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: axolotl-quants/Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16
+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 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "axolotl-quants/Llama-4-Scout-17B-16E-Linearized-bnb-nf4-bf16",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "shared_expert.down_proj",
+    "self_attn.o_proj",
+    "self_attn.v_proj",
+    "shared_expert.gate_proj",
+    "self_attn.k_proj",
+    "shared_expert.up_proj",
+    "self_attn.q_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:f416cbe1fb2287a328109ac9ae3486311fd35141490ab0ad33bb3c26256d3a72
+size 248004816

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efe9e031ed85df9c22a7e327f1e31aca2bebbd003e8dcd2b8ea91364bccc5353
+size 60910643

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:588fec71680fc47d8ace37c5ec2868728ad7bb0f9c3428eeaadb805a39358f39
+size 1382

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
+size 27948578

trainer_state.json

@@ -0,0 +1,1294 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2501737317581654,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001389854065323141,
+      "grad_norm": 0.7409176826477051,
+      "learning_rate": 3.999721593572758e-05,
+      "loss": 3.5192,
+      "step": 1
+    },
+    {
+      "epoch": 0.002779708130646282,
+      "grad_norm": 0.5615135431289673,
+      "learning_rate": 3.9991646190173924e-05,
+      "loss": 3.4286,
+      "step": 2
+    },
+    {
+      "epoch": 0.004169562195969423,
+      "grad_norm": 0.5854966044425964,
+      "learning_rate": 3.998328611487523e-05,
+      "loss": 3.4286,
+      "step": 3
+    },
+    {
+      "epoch": 0.005559416261292564,
+      "grad_norm": 0.5862582921981812,
+      "learning_rate": 3.997213570983149e-05,
+      "loss": 3.4585,
+      "step": 4
+    },
+    {
+      "epoch": 0.006949270326615705,
+      "grad_norm": 0.5955198407173157,
+      "learning_rate": 3.9958194975042716e-05,
+      "loss": 3.1467,
+      "step": 5
+    },
+    {
+      "epoch": 0.008339124391938846,
+      "grad_norm": 0.6464918851852417,
+      "learning_rate": 3.9941460272530094e-05,
+      "loss": 3.1823,
+      "step": 6
+    },
+    {
+      "epoch": 0.009728978457261988,
+      "grad_norm": 0.6563470959663391,
+      "learning_rate": 3.9921931602293625e-05,
+      "loss": 3.0063,
+      "step": 7
+    },
+    {
+      "epoch": 0.011118832522585128,
+      "grad_norm": 0.7250497341156006,
+      "learning_rate": 3.989960896433331e-05,
+      "loss": 2.9268,
+      "step": 8
+    },
+    {
+      "epoch": 0.01250868658790827,
+      "grad_norm": 0.7942679524421692,
+      "learning_rate": 3.987449599662796e-05,
+      "loss": 2.9488,
+      "step": 9
+    },
+    {
+      "epoch": 0.01389854065323141,
+      "grad_norm": 0.7256530523300171,
+      "learning_rate": 3.984659269917756e-05,
+      "loss": 2.8387,
+      "step": 10
+    },
+    {
+      "epoch": 0.015288394718554551,
+      "grad_norm": 0.96202152967453,
+      "learning_rate": 3.981589907198213e-05,
+      "loss": 2.7071,
+      "step": 11
+    },
+    {
+      "epoch": 0.01667824878387769,
+      "grad_norm": 0.8117583394050598,
+      "learning_rate": 3.978242239099927e-05,
+      "loss": 2.4934,
+      "step": 12
+    },
+    {
+      "epoch": 0.018068102849200834,
+      "grad_norm": 0.9094793796539307,
+      "learning_rate": 3.974616265622899e-05,
+      "loss": 2.6515,
+      "step": 13
+    },
+    {
+      "epoch": 0.019457956914523976,
+      "grad_norm": 0.8784312009811401,
+      "learning_rate": 3.9707127143628895e-05,
+      "loss": 2.2521,
+      "step": 14
+    },
+    {
+      "epoch": 0.020847810979847115,
+      "grad_norm": 0.8378123641014099,
+      "learning_rate": 3.966531585319899e-05,
+      "loss": 2.6406,
+      "step": 15
+    },
+    {
+      "epoch": 0.022237665045170257,
+      "grad_norm": 0.8524578809738159,
+      "learning_rate": 3.962073606089689e-05,
+      "loss": 2.5555,
+      "step": 16
+    },
+    {
+      "epoch": 0.0236275191104934,
+      "grad_norm": 1.0161993503570557,
+      "learning_rate": 3.9573395042680204e-05,
+      "loss": 2.6443,
+      "step": 17
+    },
+    {
+      "epoch": 0.02501737317581654,
