Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
+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 0.12.0

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3.1-70B-Instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_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:e74fc916fdc5e33682887673a1641ae51a666ef9773adbb33693294d7db721fa
+size 131115296

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:111ecb4bc5697b5276db9761da6d2f9c8c15a714e038d0f5e52ca2e866394957
+size 262413434

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260961c86d532453f1ae863f0ae34c050a5667f3ffbb315364fb510154c46bc5
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7e69aa73185c1b1d3ff1446e91f0f48513263da504b7402453840a7b5171046
+size 1064

trainer_state.json

@@ -0,0 +1,670 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.99510603588907,
+  "eval_steps": 500,
+  "global_step": 918,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03262642740619902,
+      "grad_norm": 0.5258967280387878,
+      "learning_rate": 5e-06,
+      "loss": 1.8319,
+      "step": 10
+    },
+    {
+      "epoch": 0.06525285481239804,
+      "grad_norm": 0.5200194120407104,
+      "learning_rate": 9.5e-06,
+      "loss": 1.7689,
+      "step": 20
+    },
+    {
+      "epoch": 0.09787928221859707,
+      "grad_norm": 0.56816166639328,
+      "learning_rate": 1.45e-05,
+      "loss": 1.7576,
+      "step": 30
+    },
+    {
+      "epoch": 0.13050570962479607,
+      "grad_norm": 0.5110853910446167,
+      "learning_rate": 1.9500000000000003e-05,
+      "loss": 1.6579,
+      "step": 40
+    },
+    {
+      "epoch": 0.1631321370309951,
+      "grad_norm": 0.4745779037475586,
+      "learning_rate": 2.45e-05,
+      "loss": 1.5154,
+      "step": 50
+    },
+    {
+      "epoch": 0.19575856443719414,
+      "grad_norm": 0.5604385137557983,
+      "learning_rate": 2.95e-05,
+      "loss": 1.3892,
+      "step": 60
+    },
+    {
+      "epoch": 0.22838499184339314,
+      "grad_norm": 0.7449052333831787,
+      "learning_rate": 3.45e-05,
+      "loss": 1.2256,
+      "step": 70
+    },
+    {
+      "epoch": 0.26101141924959215,
+      "grad_norm": 0.7363050580024719,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 0.982,
+      "step": 80
+    },
+    {
+      "epoch": 0.2936378466557912,
+      "grad_norm": 0.5178012847900391,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 0.7681,
+      "step": 90
+    },
+    {
+      "epoch": 0.3262642740619902,
+      "grad_norm": 0.6690722703933716,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 0.7226,
+      "step": 100
+    },
+    {
+      "epoch": 0.35889070146818924,
+      "grad_norm": 0.4482414424419403,
+      "learning_rate": 4.944987775061125e-05,
+      "loss": 0.6749,
+      "step": 110
+    },
+    {
+      "epoch": 0.3915171288743883,
+      "grad_norm": 0.5283921957015991,
+      "learning_rate": 4.883863080684597e-05,
+      "loss": 0.6465,
+      "step": 120
+    },
+    {
+      "epoch": 0.42414355628058725,
+      "grad_norm": 0.5526198744773865,
+      "learning_rate": 4.822738386308069e-05,
+      "loss": 0.594,
+      "step": 130
+    },
+    {
+      "epoch": 0.4567699836867863,
+      "grad_norm": 0.5214644074440002,
+      "learning_rate": 4.761613691931541e-05,
+      "loss": 0.5579,
+      "step": 140
+    },
+    {
+      "epoch": 0.4893964110929853,
+      "grad_norm": 0.5322310924530029,
+      "learning_rate": 4.7004889975550123e-05,
+      "loss": 0.5305,
+      "step": 150
+    },
+    {
+      "epoch": 0.5220228384991843,
+      "grad_norm": 0.7314450740814209,
+      "learning_rate": 4.6393643031784844e-05,
