Upload 8 files

README (2).md

@@ -0,0 +1,202 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-8B
+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 0.14.0

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-8B",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccf48890e190974116b26e9b0b3b9e55a94555a75220f3fb8a324146ec42c720
+size 27280152

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:825094d4f2bac7d355d138172a5f4a5308ce6cb1ecc31a4e89a0f067d8783bc1
+size 54633978

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453ed5a8da412b5c48cbc181bb3dea15825e9c61963cccd44c4c01bbb3204293
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:148f5fc75cd8ea02560f86cd9b51cabd4a9c22597046cda2680322175da4aaeb
+size 1064

trainer_state.json

@@ -0,0 +1,792 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9936305732484074,
+  "eval_steps": 500,
+  "global_step": 1059,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.028308563340410473,
+      "grad_norm": 10.472460746765137,
+      "learning_rate": 4.971671388101983e-05,
+      "loss": 5.6874,
+      "step": 10
+    },
+    {
+      "epoch": 0.056617126680820945,
+      "grad_norm": 1.0690819025039673,
+      "learning_rate": 4.9244570349386214e-05,
+      "loss": 1.622,
+      "step": 20
+    },
+    {
+      "epoch": 0.08492569002123142,
+      "grad_norm": 0.6105159521102905,
+      "learning_rate": 4.8772426817752596e-05,
+      "loss": 2.0585,
+      "step": 30
+    },
+    {
+      "epoch": 0.11323425336164189,
+      "grad_norm": 0.9013139009475708,
+      "learning_rate": 4.830028328611898e-05,
+      "loss": 1.3675,
+      "step": 40
+    },
+    {
+      "epoch": 0.14154281670205238,
+      "grad_norm": 1.0703097581863403,
+      "learning_rate": 4.7828139754485365e-05,
+      "loss": 1.7004,
+      "step": 50
+    },
+    {
+      "epoch": 0.16985138004246284,
+      "grad_norm": 0.715630829334259,
+      "learning_rate": 4.7355996222851754e-05,
+      "loss": 1.2608,
+      "step": 60
+    },
+    {
+      "epoch": 0.19815994338287332,
+      "grad_norm": 0.6118766069412231,
+      "learning_rate": 4.6883852691218135e-05,
+      "loss": 1.3334,
+      "step": 70
+    },
+    {
+      "epoch": 0.22646850672328378,
+      "grad_norm": 1.0044665336608887,
+      "learning_rate": 4.641170915958452e-05,
+      "loss": 1.3244,
+      "step": 80
+    },
+    {
+      "epoch": 0.25477707006369427,
+      "grad_norm": 1.927817940711975,
+      "learning_rate": 4.59395656279509e-05,
+      "loss": 1.2348,
+      "step": 90
+    },
+    {
+      "epoch": 0.28308563340410475,
+      "grad_norm": 1.5741430521011353,
+      "learning_rate": 4.546742209631728e-05,
+      "loss": 1.22,
+      "step": 100
+    },
+    {
+      "epoch": 0.31139419674451524,
+      "grad_norm": 0.6977642774581909,
+      "learning_rate": 4.499527856468367e-05,
+      "loss": 1.0786,
+      "step": 110
+    },
+    {
+      "epoch": 0.33970276008492567,
+      "grad_norm": 2.7766706943511963,
+      "learning_rate": 4.452313503305005e-05,
+      "loss": 1.1531,
+      "step": 120
+    },
+    {
+      "epoch": 0.36801132342533616,
+      "grad_norm": 2.0790321826934814,
+      "learning_rate": 4.405099150141643e-05,
+      "loss": 1.0915,
+      "step": 130
+    },
+    {
+      "epoch": 0.39631988676574664,
+      "grad_norm": 3.8764405250549316,
+      "learning_rate": 4.357884796978281e-05,
+      "loss": 1.1757,
+      "step": 140