+      "grad_norm": 0.8594086766242981,
+      "learning_rate": 3.9523296436527744e-05,
+      "loss": 2.4282,
+      "step": 18
+    },
+    {
+      "epoch": 0.02640722724113968,
+      "grad_norm": 0.8018243312835693,
+      "learning_rate": 3.947044751839712e-05,
+      "loss": 2.2656,
+      "step": 19
+    },
+    {
+      "epoch": 0.02779708130646282,
+      "grad_norm": 0.833044171333313,
+      "learning_rate": 3.9414855564245954e-05,
+      "loss": 2.2516,
+      "step": 20
+    },
+    {
+      "epoch": 0.029186935371785964,
+      "grad_norm": 0.8001306056976318,
+      "learning_rate": 3.935652785003185e-05,
+      "loss": 2.334,
+      "step": 21
+    },
+    {
+      "epoch": 0.030576789437109102,
+      "grad_norm": 1.0083926916122437,
+      "learning_rate": 3.929547528969124e-05,
+      "loss": 2.2434,
+      "step": 22
+    },
+    {
+      "epoch": 0.031966643502432245,
+      "grad_norm": 0.8387123942375183,
+      "learning_rate": 3.923170515918173e-05,
+      "loss": 2.1532,
+      "step": 23
+    },
+    {
+      "epoch": 0.03335649756775538,
+      "grad_norm": 0.8073887825012207,
+      "learning_rate": 3.916522837243974e-05,
+      "loss": 2.3309,
+      "step": 24
+    },
+    {
+      "epoch": 0.03474635163307853,
+      "grad_norm": 0.709004819393158,
+      "learning_rate": 3.90960558434017e-05,
+      "loss": 2.18,
+      "step": 25
+    },
+    {
+      "epoch": 0.03613620569840167,
+      "grad_norm": 0.674148440361023,
+      "learning_rate": 3.9024198486004025e-05,
+      "loss": 2.1713,
+      "step": 26
+    },
+    {
+      "epoch": 0.037526059763724806,
+      "grad_norm": 0.7956393361091614,
+      "learning_rate": 3.894966721418314e-05,
+      "loss": 2.3782,
+      "step": 27
+    },
+    {
+      "epoch": 0.03891591382904795,
+      "grad_norm": 0.6804589629173279,
+      "learning_rate": 3.887247294187546e-05,
+      "loss": 2.1933,
+      "step": 28
+    },
+    {
+      "epoch": 0.04030576789437109,
+      "grad_norm": 1.6819874048233032,
+      "learning_rate": 3.8792630220996216e-05,
+      "loss": 2.2018,
+      "step": 29
+    },
+    {
+      "epoch": 0.04169562195969423,
+      "grad_norm": 0.685869574546814,
+      "learning_rate": 3.871014996548183e-05,
+      "loss": 2.2206,
+      "step": 30
+    },
+    {
+      "epoch": 0.043085476025017375,
+      "grad_norm": 0.6232013702392578,
+      "learning_rate": 3.862505036522634e-05,
+      "loss": 2.1251,
+      "step": 31
+    },
+    {
+      "epoch": 0.04447533009034051,
+      "grad_norm": 0.609855592250824,
+      "learning_rate": 3.853733869618736e-05,
+      "loss": 2.2228,
+      "step": 32
+    },
+    {
+      "epoch": 0.04586518415566365,
+      "grad_norm": 0.6258031725883484,
+      "learning_rate": 3.844703678623773e-05,
+      "loss": 2.2185,
+      "step": 33
+    },
+    {
+      "epoch": 0.0472550382209868,
+      "grad_norm": 0.5621820688247681,
+      "learning_rate": 3.835415554931387e-05,
+      "loss": 2.168,
+      "step": 34
+    },
+    {
+      "epoch": 0.048644892286309936,
+      "grad_norm": 0.5401716828346252,
+      "learning_rate": 3.825871317530982e-05,
+      "loss": 2.175,
+      "step": 35
+    },
+    {
+      "epoch": 0.05003474635163308,
+      "grad_norm": 0.5031033754348755,
+      "learning_rate": 3.816072421614081e-05,
+      "loss": 2.0321,
+      "step": 36
+    },
+    {
+      "epoch": 0.05142460041695622,
+      "grad_norm": 0.49892041087150574,
+      "learning_rate": 3.806021049967967e-05,
+      "loss": 2.2909,
+      "step": 37
+    },
+    {
+      "epoch": 0.05281445448227936,
+      "grad_norm": 0.47056782245635986,
+      "learning_rate": 3.795718293986283e-05,
+      "loss": 2.1851,
+      "step": 38
+    },
+    {
+      "epoch": 0.054204308547602505,
+      "grad_norm": 0.4496292173862457,
+      "learning_rate": 3.785166336456314e-05,
+      "loss": 2.0675,
+      "step": 39
+    },
+    {
+      "epoch": 0.05559416261292564,
+      "grad_norm": 0.473352313041687,
+      "learning_rate": 3.774366996367462e-05,
+      "loss": 2.2851,
+      "step": 40
+    },
+    {
+      "epoch": 0.05698401667824878,
+      "grad_norm": 0.4474506378173828,
+      "learning_rate": 3.7633220927091315e-05,
+      "loss": 2.1041,
+      "step": 41