+      "loss": 0.4756,
+      "step": 160
+    },
+    {
+      "epoch": 0.5546492659053833,
+      "grad_norm": 0.8103362917900085,
+      "learning_rate": 4.5782396088019564e-05,
+      "loss": 0.4592,
+      "step": 170
+    },
+    {
+      "epoch": 0.5872756933115824,
+      "grad_norm": 0.6366791725158691,
+      "learning_rate": 4.5171149144254284e-05,
+      "loss": 0.4786,
+      "step": 180
+    },
+    {
+      "epoch": 0.6199021207177814,
+      "grad_norm": 0.6715788245201111,
+      "learning_rate": 4.4559902200489e-05,
+      "loss": 0.4216,
+      "step": 190
+    },
+    {
+      "epoch": 0.6525285481239804,
+      "grad_norm": 0.6936819553375244,
+      "learning_rate": 4.394865525672372e-05,
+      "loss": 0.3964,
+      "step": 200
+    },
+    {
+      "epoch": 0.6851549755301795,
+      "grad_norm": 0.8318383693695068,
+      "learning_rate": 4.333740831295844e-05,
+      "loss": 0.4043,
+      "step": 210
+    },
+    {
+      "epoch": 0.7177814029363785,
+      "grad_norm": 0.656146228313446,
+      "learning_rate": 4.272616136919316e-05,
+      "loss": 0.3881,
+      "step": 220
+    },
+    {
+      "epoch": 0.7504078303425775,
+      "grad_norm": 0.9217523336410522,
+      "learning_rate": 4.211491442542788e-05,
+      "loss": 0.3378,
+      "step": 230
+    },
+    {
+      "epoch": 0.7830342577487766,
+      "grad_norm": 0.7269819378852844,
+      "learning_rate": 4.150366748166259e-05,
+      "loss": 0.3052,
+      "step": 240
+    },
+    {
+      "epoch": 0.8156606851549756,
+      "grad_norm": 0.7469998002052307,
+      "learning_rate": 4.089242053789731e-05,
+      "loss": 0.301,
+      "step": 250
+    },
+    {
+      "epoch": 0.8482871125611745,
+      "grad_norm": 0.7021219730377197,
+      "learning_rate": 4.028117359413203e-05,
+      "loss": 0.32,
+      "step": 260
+    },
+    {
+      "epoch": 0.8809135399673735,
+      "grad_norm": 0.6621549725532532,
+      "learning_rate": 3.966992665036675e-05,
+      "loss": 0.283,
+      "step": 270
+    },
+    {
+      "epoch": 0.9135399673735726,
+      "grad_norm": 1.2602078914642334,
+      "learning_rate": 3.905867970660147e-05,
+      "loss": 0.3075,
+      "step": 280
+    },
+    {
+      "epoch": 0.9461663947797716,
+      "grad_norm": 0.8152816295623779,
+      "learning_rate": 3.8447432762836186e-05,
+      "loss": 0.2951,
+      "step": 290
+    },
+    {
+      "epoch": 0.9787928221859706,
+      "grad_norm": 0.7038506865501404,
+      "learning_rate": 3.783618581907091e-05,
+      "loss": 0.2964,
+      "step": 300
+    },
+    {
+      "epoch": 1.0114192495921697,
+      "grad_norm": 1.1956801414489746,
+      "learning_rate": 3.722493887530563e-05,
+      "loss": 0.2707,
+      "step": 310
+    },
+    {
+      "epoch": 1.0440456769983686,
+      "grad_norm": 0.6589512228965759,
+      "learning_rate": 3.661369193154035e-05,
+      "loss": 0.2689,
+      "step": 320
+    },
+    {
+      "epoch": 1.0766721044045677,
+      "grad_norm": 0.953842043876648,
+      "learning_rate": 3.600244498777506e-05,
+      "loss": 0.2898,
+      "step": 330
+    },
+    {
+      "epoch": 1.1092985318107667,
+      "grad_norm": 0.6870063543319702,
+      "learning_rate": 3.539119804400978e-05,
+      "loss": 0.2836,
+      "step": 340
+    },
+    {
+      "epoch": 1.1419249592169658,
+      "grad_norm": 0.9847205877304077,
+      "learning_rate": 3.47799511002445e-05,
+      "loss": 0.2707,
+      "step": 350
+    },
+    {
+      "epoch": 1.1745513866231647,
+      "grad_norm": 1.0384355783462524,
+      "learning_rate": 3.416870415647922e-05,
+      "loss": 0.2578,
+      "step": 360