+    },
+    {
+      "epoch": 0.42462845010615713,
+      "grad_norm": 0.8142156600952148,
+      "learning_rate": 4.31067044381492e-05,
+      "loss": 1.0972,
+      "step": 150
+    },
+    {
+      "epoch": 0.45293701344656756,
+      "grad_norm": 2.6679811477661133,
+      "learning_rate": 4.263456090651558e-05,
+      "loss": 1.1941,
+      "step": 160
+    },
+    {
+      "epoch": 0.48124557678697805,
+      "grad_norm": 3.724242925643921,
+      "learning_rate": 4.216241737488197e-05,
+      "loss": 1.0199,
+      "step": 170
+    },
+    {
+      "epoch": 0.5095541401273885,
+      "grad_norm": 0.9096172451972961,
+      "learning_rate": 4.169027384324835e-05,
+      "loss": 0.9365,
+      "step": 180
+    },
+    {
+      "epoch": 0.537862703467799,
+      "grad_norm": 0.8280671834945679,
+      "learning_rate": 4.1218130311614734e-05,
+      "loss": 0.7999,
+      "step": 190
+    },
+    {
+      "epoch": 0.5661712668082095,
+      "grad_norm": 0.7605137825012207,
+      "learning_rate": 4.0745986779981115e-05,
+      "loss": 0.9142,
+      "step": 200
+    },
+    {
+      "epoch": 0.5944798301486199,
+      "grad_norm": 1.1094071865081787,
+      "learning_rate": 4.02738432483475e-05,
+      "loss": 0.9304,
+      "step": 210
+    },
+    {
+      "epoch": 0.6227883934890305,
+      "grad_norm": 1.2188092470169067,
+      "learning_rate": 3.980169971671388e-05,
+      "loss": 1.0773,
+      "step": 220
+    },
+    {
+      "epoch": 0.6510969568294409,
+      "grad_norm": 1.421103835105896,
+      "learning_rate": 3.932955618508027e-05,
+      "loss": 0.9702,
+      "step": 230
+    },
+    {
+      "epoch": 0.6794055201698513,
+      "grad_norm": 0.6401333212852478,
+      "learning_rate": 3.885741265344665e-05,
+      "loss": 0.8283,
+      "step": 240
+    },
+    {
+      "epoch": 0.7077140835102619,
+      "grad_norm": 1.2169103622436523,
+      "learning_rate": 3.8385269121813036e-05,
+      "loss": 0.7306,
+      "step": 250
+    },
+    {
+      "epoch": 0.7360226468506723,
+      "grad_norm": 4.206311225891113,
+      "learning_rate": 3.791312559017942e-05,
+      "loss": 0.7564,
+      "step": 260
+    },
+    {
+      "epoch": 0.7643312101910829,
+      "grad_norm": 0.7803528308868408,
+      "learning_rate": 3.74409820585458e-05,
+      "loss": 0.9409,
+      "step": 270
+    },
+    {
+      "epoch": 0.7926397735314933,
+      "grad_norm": 1.2564524412155151,
+      "learning_rate": 3.696883852691218e-05,
+      "loss": 0.8487,
+      "step": 280
+    },
+    {
+      "epoch": 0.8209483368719037,
+      "grad_norm": 1.0345911979675293,
+      "learning_rate": 3.649669499527857e-05,
+      "loss": 0.9284,
+      "step": 290
+    },
+    {
+      "epoch": 0.8492569002123143,
+      "grad_norm": 2.6895930767059326,
+      "learning_rate": 3.602455146364495e-05,
+      "loss": 1.1654,
+      "step": 300
+    },
+    {
+      "epoch": 0.8775654635527247,
+      "grad_norm": 1.2171903848648071,
+      "learning_rate": 3.555240793201133e-05,
+      "loss": 0.8589,
+      "step": 310
+    },
+    {
+      "epoch": 0.9058740268931351,
+      "grad_norm": 2.6197869777679443,
+      "learning_rate": 3.5080264400377714e-05,
+      "loss": 0.8405,
+      "step": 320
+    },
+    {
+      "epoch": 0.9341825902335457,
+      "grad_norm": 0.9666792750358582,
+      "learning_rate": 3.4608120868744095e-05,
+      "loss": 1.1513,
+      "step": 330
+    },
+    {