+    },
+    {
+      "epoch": 0.05837387074357193,
+      "grad_norm": 0.4823157489299774,
+      "learning_rate": 3.752033808268607e-05,
+      "loss": 2.0805,
+      "step": 42
+    },
+    {
+      "epoch": 0.059763724808895066,
+      "grad_norm": 0.45550891757011414,
+      "learning_rate": 3.740503962035291e-05,
+      "loss": 2.2575,
+      "step": 43
+    },
+    {
+      "epoch": 0.061153578874218205,
+      "grad_norm": 0.3821059763431549,
+      "learning_rate": 3.7287347367964685e-05,
+      "loss": 2.1388,
+      "step": 44
+    },
+    {
+      "epoch": 0.06254343293954134,
+      "grad_norm": 0.36882323026657104,
+      "learning_rate": 3.716727951541543e-05,
+      "loss": 2.1219,
+      "step": 45
+    },
+    {
+      "epoch": 0.06393328700486449,
+      "grad_norm": 0.38791537284851074,
+      "learning_rate": 3.7044861528556794e-05,
+      "loss": 2.1315,
+      "step": 46
+    },
+    {
+      "epoch": 0.06532314107018763,
+      "grad_norm": 0.3582218885421753,
+      "learning_rate": 3.692011523526162e-05,
+      "loss": 2.2317,
+      "step": 47
+    },
+    {
+      "epoch": 0.06671299513551077,
+      "grad_norm": 0.329677551984787,
+      "learning_rate": 3.679306246340275e-05,
+      "loss": 2.0869,
+      "step": 48
+    },
+    {
+      "epoch": 0.06810284920083391,
+      "grad_norm": 0.32158908247947693,
+      "learning_rate": 3.6663725040853024e-05,
+      "loss": 2.3178,
+      "step": 49
+    },
+    {
+      "epoch": 0.06949270326615706,
+      "grad_norm": 0.384804904460907,
+      "learning_rate": 3.653212479548529e-05,
+      "loss": 2.1155,
+      "step": 50
+    },
+    {
+      "epoch": 0.07088255733148019,
+      "grad_norm": 0.3261670768260956,
+      "learning_rate": 3.639828719315119e-05,
+      "loss": 2.2381,
+      "step": 51
+    },
+    {
+      "epoch": 0.07227241139680333,
+      "grad_norm": 0.3406740128993988,
+      "learning_rate": 3.626223769970238e-05,
+      "loss": 2.0653,
+      "step": 52
+    },
+    {
+      "epoch": 0.07366226546212648,
+      "grad_norm": 0.32772770524024963,
+      "learning_rate": 3.612400178099051e-05,
+      "loss": 2.0903,
+      "step": 53
+    },
+    {
+      "epoch": 0.07505211952744961,
+      "grad_norm": 0.3069205582141876,
+      "learning_rate": 3.598360126488842e-05,
+      "loss": 1.9182,
+      "step": 54
+    },
+    {
+      "epoch": 0.07644197359277276,
+      "grad_norm": 0.2695797085762024,
+      "learning_rate": 3.5841068893205374e-05,
+      "loss": 1.97,
+      "step": 55
+    },
+    {
+      "epoch": 0.0778318276580959,
+      "grad_norm": 0.37067824602127075,
+      "learning_rate": 3.569642285583541e-05,
+      "loss": 2.2509,
+      "step": 56
+    },
+    {
+      "epoch": 0.07922168172341904,
+      "grad_norm": 0.3385728895664215,
+      "learning_rate": 3.5549695894587785e-05,
+      "loss": 2.2857,
+      "step": 57
+    },
+    {
+      "epoch": 0.08061153578874218,
+      "grad_norm": 0.28427156805992126,
+      "learning_rate": 3.540090983733535e-05,
+      "loss": 2.0356,
+      "step": 58
+    },
+    {
+      "epoch": 0.08200138985406533,
+      "grad_norm": 0.3377193510532379,
+      "learning_rate": 3.5250093787908554e-05,
+      "loss": 2.1744,
+      "step": 59
+    },
+    {
+      "epoch": 0.08339124391938846,
+      "grad_norm": 0.27540090680122375,
+      "learning_rate": 3.509727321215905e-05,
+      "loss": 2.1665,
+      "step": 60
+    },
+    {
+      "epoch": 0.0847810979847116,
+      "grad_norm": 0.3422718644142151,
+      "learning_rate": 3.494248085189611e-05,
+      "loss": 1.9342,
+      "step": 61
+    },
+    {
+      "epoch": 0.08617095205003475,
+      "grad_norm": 0.2574728727340698,
+      "learning_rate": 3.478574217297137e-05,
+      "loss": 2.2009,
+      "step": 62
+    },
+    {
+      "epoch": 0.08756080611535788,
+      "grad_norm": 0.2330848127603531,
+      "learning_rate": 3.462708627921529e-05,
+      "loss": 2.1879,
+      "step": 63
+    },
+    {
+      "epoch": 0.08895066018068103,
+      "grad_norm": 0.2683883309364319,
+      "learning_rate": 3.4466542274458334e-05,
+      "loss": 2.1559,
+      "step": 64
+    },
+    {
+      "epoch": 0.09034051424600417,
+      "grad_norm": 0.21715426445007324,
