248901,
+      "learning_rate": 0.00019487887022684336,
+      "loss": 0.7888,
+      "step": 65
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.6570881605148315,
+      "learning_rate": 0.00019454623017175812,
+      "loss": 0.7447,
+      "step": 66
+    },
+    {
+      "epoch": 0.39880952380952384,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001942034263469989,
+      "loss": 0.6974,
+      "step": 67
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 0.27752581238746643,
+      "learning_rate": 0.00019385049560415794,
+      "loss": 0.7294,
+      "step": 68
+    },
+    {
+      "epoch": 0.4107142857142857,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019348747588347637,
+      "loss": 0.7808,
+      "step": 69
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019311440620976597,
+      "loss": 0.7768,
+      "step": 70
+    },
+    {
+      "epoch": 0.4226190476190476,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019273132668821364,
+      "loss": 0.7695,
+      "step": 71
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.7289093136787415,
+      "learning_rate": 0.00019233827850007027,
+      "loss": 0.7551,
+      "step": 72
+    },
+    {
+      "epoch": 0.43452380952380953,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019193530389822363,
+      "loss": 0.7231,
+      "step": 73
+    },
+    {
+      "epoch": 0.44047619047619047,
+      "grad_norm": 0.47448015213012695,
+      "learning_rate": 0.0001915224462026563,
+      "loss": 0.715,
+      "step": 74
+    },
+    {
+      "epoch": 0.44642857142857145,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001910997497957885,
+      "loss": 0.7635,
+      "step": 75
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 0.730553150177002,
+      "learning_rate": 0.00019066726011770726,
+      "loss": 0.7343,
+      "step": 76
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.5381748080253601,
+      "learning_rate": 0.00019022502366128135,
+      "loss": 0.7316,
+      "step": 77
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001897730879671634,
+      "loss": 0.7176,
+      "step": 78
+    },
+    {
+      "epoch": 0.47023809523809523,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018931150161867916,
+      "loss": 0.6801,
+      "step": 79
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.2901756167411804,
+      "learning_rate": 0.0001888403142366049,
+      "loss": 0.7292,
+      "step": 80
+    },
+    {
+      "epoch": 0.48214285714285715,
+      "grad_norm": 0.8726024031639099,
+      "learning_rate": 0.00018835957647383303,
+      "loss": 0.8004,
+      "step": 81
+    },
+    {
+      "epoch": 0.4880952380952381,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018786934000992688,
+      "loss": 0.7288,
+      "step": 82
+    },
+    {
+      "epoch": 0.49404761904761907,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018736965754556528,
+      "loss": 0.7356,
+      "step": 83
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3493836224079132,
+      "learning_rate": 0.00018686058279687698,
+      "loss": 0.7117,
+      "step": 84
+    },
+    {
+      "epoch": 0.5059523809523809,
+      "grad_norm": 0.8651177883148193,
+      "learning_rate": 0.00018634217048966637,
+      "loss": 0.7657,
+      "step": 85
+    },
+    {
+      "epoch": 0.5119047619047619,
+      "grad_norm": 0.29697635769844055,
+      "learning_rate": 0.0001858144763535302,
+      "loss": 0.7119,
+      "step": 86
+    },
+    {
+      "epoch": 0.5178571428571429,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018527755711586678,
+      "loss": 0.7415,
+      "step": 87
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.4528316557407379,
+      "learning_rate": 0.00018473147049577774,
+      "loss": 0.7175,
+      "step": 88
+    },
+    {
+      "epoch": 0.5297619047619048,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018417627519786315,
+      "loss": 0.7537,
+      "step": 89
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018361203090591071,
+      "loss": 0.7542,
+      "step": 90
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018303879827647975,
+      "loss": 0.7518,
+      "step": 91
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 0.6303791403770447,