+      "epoch": 0.9624911535739561,
+      "grad_norm": 0.9216092824935913,
+      "learning_rate": 3.4135977337110484e-05,
+      "loss": 0.8712,
+      "step": 340
+    },
+    {
+      "epoch": 0.9907997169143666,
+      "grad_norm": 2.9435744285583496,
+      "learning_rate": 3.366383380547687e-05,
+      "loss": 0.9633,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.920014500617981,
+      "eval_runtime": 45.4818,
+      "eval_samples_per_second": 15.545,
+      "eval_steps_per_second": 1.957,
+      "step": 354
+    },
+    {
+      "epoch": 1.0169851380042463,
+      "grad_norm": 0.7391465306282043,
+      "learning_rate": 3.3191690273843253e-05,
+      "loss": 0.6779,
+      "step": 360
+    },
+    {
+      "epoch": 1.0452937013446568,
+      "grad_norm": 1.267843246459961,
+      "learning_rate": 3.2719546742209635e-05,
+      "loss": 0.9072,
+      "step": 370
+    },
+    {
+      "epoch": 1.0736022646850671,
+      "grad_norm": 0.7193703651428223,
+      "learning_rate": 3.2247403210576016e-05,
+      "loss": 1.0308,
+      "step": 380
+    },
+    {
+      "epoch": 1.1019108280254777,
+      "grad_norm": 3.1680991649627686,
+      "learning_rate": 3.17752596789424e-05,
+      "loss": 0.8272,
+      "step": 390
+    },
+    {
+      "epoch": 1.1302193913658882,
+      "grad_norm": 1.0723551511764526,
+      "learning_rate": 3.130311614730878e-05,
+      "loss": 1.02,
+      "step": 400
+    },
+    {
+      "epoch": 1.1585279547062988,
+      "grad_norm": 0.7101927995681763,
+      "learning_rate": 3.083097261567517e-05,
+      "loss": 0.942,
+      "step": 410
+    },
+    {
+      "epoch": 1.186836518046709,
+      "grad_norm": 1.9213780164718628,
+      "learning_rate": 3.0358829084041553e-05,
+      "loss": 0.8884,
+      "step": 420
+    },
+    {
+      "epoch": 1.2151450813871196,
+      "grad_norm": 4.313545227050781,
+      "learning_rate": 2.9886685552407934e-05,
+      "loss": 1.055,
+      "step": 430
+    },
+    {
+      "epoch": 1.2434536447275302,
+      "grad_norm": 1.1699409484863281,
+      "learning_rate": 2.9414542020774316e-05,
+      "loss": 0.7015,
+      "step": 440
+    },
+    {
+      "epoch": 1.2717622080679405,
+      "grad_norm": 0.7084372043609619,
+      "learning_rate": 2.8942398489140697e-05,
+      "loss": 0.8342,
+      "step": 450
+    },
+    {
+      "epoch": 1.300070771408351,
+      "grad_norm": 1.1760873794555664,
+      "learning_rate": 2.8470254957507082e-05,
+      "loss": 0.7567,
+      "step": 460
+    },
+    {
+      "epoch": 1.3283793347487616,
+      "grad_norm": 6.9120192527771,
+      "learning_rate": 2.799811142587347e-05,
+      "loss": 0.8156,
+      "step": 470
+    },
+    {
+      "epoch": 1.356687898089172,
+      "grad_norm": 0.7138371467590332,
+      "learning_rate": 2.7525967894239852e-05,
+      "loss": 0.8024,
+      "step": 480
+    },
+    {
+      "epoch": 1.3849964614295824,
+      "grad_norm": 0.6835730075836182,
+      "learning_rate": 2.7053824362606233e-05,
+      "loss": 0.7977,
+      "step": 490
+    },
+    {
+      "epoch": 1.413305024769993,
+      "grad_norm": 6.436087608337402,
+      "learning_rate": 2.6581680830972615e-05,
+      "loss": 0.8102,
+      "step": 500
+    },
+    {
+      "epoch": 1.4416135881104033,
+      "grad_norm": 3.4291305541992188,
+      "learning_rate": 2.6109537299339e-05,
+      "loss": 0.7643,
+      "step": 510
+    },
+    {
+      "epoch": 1.4699221514508138,