+      "learning_rate": 3.430413926253095e-05,
+      "loss": 2.0487,
+      "step": 65
+    },
+    {
+      "epoch": 0.0917303683113273,
+      "grad_norm": 0.23342643678188324,
+      "learning_rate": 3.413990998524241e-05,
+      "loss": 2.1284,
+      "step": 66
+    },
+    {
+      "epoch": 0.09312022237665045,
+      "grad_norm": 0.2351645976305008,
+      "learning_rate": 3.397387990844436e-05,
+      "loss": 2.113,
+      "step": 67
+    },
+    {
+      "epoch": 0.0945100764419736,
+      "grad_norm": 0.352430135011673,
+      "learning_rate": 3.380608541192487e-05,
+      "loss": 2.2563,
+      "step": 68
+    },
+    {
+      "epoch": 0.09589993050729674,
+      "grad_norm": 0.2351987361907959,
+      "learning_rate": 3.363655196153559e-05,
+      "loss": 2.1185,
+      "step": 69
+    },
+    {
+      "epoch": 0.09728978457261987,
+      "grad_norm": 0.25391116738319397,
+      "learning_rate": 3.346531229908578e-05,
+      "loss": 1.9646,
+      "step": 70
+    },
+    {
+      "epoch": 0.09867963863794302,
+      "grad_norm": 0.24878591299057007,
+      "learning_rate": 3.3292395528405905e-05,
+      "loss": 1.8972,
+      "step": 71
+    },
+    {
+      "epoch": 0.10006949270326616,
+      "grad_norm": 0.2513987421989441,
+      "learning_rate": 3.311783439130522e-05,
+      "loss": 2.3366,
+      "step": 72
+    },
+    {
+      "epoch": 0.1014593467685893,
+      "grad_norm": 0.22613292932510376,
+      "learning_rate": 3.2941661629593e-05,
+      "loss": 2.0588,
+      "step": 73
+    },
+    {
+      "epoch": 0.10284920083391244,
+      "grad_norm": 0.21839161217212677,
+      "learning_rate": 3.27639099850785e-05,
+      "loss": 2.0658,
+      "step": 74
+    },
+    {
+      "epoch": 0.10423905489923559,
+      "grad_norm": 0.21652136743068695,
+      "learning_rate": 3.2584608561592177e-05,
+      "loss": 1.9668,
+      "step": 75
+    },
+    {
+      "epoch": 0.10562890896455872,
+      "grad_norm": 0.33612847328186035,
+      "learning_rate": 3.2403793738922104e-05,
+      "loss": 1.9812,
+      "step": 76
+    },
+    {
+      "epoch": 0.10701876302988186,
+      "grad_norm": 0.2500985264778137,
+      "learning_rate": 3.2221498258877546e-05,
+      "loss": 1.9848,
+      "step": 77
+    },
+    {
+      "epoch": 0.10840861709520501,
+      "grad_norm": 0.2622527778148651,
+      "learning_rate": 3.203775122528896e-05,
+      "loss": 2.2417,
+      "step": 78
+    },
+    {
+      "epoch": 0.10979847116052814,
+      "grad_norm": 0.22762766480445862,
+      "learning_rate": 3.185258901794441e-05,
+      "loss": 2.2114,
+      "step": 79
+    },
+    {
+      "epoch": 0.11118832522585129,
+      "grad_norm": 0.18959005177021027,
+      "learning_rate": 3.166604437865317e-05,
+      "loss": 1.9689,
+      "step": 80
+    },
+    {
+      "epoch": 0.11257817929117443,
+      "grad_norm": 0.2245381474494934,
+      "learning_rate": 3.1478150049224496e-05,
+      "loss": 2.0861,
+      "step": 81
+    },
+    {
+      "epoch": 0.11396803335649756,
+      "grad_norm": 0.2584340572357178,
+      "learning_rate": 3.1288938771467656e-05,
+      "loss": 2.0639,
+      "step": 82
+    },
+    {
+      "epoch": 0.11535788742182071,
+      "grad_norm": 0.22430986166000366,
+      "learning_rate": 3.109844692517072e-05,
+      "loss": 1.9695,
+      "step": 83
+    },
+    {
+      "epoch": 0.11674774148714386,
+      "grad_norm": 0.27213403582572937,
+      "learning_rate": 3.090670725214295e-05,
+      "loss": 2.0551,
+      "step": 84
+    },
+    {
+      "epoch": 0.11813759555246699,
+      "grad_norm": 0.23510581254959106,
+      "learning_rate": 3.0713752494193614e-05,
+      "loss": 2.1565,
+      "step": 85
+    },
+    {
+      "epoch": 0.11952744961779013,
+      "grad_norm": 0.4063816964626312,
+      "learning_rate": 3.051961903111078e-05,
+      "loss": 2.2242,
+      "step": 86
+    },
+    {
+      "epoch": 0.12091730368311328,
+      "grad_norm": 0.3135417401790619,
+      "learning_rate": 3.032433960470371e-05,
+      "loss": 2.2841,
+      "step": 87
+    },
+    {
+      "epoch": 0.12230715774843641,
+      "grad_norm": 0.2632151246070862,
+      "learning_rate": 3.0127950594760478e-05,
+      "loss": 2.1075,
+      "step": 88
+    },
+    {