+      "learning_rate": 0.00018245663893238075,
+      "loss": 0.7584,
+      "step": 92
+    },
+    {
+      "epoch": 0.5535714285714286,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018186561545605054,
+      "loss": 0.7056,
+      "step": 93
+    },
+    {
+      "epoch": 0.5595238095238095,
+      "grad_norm": 0.4130224287509918,
+      "learning_rate": 0.00018126579138282503,
+      "loss": 0.7339,
+      "step": 94
+    },
+    {
+      "epoch": 0.5654761904761905,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018065723119410884,
+      "loss": 0.7293,
+      "step": 95
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001800400003104436,
+      "loss": 0.7371,
+      "step": 96
+    },
+    {
+      "epoch": 0.5773809523809523,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017941416508447536,
+      "loss": 0.7338,
+      "step": 97
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.5456637144088745,
+      "learning_rate": 0.00017877979279382135,
+      "loss": 0.7373,
+      "step": 98
+    },
+    {
+      "epoch": 0.5892857142857143,
+      "grad_norm": 0.9624040722846985,
+      "learning_rate": 0.0001781369516338378,
+      "loss": 0.7221,
+      "step": 99
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": NaN,
+      "learning_rate": 0.000177485710710289,
+      "loss": 0.6884,
+      "step": 100
+    },
+    {
+      "epoch": 0.6011904761904762,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017682614003191807,
+      "loss": 0.6891,
+      "step": 101
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001761583105029213,
+      "loss": 0.6814,
+      "step": 102
+    },
+    {
+      "epoch": 0.6130952380952381,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017548229391532572,
+      "loss": 0.728,
+      "step": 103
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017479816294127152,
+      "loss": 0.7014,
+      "step": 104
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.18876609206199646,
+      "learning_rate": 0.0001741059911251997,
+      "loss": 0.6979,
+      "step": 105
+    },
+    {
+      "epoch": 0.6309523809523809,
+      "grad_norm": 0.8331655859947205,
+      "learning_rate": 0.00017340585287594604,
+      "loss": 0.8229,
+      "step": 106
+    },
+    {
+      "epoch": 0.6369047619047619,
+      "grad_norm": 0.3347514271736145,
+      "learning_rate": 0.00017269782345874203,
+      "loss": 0.6952,
+      "step": 107
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.3232339024543762,
+      "learning_rate": 0.00017198197898712404,
+      "loss": 0.7005,
+      "step": 108
+    },
+    {
+      "epoch": 0.6488095238095238,
+      "grad_norm": 0.47910553216934204,
+      "learning_rate": 0.00017125839641475072,
+      "loss": 0.7186,
+      "step": 109
+    },
+    {
+      "epoch": 0.6547619047619048,
+      "grad_norm": 0.5297046303749084,
+      "learning_rate": 0.00017052715352713075,
+      "loss": 0.7412,
+      "step": 110
+    },
+    {
+      "epoch": 0.6607142857142857,
+      "grad_norm": 0.27944743633270264,
+      "learning_rate": 0.00016978832893326074,
+      "loss": 0.729,
+      "step": 111
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.29528820514678955,
+      "learning_rate": 0.0001690420020571747,
+      "loss": 0.7299,
+      "step": 112
+    },
+    {
+      "epoch": 0.6726190476190477,
+      "grad_norm": 0.2554149925708771,
+      "learning_rate": 0.00016828825312940592,
+      "loss": 0.7413,
+      "step": 113
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.20665590465068817,
+      "learning_rate": 0.00016752716317836229,
+      "loss": 0.7038,
+      "step": 114
+    },
+    {
+      "epoch": 0.6845238095238095,
+      "grad_norm": 0.1837390661239624,
+      "learning_rate": 0.00016675881402161536,
+      "loss": 0.7124,
+      "step": 115
+    },
+    {
+      "epoch": 0.6904761904761905,
+      "grad_norm": 0.16445870697498322,
+      "learning_rate": 0.00016598328825710533,
+      "loss": 0.7087,
+      "step": 116
+    },
+    {
+      "epoch": 0.6964285714285714,
+      "grad_norm": 0.16310396790504456,
+      "learning_rate": 0.00016520066925426144,
+      "loss": 0.7202,
+      "step": 117
+    },
+    {
+      "epoch": 0.7023809523809523,
+      "grad_norm": 0.31951698660850525,
+      "learning_rate": 0.0001644110411450398,