+      "grad_norm": 0.9250390529632568,
+      "learning_rate": 2.563739376770538e-05,
+      "loss": 0.8417,
+      "step": 520
+    },
+    {
+      "epoch": 1.4982307147912244,
+      "grad_norm": 3.264242649078369,
+      "learning_rate": 2.516525023607177e-05,
+      "loss": 0.9988,
+      "step": 530
+    },
+    {
+      "epoch": 1.5265392781316347,
+      "grad_norm": 1.8651660680770874,
+      "learning_rate": 2.469310670443815e-05,
+      "loss": 0.8652,
+      "step": 540
+    },
+    {
+      "epoch": 1.5548478414720452,
+      "grad_norm": 5.576003074645996,
+      "learning_rate": 2.4220963172804533e-05,
+      "loss": 0.7481,
+      "step": 550
+    },
+    {
+      "epoch": 1.5831564048124558,
+      "grad_norm": 4.8853302001953125,
+      "learning_rate": 2.3748819641170918e-05,
+      "loss": 0.7857,
+      "step": 560
+    },
+    {
+      "epoch": 1.611464968152866,
+      "grad_norm": 2.0183866024017334,
+      "learning_rate": 2.3276676109537303e-05,
+      "loss": 0.607,
+      "step": 570
+    },
+    {
+      "epoch": 1.6397735314932769,
+      "grad_norm": 3.133368730545044,
+      "learning_rate": 2.2804532577903684e-05,
+      "loss": 0.8706,
+      "step": 580
+    },
+    {
+      "epoch": 1.6680820948336872,
+      "grad_norm": 2.440894365310669,
+      "learning_rate": 2.2332389046270066e-05,
+      "loss": 0.8035,
+      "step": 590
+    },
+    {
+      "epoch": 1.6963906581740975,
+      "grad_norm": 3.0257763862609863,
+      "learning_rate": 2.186024551463645e-05,
+      "loss": 1.1186,
+      "step": 600
+    },
+    {
+      "epoch": 1.7246992215145083,
+      "grad_norm": 2.741161823272705,
+      "learning_rate": 2.1388101983002835e-05,
+      "loss": 1.0302,
+      "step": 610
+    },
+    {
+      "epoch": 1.7530077848549186,
+      "grad_norm": 3.0165324211120605,
+      "learning_rate": 2.0915958451369217e-05,
+      "loss": 1.0235,
+      "step": 620
+    },
+    {
+      "epoch": 1.7813163481953291,
+      "grad_norm": 1.8402531147003174,
+      "learning_rate": 2.0443814919735602e-05,
+      "loss": 0.8455,
+      "step": 630
+    },
+    {
+      "epoch": 1.8096249115357397,
+      "grad_norm": 1.0427038669586182,
+      "learning_rate": 1.9971671388101983e-05,
+      "loss": 0.7868,
+      "step": 640
+    },
+    {
+      "epoch": 1.83793347487615,
+      "grad_norm": 4.955197334289551,
+      "learning_rate": 1.9499527856468365e-05,
+      "loss": 0.8728,
+      "step": 650
+    },
+    {
+      "epoch": 1.8662420382165605,
+      "grad_norm": 1.1331288814544678,
+      "learning_rate": 1.9027384324834753e-05,
+      "loss": 0.8719,
+      "step": 660
+    },
+    {
+      "epoch": 1.894550601556971,
+      "grad_norm": 1.395735263824463,
+      "learning_rate": 1.8555240793201135e-05,
+      "loss": 0.8224,
+      "step": 670
+    },
+    {
+      "epoch": 1.9228591648973814,
+      "grad_norm": 1.110823154449463,
+      "learning_rate": 1.8083097261567516e-05,
+      "loss": 0.6859,
+      "step": 680
+    },
+    {
+      "epoch": 1.951167728237792,
+      "grad_norm": 1.224063754081726,
+      "learning_rate": 1.76109537299339e-05,
+      "loss": 0.79,
+      "step": 690
+    },
+    {
+      "epoch": 1.9794762915782025,
+      "grad_norm": 1.4636934995651245,
+      "learning_rate": 1.7138810198300283e-05,
+      "loss": 0.9543,
+      "step": 700
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.8783606290817261,