+      "epoch": 0.12369701181375956,
+      "grad_norm": 0.2494344264268875,
+      "learning_rate": 2.9930484743090346e-05,
+      "loss": 2.1096,
+      "step": 89
+    },
+    {
+      "epoch": 0.1250868658790827,
+      "grad_norm": 0.2007075548171997,
+      "learning_rate": 2.9731978429481387e-05,
+      "loss": 2.1779,
+      "step": 90
+    },
+    {
+      "epoch": 0.12647671994440585,
+      "grad_norm": 0.21900464594364166,
+      "learning_rate": 2.9532464395742863e-05,
+      "loss": 2.0586,
+      "step": 91
+    },
+    {
+      "epoch": 0.12786657400972898,
+      "grad_norm": 0.2916090190410614,
+      "learning_rate": 2.9331979021662846e-05,
+      "loss": 1.9652,
+      "step": 92
+    },
+    {
+      "epoch": 0.1292564280750521,
+      "grad_norm": 0.25345149636268616,
+      "learning_rate": 2.9130556868040003e-05,
+      "loss": 2.0456,
+      "step": 93
+    },
+    {
+      "epoch": 0.13064628214037527,
+      "grad_norm": 0.33592185378074646,
+      "learning_rate": 2.8928230676683597e-05,
+      "loss": 2.0481,
+      "step": 94
+    },
+    {
+      "epoch": 0.1320361362056984,
+      "grad_norm": 0.2137216031551361,
+      "learning_rate": 2.87250368273817e-05,
+      "loss": 1.9936,
+      "step": 95
+    },
+    {
+      "epoch": 0.13342599027102153,
+      "grad_norm": 0.1986539214849472,
+      "learning_rate": 2.8521011699922383e-05,
+      "loss": 2.101,
+      "step": 96
+    },
+    {
+      "epoch": 0.1348158443363447,
+      "grad_norm": 0.19974084198474884,
+      "learning_rate": 2.8316189855104312e-05,
+      "loss": 2.1086,
+      "step": 97
+    },
+    {
+      "epoch": 0.13620569840166782,
+      "grad_norm": 0.22967414557933807,
+      "learning_rate": 2.8110605853726156e-05,
+      "loss": 1.9475,
+      "step": 98
+    },
+    {
+      "epoch": 0.13759555246699096,
+      "grad_norm": 0.21497172117233276,
+      "learning_rate": 2.790429425658658e-05,
+      "loss": 2.1221,
+      "step": 99
+    },
+    {
+      "epoch": 0.13898540653231412,
+      "grad_norm": 0.2060205489397049,
+      "learning_rate": 2.7697289624484256e-05,
+      "loss": 2.157,
+      "step": 100
+    },
+    {
+      "epoch": 0.14037526059763725,
+      "grad_norm": 0.2061186283826828,
+      "learning_rate": 2.7489626518217847e-05,
+      "loss": 1.9418,
+      "step": 101
+    },
+    {
+      "epoch": 0.14176511466296038,
+      "grad_norm": 0.2318679243326187,
+      "learning_rate": 2.7281341317575425e-05,
+      "loss": 1.9337,
+      "step": 102
+    },
+    {
+      "epoch": 0.14315496872828354,
+      "grad_norm": 0.19199368357658386,
+      "learning_rate": 2.7072468583355658e-05,
+      "loss": 2.1347,
+      "step": 103
+    },
+    {
+      "epoch": 0.14454482279360667,
+      "grad_norm": 0.5738226175308228,
+      "learning_rate": 2.686304105736781e-05,
+      "loss": 1.9709,
+      "step": 104
+    },
+    {
+      "epoch": 0.1459346768589298,
+      "grad_norm": 0.2086687982082367,
+      "learning_rate": 2.665309511939995e-05,
+      "loss": 2.1757,
+      "step": 105
+    },
+    {
+      "epoch": 0.14732453092425296,
+      "grad_norm": 0.18678060173988342,
+      "learning_rate": 2.6442665330250748e-05,
+      "loss": 1.9203,
+      "step": 106
+    },
+    {
+      "epoch": 0.1487143849895761,
+      "grad_norm": 0.24349789321422577,
+      "learning_rate": 2.623178625071887e-05,
+      "loss": 2.0041,
+      "step": 107
+    },
+    {
+      "epoch": 0.15010423905489922,
+      "grad_norm": 0.44293686747550964,
+      "learning_rate": 2.602049062261358e-05,
+      "loss": 2.0651,
+      "step": 108
+    },
+    {
+      "epoch": 0.15149409312022238,
+      "grad_norm": 0.23788246512413025,
+      "learning_rate": 2.5808814825722948e-05,
+      "loss": 2.0853,
+      "step": 109
+    },
+    {
+      "epoch": 0.15288394718554552,
+      "grad_norm": 0.24998068809509277,
+      "learning_rate": 2.5596793420845643e-05,
+      "loss": 2.1346,
+      "step": 110
+    },
+    {
+      "epoch": 0.15427380125086865,
+      "grad_norm": 0.23647256195545197,
+      "learning_rate": 2.5384459149790928e-05,
+      "loss": 1.9715,
+      "step": 111
+    },
+    {
+      "epoch": 0.1556636553161918,
+      "grad_norm": 0.31655153632164,