+      "loss": 0.7107,
+      "step": 118
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.16259659826755524,
+      "learning_rate": 0.00016361448881487914,
+      "loss": 0.735,
+      "step": 119
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.15429353713989258,
+      "learning_rate": 0.0001628110978935756,
+      "loss": 0.6837,
+      "step": 120
+    },
+    {
+      "epoch": 0.7202380952380952,
+      "grad_norm": 0.1663048267364502,
+      "learning_rate": 0.00016200095474607753,
+      "loss": 0.6939,
+      "step": 121
+    },
+    {
+      "epoch": 0.7261904761904762,
+      "grad_norm": 0.23671415448188782,
+      "learning_rate": 0.0001611841464632011,
+      "loss": 0.7126,
+      "step": 122
+    },
+    {
+      "epoch": 0.7321428571428571,
+      "grad_norm": 0.13842295110225677,
+      "learning_rate": 0.00016036076085226814,
+      "loss": 0.7114,
+      "step": 123
+    },
+    {
+      "epoch": 0.7380952380952381,
+      "grad_norm": 0.1538868099451065,
+      "learning_rate": 0.0001595308864276666,
+      "loss": 0.7297,
+      "step": 124
+    },
+    {
+      "epoch": 0.7440476190476191,
+      "grad_norm": 0.14543598890304565,
+      "learning_rate": 0.0001586946124013354,
+      "loss": 0.6717,
+      "step": 125
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.29232776165008545,
+      "learning_rate": 0.00015785202867317407,
+      "loss": 0.6727,
+      "step": 126
+    },
+    {
+      "epoch": 0.7559523809523809,
+      "grad_norm": 0.15757755935192108,
+      "learning_rate": 0.00015700322582137827,
+      "loss": 0.7004,
+      "step": 127
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.13468873500823975,
+      "learning_rate": 0.0001561482950927029,
+      "loss": 0.7022,
+      "step": 128
+    },
+    {
+      "epoch": 0.7678571428571429,
+      "grad_norm": 0.15298475325107574,
+      "learning_rate": 0.00015528732839265272,
+      "loss": 0.7037,
+      "step": 129
+    },
+    {
+      "epoch": 0.7738095238095238,
+      "grad_norm": 0.13249006867408752,
+      "learning_rate": 0.00015442041827560274,
+      "loss": 0.6854,
+      "step": 130
+    },
+    {
+      "epoch": 0.7797619047619048,
+      "grad_norm": 0.134177565574646,
+      "learning_rate": 0.00015354765793484834,
+      "loss": 0.6762,
+      "step": 131
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.12376086413860321,
+      "learning_rate": 0.000152669141192587,
+      "loss": 0.678,
+      "step": 132
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.12841054797172546,
+      "learning_rate": 0.00015178496248983254,
+      "loss": 0.6848,
+      "step": 133
+    },
+    {
+      "epoch": 0.7976190476190477,
+      "grad_norm": 0.14284221827983856,
+      "learning_rate": 0.00015089521687626243,
+      "loss": 0.6801,
+      "step": 134
+    },
+    {
+      "epoch": 0.8035714285714286,
+      "grad_norm": 0.16310954093933105,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.6784,
+      "step": 135
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.31779271364212036,
+      "learning_rate": 0.00014909940809733222,
+      "loss": 0.7084,
+      "step": 136
+    },
+    {
+      "epoch": 0.8154761904761905,
+      "grad_norm": 0.2745242416858673,
+      "learning_rate": 0.00014819353798236427,
+      "loss": 0.6729,
+      "step": 137
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014728248703661182,
+      "loss": 0.686,
+      "step": 138
+    },
+    {
+      "epoch": 0.8273809523809523,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014636635319853275,
+      "loss": 0.6863,
+      "step": 139
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014544523495299842,
+      "loss": 0.6856,
+      "step": 140
+    },
+    {
+      "epoch": 0.8392857142857143,
+      "grad_norm": 0.13249583542346954,
+      "learning_rate": 0.0001445192313207067,
+      "loss": 0.7115,
+      "step": 141
+    },
+    {
+      "epoch": 0.8452380952380952,
+      "grad_norm": 0.9579920768737793,
+      "learning_rate": 0.00014358844184753712,
+      "loss": 0.758,
+      "step": 142
+    },
+    {
+      "epoch": 0.8511904761904762,
+      "grad_norm": 0.8529394865036011,
+      "learning_rate": 0.00014265296659384956,
+      "loss": 0.794,
+      "step": 143