+      "eval_runtime": 45.4943,
+      "eval_samples_per_second": 15.54,
+      "eval_steps_per_second": 1.956,
+      "step": 708
+    },
+    {
+      "epoch": 2.0056617126680822,
+      "grad_norm": 3.3927221298217773,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.0075,
+      "step": 710
+    },
+    {
+      "epoch": 2.0339702760084926,
+      "grad_norm": 2.4237897396087646,
+      "learning_rate": 1.6194523135033052e-05,
+      "loss": 0.7245,
+      "step": 720
+    },
+    {
+      "epoch": 2.062278839348903,
+      "grad_norm": 0.9672299027442932,
+      "learning_rate": 1.5722379603399434e-05,
+      "loss": 0.7631,
+      "step": 730
+    },
+    {
+      "epoch": 2.0905874026893136,
+      "grad_norm": 2.908951997756958,
+      "learning_rate": 1.5250236071765817e-05,
+      "loss": 1.0795,
+      "step": 740
+    },
+    {
+      "epoch": 2.118895966029724,
+      "grad_norm": 3.8468856811523438,
+      "learning_rate": 1.4778092540132202e-05,
+      "loss": 0.6312,
+      "step": 750
+    },
+    {
+      "epoch": 2.1472045293701343,
+      "grad_norm": 1.352995753288269,
+      "learning_rate": 1.4305949008498584e-05,
+      "loss": 0.8062,
+      "step": 760
+    },
+    {
+      "epoch": 2.175513092710545,
+      "grad_norm": 1.1038804054260254,
+      "learning_rate": 1.3833805476864967e-05,
+      "loss": 0.8566,
+      "step": 770
+    },
+    {
+      "epoch": 2.2038216560509554,
+      "grad_norm": 1.2990654706954956,
+      "learning_rate": 1.3361661945231352e-05,
+      "loss": 0.7693,
+      "step": 780
+    },
+    {
+      "epoch": 2.2321302193913657,
+      "grad_norm": 2.6625759601593018,
+      "learning_rate": 1.2889518413597735e-05,
+      "loss": 0.6126,
+      "step": 790
+    },
+    {
+      "epoch": 2.2604387827317765,
+      "grad_norm": 5.676569938659668,
+      "learning_rate": 1.2417374881964118e-05,
+      "loss": 0.7988,
+      "step": 800
+    },
+    {
+      "epoch": 2.2887473460721868,
+      "grad_norm": 2.953200340270996,
+      "learning_rate": 1.1945231350330501e-05,
+      "loss": 0.6122,
+      "step": 810
+    },
+    {
+      "epoch": 2.3170559094125975,
+      "grad_norm": 2.253474473953247,
+      "learning_rate": 1.1473087818696884e-05,
+      "loss": 1.1378,
+      "step": 820
+    },
+    {
+      "epoch": 2.345364472753008,
+      "grad_norm": 1.5058188438415527,
+      "learning_rate": 1.1000944287063268e-05,
+      "loss": 0.8095,
+      "step": 830
+    },
+    {
+      "epoch": 2.373673036093418,
+      "grad_norm": 0.8082104325294495,
+      "learning_rate": 1.0528800755429651e-05,
+      "loss": 0.5857,
+      "step": 840
+    },
+    {
+      "epoch": 2.401981599433829,
+      "grad_norm": 2.0527071952819824,
+      "learning_rate": 1.0056657223796034e-05,
+      "loss": 0.9159,
+      "step": 850
+    },
+    {
+      "epoch": 2.4302901627742393,
+      "grad_norm": 4.757397651672363,
+      "learning_rate": 9.584513692162419e-06,
+      "loss": 0.7801,
+      "step": 860
+    },
+    {
+      "epoch": 2.4585987261146496,
+      "grad_norm": 2.750612735748291,
+      "learning_rate": 9.1123701605288e-06,
+      "loss": 0.7435,
+      "step": 870
+    },
+    {
+      "epoch": 2.4869072894550603,
+      "grad_norm": 0.7405831813812256,
+      "learning_rate": 8.640226628895184e-06,
+      "loss": 0.7491,
+      "step": 880
+    },
+    {
+      "epoch": 2.5152158527954707,
+      "grad_norm": 3.5916926860809326,