+      "learning_rate": 2.517184657335747e-05,
+      "loss": 2.0115,
+      "step": 112
+    },
+    {
+      "epoch": 0.15705350938151494,
+      "grad_norm": 0.19617554545402527,
+      "learning_rate": 2.4958988433354534e-05,
+      "loss": 2.0552,
+      "step": 113
+    },
+    {
+      "epoch": 0.15844336344683807,
+      "grad_norm": 0.22154586017131805,
+      "learning_rate": 2.4745919290580787e-05,
+      "loss": 2.0653,
+      "step": 114
+    },
+    {
+      "epoch": 0.15983321751216123,
+      "grad_norm": 0.2188163846731186,
+      "learning_rate": 2.4532671886845492e-05,
+      "loss": 2.2253,
+      "step": 115
+    },
+    {
+      "epoch": 0.16122307157748436,
+      "grad_norm": 0.19053936004638672,
+      "learning_rate": 2.4319278963957913e-05,
+      "loss": 2.0672,
+      "step": 116
+    },
+    {
+      "epoch": 0.1626129256428075,
+      "grad_norm": 0.2588854432106018,
+      "learning_rate": 2.410577508271672e-05,
+      "loss": 2.0342,
+      "step": 117
+    },
+    {
+      "epoch": 0.16400277970813065,
+      "grad_norm": 0.2963363230228424,
+      "learning_rate": 2.389219298493117e-05,
+      "loss": 2.0387,
+      "step": 118
+    },
+    {
+      "epoch": 0.16539263377345378,
+      "grad_norm": 0.23298707604408264,
+      "learning_rate": 2.3678565412410535e-05,
+      "loss": 2.0423,
+      "step": 119
+    },
+    {
+      "epoch": 0.16678248783877692,
+      "grad_norm": 0.20690463483333588,
+      "learning_rate": 2.3464925106964074e-05,
+      "loss": 1.9764,
+      "step": 120
+    },
+    {
+      "epoch": 0.16817234190410008,
+      "grad_norm": 0.23895452916622162,
+      "learning_rate": 2.325130299141165e-05,
+      "loss": 1.9615,
+      "step": 121
+    },
+    {
+      "epoch": 0.1695621959694232,
+      "grad_norm": 0.2269681841135025,
+      "learning_rate": 2.3037731807562523e-05,
+      "loss": 1.8685,
+      "step": 122
+    },
+    {
+      "epoch": 0.17095205003474634,
+      "grad_norm": 0.26502808928489685,
+      "learning_rate": 2.2824242478236556e-05,
+      "loss": 1.9815,
+      "step": 123
+    },
+    {
+      "epoch": 0.1723419041000695,
+      "grad_norm": 0.24106465280056,
+      "learning_rate": 2.2610867745243013e-05,
+      "loss": 2.0057,
+      "step": 124
+    },
+    {
+      "epoch": 0.17373175816539263,
+      "grad_norm": 0.1920744776725769,
+      "learning_rate": 2.2397638531401753e-05,
+      "loss": 1.9905,
+      "step": 125
+    },
+    {
+      "epoch": 0.17512161223071576,
+      "grad_norm": 0.299200177192688,
+      "learning_rate": 2.2184585759532638e-05,
+      "loss": 1.8186,
+      "step": 126
+    },
+    {
+      "epoch": 0.17651146629603892,
+      "grad_norm": 0.21507440507411957,
+      "learning_rate": 2.1971740352455527e-05,
+      "loss": 1.965,
+      "step": 127
+    },
+    {
+      "epoch": 0.17790132036136205,
+      "grad_norm": 0.2105863094329834,
+      "learning_rate": 2.1759131414000876e-05,
+      "loss": 2.115,
+      "step": 128
+    },
+    {
+      "epoch": 0.17929117442668518,
+      "grad_norm": 0.21202439069747925,
+      "learning_rate": 2.154679168597795e-05,
+      "loss": 1.9482,
+      "step": 129
+    },
+    {
+      "epoch": 0.18068102849200834,
+      "grad_norm": 0.21153898537158966,
+      "learning_rate": 2.1334748453227803e-05,
+      "loss": 1.9907,
+      "step": 130
+    },
+    {
+      "epoch": 0.18207088255733148,
+      "grad_norm": 0.22135163843631744,
+      "learning_rate": 2.1123032638570294e-05,
+      "loss": 2.1229,
+      "step": 131
+    },
+    {
+      "epoch": 0.1834607366226546,
+      "grad_norm": 0.2102488875389099,
+      "learning_rate": 2.091167334583588e-05,
+      "loss": 2.1547,
+      "step": 132
+    },
+    {
+      "epoch": 0.18485059068797777,
+      "grad_norm": 0.500489354133606,
+      "learning_rate": 2.070070149784442e-05,
+      "loss": 2.0868,
+      "step": 133
+    },
+    {
+      "epoch": 0.1862404447533009,
+      "grad_norm": 0.3173089325428009,
+      "learning_rate": 2.049014437943697e-05,
+      "loss": 1.8882,
+      "step": 134
+    },
+    {
+      "epoch": 0.18763029881862406,
+      "grad_norm": 0.2581390142440796,
+      "learning_rate": 2.028002927545458e-05,
+      "loss": 2.0773,
+      "step": 135