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001417129061237278,
+      "loss": 0.7051,
+      "step": 144
+    },
+    {
+      "epoch": 0.8630952380952381,
+      "grad_norm": 0.3197040259838104,
+      "learning_rate": 0.00014076836149416887,
+      "loss": 0.7122,
+      "step": 145
+    },
+    {
+      "epoch": 0.8690476190476191,
+      "grad_norm": 0.6125820279121399,
+      "learning_rate": 0.00013981943424421932,
+      "loss": 0.7432,
+      "step": 146
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.37258052825927734,
+      "learning_rate": 0.00013886622638405952,
+      "loss": 0.7193,
+      "step": 147
+    },
+    {
+      "epoch": 0.8809523809523809,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013790884038403795,
+      "loss": 0.7056,
+      "step": 148
+    },
+    {
+      "epoch": 0.8869047619047619,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013694737916365517,
+      "loss": 0.7286,
+      "step": 149
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.41245830059051514,
+      "learning_rate": 0.0001359819460805001,
+      "loss": 0.7262,
+      "step": 150
+    },
+    {
+      "epoch": 0.8988095238095238,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013501264491913906,
+      "loss": 0.7652,
+      "step": 151
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.8128747344017029,
+      "learning_rate": 0.00013403957987995882,
+      "loss": 0.7519,
+      "step": 152
+    },
+    {
+      "epoch": 0.9107142857142857,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013306285556796495,
+      "loss": 0.7252,
+      "step": 153
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013208257698153677,
+      "loss": 0.7274,
+      "step": 154
+    },
+    {
+      "epoch": 0.9226190476190477,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013109884950114007,
+      "loss": 0.7298,
+      "step": 155
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013011177887799845,
+      "loss": 0.7546,
+      "step": 156
+    },
+    {
+      "epoch": 0.9345238095238095,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012912147122272523,
+      "loss": 0.7247,
+      "step": 157
+    },
+    {
+      "epoch": 0.9404761904761905,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012812803299391628,
+      "loss": 0.7357,
+      "step": 158
+    },
+    {
+      "epoch": 0.9464285714285714,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001271315709867059,
+      "loss": 0.7334,
+      "step": 159
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.3542296588420868,
+      "learning_rate": 0.00012613219232128608,
+      "loss": 0.7322,
+      "step": 160
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012513000443139112,
+      "loss": 0.7323,
+      "step": 161
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012412511505274844,
+      "loss": 0.7083,
+      "step": 162
+    },
+    {
+      "epoch": 0.9702380952380952,
+      "grad_norm": NaN,
+      "learning_rate": 0.000123117632211497,
+      "loss": 0.7315,
+      "step": 163
+    },
+    {
+      "epoch": 0.9761904761904762,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001221076642125742,
+      "loss": 0.7154,
+      "step": 164
+    },
+    {
+      "epoch": 0.9821428571428571,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012109531962807332,
+      "loss": 0.733,
+      "step": 165
+    },
+    {
+      "epoch": 0.9880952380952381,
+      "grad_norm": 0.4259299337863922,
+      "learning_rate": 0.00012008070728557186,
+      "loss": 0.726,
+      "step": 166
+    },
+    {
+      "epoch": 0.9940476190476191,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011906393625643244,
+      "loss": 0.7351,
+      "step": 167
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011804511584407763,
+      "loss": 0.7286,
+      "step": 168
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.5009281635284424,
+      "eval_runtime": 1968.0548,
+      "eval_samples_per_second": 12.245,
+      "eval_steps_per_second": 0.096,
+      "step": 168
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 336,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4143922966152348e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3f1078e523ce1bda80854e152c01ddf6fd5077d09862baf72e79cc66ff8ddfa
+size 14648