+      "learning_rate": 8.168083097261569e-06,
+      "loss": 0.896,
+      "step": 890
+    },
+    {
+      "epoch": 2.543524416135881,
+      "grad_norm": 2.436352252960205,
+      "learning_rate": 7.69593956562795e-06,
+      "loss": 0.7018,
+      "step": 900
+    },
+    {
+      "epoch": 2.5718329794762917,
+      "grad_norm": 0.8077714443206787,
+      "learning_rate": 7.223796033994334e-06,
+      "loss": 1.1473,
+      "step": 910
+    },
+    {
+      "epoch": 2.600141542816702,
+      "grad_norm": 2.01489520072937,
+      "learning_rate": 6.751652502360718e-06,
+      "loss": 0.8547,
+      "step": 920
+    },
+    {
+      "epoch": 2.6284501061571124,
+      "grad_norm": 0.9167873859405518,
+      "learning_rate": 6.279508970727101e-06,
+      "loss": 0.9682,
+      "step": 930
+    },
+    {
+      "epoch": 2.656758669497523,
+      "grad_norm": 0.8447218537330627,
+      "learning_rate": 5.807365439093485e-06,
+      "loss": 0.5817,
+      "step": 940
+    },
+    {
+      "epoch": 2.6850672328379335,
+      "grad_norm": 1.5092198848724365,
+      "learning_rate": 5.335221907459869e-06,
+      "loss": 1.2028,
+      "step": 950
+    },
+    {
+      "epoch": 2.713375796178344,
+      "grad_norm": 2.282589912414551,
+      "learning_rate": 4.863078375826251e-06,
+      "loss": 0.6571,
+      "step": 960
+    },
+    {
+      "epoch": 2.7416843595187546,
+      "grad_norm": 1.5408430099487305,
+      "learning_rate": 4.390934844192634e-06,
+      "loss": 0.6459,
+      "step": 970
+    },
+    {
+      "epoch": 2.769992922859165,
+      "grad_norm": 5.208029270172119,
+      "learning_rate": 3.918791312559018e-06,
+      "loss": 0.8532,
+      "step": 980
+    },
+    {
+      "epoch": 2.798301486199575,
+      "grad_norm": 1.4328051805496216,
+      "learning_rate": 3.4466477809254016e-06,
+      "loss": 0.8735,
+      "step": 990
+    },
+    {
+      "epoch": 2.826610049539986,
+      "grad_norm": 2.1999919414520264,
+      "learning_rate": 2.9745042492917848e-06,
+      "loss": 1.0141,
+      "step": 1000
+    },
+    {
+      "epoch": 2.8549186128803963,
+      "grad_norm": 1.0183438062667847,
+      "learning_rate": 2.502360717658168e-06,
+      "loss": 0.7974,
+      "step": 1010
+    },
+    {
+      "epoch": 2.8832271762208066,
+      "grad_norm": 3.3981127738952637,
+      "learning_rate": 2.0302171860245516e-06,
+      "loss": 0.8471,
+      "step": 1020
+    },
+    {
+      "epoch": 2.9115357395612174,
+      "grad_norm": 2.758704662322998,
+      "learning_rate": 1.5580736543909348e-06,
+      "loss": 0.8021,
+      "step": 1030
+    },
+    {
+      "epoch": 2.9398443029016277,
+      "grad_norm": 0.8233171105384827,
+      "learning_rate": 1.0859301227573182e-06,
+      "loss": 0.7704,
+      "step": 1040
+    },
+    {
+      "epoch": 2.968152866242038,
+      "grad_norm": 3.0792815685272217,
+      "learning_rate": 6.137865911237016e-07,
+      "loss": 0.6247,
+      "step": 1050
+    },
+    {
+      "epoch": 2.9936305732484074,
+      "eval_loss": 0.861165463924408,
+      "eval_runtime": 45.4972,
+      "eval_samples_per_second": 15.539,
+      "eval_steps_per_second": 1.956,
+      "step": 1059
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1059,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.95177370947158e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c49fdf0e3c7b9d2b07195d6f5fd8e871220a5835fa676a5207ef89087b6daff
+size 5304