+    },
+    {
+      "epoch": 0.1890201528839472,
+      "grad_norm": 0.20216765999794006,
+      "learning_rate": 2.007038528972771e-05,
+      "loss": 2.0587,
+      "step": 136
+    },
+    {
+      "epoch": 0.19041000694927032,
+      "grad_norm": 0.20798902213573456,
+      "learning_rate": 1.986123970709741e-05,
+      "loss": 1.9818,
+      "step": 137
+    },
+    {
+      "epoch": 0.19179986101459348,
+      "grad_norm": 0.20478519797325134,
+      "learning_rate": 1.9652619812404737e-05,
+      "loss": 2.1231,
+      "step": 138
+    },
+    {
+      "epoch": 0.1931897150799166,
+      "grad_norm": 0.2358742356300354,
+      "learning_rate": 1.944455289049074e-05,
+      "loss": 1.9059,
+      "step": 139
+    },
+    {
+      "epoch": 0.19457956914523974,
+      "grad_norm": 0.19055970013141632,
+      "learning_rate": 1.9237066226196475e-05,
+      "loss": 1.9074,
+      "step": 140
+    },
+    {
+      "epoch": 0.1959694232105629,
+      "grad_norm": 0.21943627297878265,
+      "learning_rate": 1.9030183466384187e-05,
+      "loss": 1.887,
+      "step": 141
+    },
+    {
+      "epoch": 0.19735927727588604,
+      "grad_norm": 0.20230762660503387,
+      "learning_rate": 1.8823933714884333e-05,
+      "loss": 2.0427,
+      "step": 142
+    },
+    {
+      "epoch": 0.19874913134120917,
+      "grad_norm": 0.2051026076078415,
+      "learning_rate": 1.861834061855916e-05,
+      "loss": 1.8915,
+      "step": 143
+    },
+    {
+      "epoch": 0.20013898540653233,
+      "grad_norm": 1.0352438688278198,
+      "learning_rate": 1.8413429643260315e-05,
+      "loss": 1.9431,
+      "step": 144
+    },
+    {
+      "epoch": 0.20152883947185546,
+      "grad_norm": 0.2811901271343231,
+      "learning_rate": 1.8209228073828854e-05,
+      "loss": 1.897,
+      "step": 145
+    },
+    {
+      "epoch": 0.2029186935371786,
+      "grad_norm": 0.46414074301719666,
+      "learning_rate": 1.8005757738137618e-05,
+      "loss": 2.0354,
+      "step": 146
+    },
+    {
+      "epoch": 0.20430854760250175,
+      "grad_norm": 0.22770829498767853,
+      "learning_rate": 1.7803044102038257e-05,
+      "loss": 2.0427,
+      "step": 147
+    },
+    {
+      "epoch": 0.20569840166782488,
+      "grad_norm": 0.2260872721672058,
+      "learning_rate": 1.7601108993403614e-05,
+      "loss": 1.9558,
+      "step": 148
+    },
+    {
+      "epoch": 0.207088255733148,
+      "grad_norm": 0.1908380687236786,
+      "learning_rate": 1.7399976059095934e-05,
+      "loss": 2.0494,
+      "step": 149
+    },
+    {
+      "epoch": 0.20847810979847117,
+      "grad_norm": 0.19630920886993408,
+      "learning_rate": 1.7199668945977464e-05,
+      "loss": 1.893,
+      "step": 150
+    },
+    {
+      "epoch": 0.2098679638637943,
+      "grad_norm": 0.18318656086921692,
+      "learning_rate": 1.7000209481921047e-05,
+      "loss": 1.8479,
+      "step": 151
+    },
+    {
+      "epoch": 0.21125781792911744,
+      "grad_norm": 0.20488278567790985,
+      "learning_rate": 1.6801621313788928e-05,
+      "loss": 1.9398,
+      "step": 152
+    },
+    {
+      "epoch": 0.2126476719944406,
+      "grad_norm": 0.18846479058265686,
+      "learning_rate": 1.6603924450464547e-05,
+      "loss": 1.8462,
+      "step": 153
+    },
+    {
+      "epoch": 0.21403752605976373,
+      "grad_norm": 0.1990012526512146,
+      "learning_rate": 1.6407140719820745e-05,
+      "loss": 1.8491,
+      "step": 154
+    },
+    {
+      "epoch": 0.21542738012508686,
+      "grad_norm": 0.20991306006908417,
+      "learning_rate": 1.6211291949730366e-05,
+      "loss": 2.0807,
+      "step": 155
+    },
+    {
+      "epoch": 0.21681723419041002,
+      "grad_norm": 0.1805444061756134,
+      "learning_rate": 1.6016396330087446e-05,
+      "loss": 1.8295,
+      "step": 156
+    },
+    {
+      "epoch": 0.21820708825573315,
+      "grad_norm": 0.22825907170772552,
+      "learning_rate": 1.5822475688764825e-05,
+      "loss": 2.0153,
+      "step": 157
+    },
+    {
+      "epoch": 0.21959694232105628,
+      "grad_norm": 0.17874298989772797,
+      "learning_rate": 1.562954821565654e-05,
+      "loss": 1.8857,
+      "step": 158
+    },
+    {
+      "epoch": 0.22098679638637944,
+      "grad_norm": 0.20816968381404877,
+      "learning_rate": 1.5437633919646032e-05,
+      "loss": 2.0169,
+      "step": 159
+    },
+    {
+      "epoch": 0.22237665045170257,
+      "grad_norm": 0.1875351518392563,
+      "learning_rate": 1.5246751900122035e-05,
+      "loss": 2.0116,
+      "step": 160
+    },
+    {
+      "epoch": 0.2237665045170257,
+      "grad_norm": 0.1880957931280136,
+      "learning_rate": 1.5056919437483884e-05,
+      "loss": 1.9458,
+      "step": 161
+    },
+    {
+      "epoch": 0.22515635858234886,
+      "grad_norm": 0.2217608243227005,
+      "learning_rate": 1.4868154721625615e-05,
+      "loss": 2.1639,
+      "step": 162
+    },
+    {
+      "epoch": 0.226546212647672,
+      "grad_norm": 0.21479056775569916,
+      "learning_rate": 1.468047503294656e-05,
+      "loss": 2.0,
+      "step": 163
+    },
+    {
+      "epoch": 0.22793606671299513,
+      "grad_norm": 0.2338622510433197,
+      "learning_rate": 1.4493896742351353e-05,
+      "loss": 2.0731,
+      "step": 164
+    },
+    {
+      "epoch": 0.2293259207783183,
+      "grad_norm": 0.23026101291179657,
+      "learning_rate": 1.4308437130239327e-05,
+      "loss": 2.1193,
+      "step": 165
+    },
+    {
+      "epoch": 0.23071577484364142,
+      "grad_norm": 0.21515104174613953,
+      "learning_rate": 1.4124113477009814e-05,
+      "loss": 1.966,
+      "step": 166
+    },
+    {
+      "epoch": 0.23210562890896455,
+      "grad_norm": 0.22686313092708588,
+      "learning_rate": 1.3940940334578045e-05,
+      "loss": 2.0554,
+      "step": 167
+    },
+    {
+      "epoch": 0.2334954829742877,
+      "grad_norm": 0.22290675342082977,
+      "learning_rate": 1.3758932254859246e-05,
+      "loss": 2.1244,
+      "step": 168
+    },
+    {
+      "epoch": 0.23488533703961084,
+      "grad_norm": 0.19737748801708221,
+      "learning_rate": 1.357810469926335e-05,
+      "loss": 2.0386,
+      "step": 169
+    },
+    {
+      "epoch": 0.23627519110493397,
+      "grad_norm": 0.2284354418516159,
+      "learning_rate": 1.3398472219705582e-05,
+      "loss": 1.9145,
+      "step": 170
+    },
+    {
+      "epoch": 0.23766504517025713,
+      "grad_norm": 0.18580572307109833,
+      "learning_rate": 1.322004845860647e-05,
+      "loss": 1.8991,
+      "step": 171
+    },
+    {
+      "epoch": 0.23905489923558026,
+      "grad_norm": 0.18737782537937164,
+      "learning_rate": 1.3042847058386542e-05,
+      "loss": 1.8709,
+      "step": 172
+    },
+    {
+      "epoch": 0.2404447533009034,
+      "grad_norm": 0.2080836445093155,
+      "learning_rate": 1.2866880751971621e-05,
+      "loss": 1.7018,
+      "step": 173
+    },
+    {
+      "epoch": 0.24183460736622656,
+      "grad_norm": 0.20678725838661194,
+      "learning_rate": 1.2692163181782234e-05,
+      "loss": 1.7609,
+      "step": 174
+    },
+    {
+      "epoch": 0.2432244614315497,
+      "grad_norm": 0.21453110873699188,
+      "learning_rate": 1.2518705261754803e-05,
+      "loss": 2.1415,
+      "step": 175
+    },
+    {
+      "epoch": 0.24461431549687282,
+      "grad_norm": 0.23385198414325714,
+      "learning_rate": 1.234651881532045e-05,
+      "loss": 1.8789,
+      "step": 176
+    },
+    {
+      "epoch": 0.24600416956219598,
+      "grad_norm": 0.18875467777252197,
+      "learning_rate": 1.2175616575405002e-05,
+      "loss": 1.7596,
+      "step": 177
+    },
+    {
+      "epoch": 0.2473940236275191,
+      "grad_norm": 0.22677035629749298,
+      "learning_rate": 1.2006007636955474e-05,
+      "loss": 2.0212,
+      "step": 178
+    },
+    {
+      "epoch": 0.24878387769284224,
+      "grad_norm": 0.16881951689720154,
+      "learning_rate": 1.183770382340299e-05,
+      "loss": 1.7595,
+      "step": 179
+    },
+    {
+      "epoch": 0.2501737317581654,
+      "grad_norm": 0.21647167205810547,
+      "learning_rate": 1.1670714229694568e-05,
+      "loss": 2.1274,
+      "step": 180
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1438,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 180,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.5241420974210417e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:545076fbf36d7ac4864c0363ad726d00793d288ddc0c4167578cda7663213cdc
+size 11704