+    },
+    {
+      "epoch": 1.2071778140293639,
+      "grad_norm": 0.7339671850204468,
+      "learning_rate": 3.355745721271394e-05,
+      "loss": 0.2622,
+      "step": 370
+    },
+    {
+      "epoch": 1.2398042414355628,
+      "grad_norm": 0.8134469389915466,
+      "learning_rate": 3.2946210268948655e-05,
+      "loss": 0.2365,
+      "step": 380
+    },
+    {
+      "epoch": 1.272430668841762,
+      "grad_norm": 0.9134344458580017,
+      "learning_rate": 3.2334963325183375e-05,
+      "loss": 0.2586,
+      "step": 390
+    },
+    {
+      "epoch": 1.3050570962479608,
+      "grad_norm": 0.7556074261665344,
+      "learning_rate": 3.1723716381418096e-05,
+      "loss": 0.236,
+      "step": 400
+    },
+    {
+      "epoch": 1.3376835236541598,
+      "grad_norm": 1.0541133880615234,
+      "learning_rate": 3.1112469437652816e-05,
+      "loss": 0.2483,
+      "step": 410
+    },
+    {
+      "epoch": 1.370309951060359,
+      "grad_norm": 1.0119078159332275,
+      "learning_rate": 3.0501222493887533e-05,
+      "loss": 0.2462,
+      "step": 420
+    },
+    {
+      "epoch": 1.4029363784665578,
+      "grad_norm": 0.9008921980857849,
+      "learning_rate": 2.988997555012225e-05,
+      "loss": 0.2373,
+      "step": 430
+    },
+    {
+      "epoch": 1.435562805872757,
+      "grad_norm": 0.9207481741905212,
+      "learning_rate": 2.927872860635697e-05,
+      "loss": 0.2504,
+      "step": 440
+    },
+    {
+      "epoch": 1.468189233278956,
+      "grad_norm": 0.8675833344459534,
+      "learning_rate": 2.866748166259169e-05,
+      "loss": 0.2463,
+      "step": 450
+    },
+    {
+      "epoch": 1.5008156606851548,
+      "grad_norm": 1.7861591577529907,
+      "learning_rate": 2.8056234718826407e-05,
+      "loss": 0.2468,
+      "step": 460
+    },
+    {
+      "epoch": 1.533442088091354,
+      "grad_norm": 0.8898101449012756,
+      "learning_rate": 2.7444987775061127e-05,
+      "loss": 0.2254,
+      "step": 470
+    },
+    {
+      "epoch": 1.566068515497553,
+      "grad_norm": 0.9002168774604797,
+      "learning_rate": 2.6833740831295844e-05,
+      "loss": 0.2265,
+      "step": 480
+    },
+    {
+      "epoch": 1.598694942903752,
+      "grad_norm": 1.0384007692337036,
+      "learning_rate": 2.6222493887530564e-05,
+      "loss": 0.214,
+      "step": 490
+    },
+    {
+      "epoch": 1.631321370309951,
+      "grad_norm": 0.7849037647247314,
+      "learning_rate": 2.561124694376528e-05,
+      "loss": 0.2325,
+      "step": 500
+    },
+    {
+      "epoch": 1.66394779771615,
+      "grad_norm": 0.7699252367019653,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2171,
+      "step": 510
+    },
+    {
+      "epoch": 1.6965742251223492,
+      "grad_norm": 0.9055914878845215,
+      "learning_rate": 2.438875305623472e-05,
+      "loss": 0.2322,
+      "step": 520
+    },
+    {
+      "epoch": 1.7292006525285482,
+      "grad_norm": 1.4799339771270752,
+      "learning_rate": 2.3777506112469438e-05,
+      "loss": 0.2165,
+      "step": 530
+    },
+    {
+      "epoch": 1.761827079934747,
+      "grad_norm": 0.9675979018211365,
+      "learning_rate": 2.316625916870416e-05,
+      "loss": 0.2218,
+      "step": 540
+    },
+    {
+      "epoch": 1.7944535073409462,
+      "grad_norm": 1.1401549577713013,
+      "learning_rate": 2.2555012224938875e-05,
+      "loss": 0.2123,
+      "step": 550
+    },
+    {
+      "epoch": 1.8270799347471451,
+      "grad_norm": 1.1033681631088257,
+      "learning_rate": 2.1943765281173596e-05,
+      "loss": 0.2285,
+      "step": 560
+    },
+    {
+      "epoch": 1.8597063621533443,
+      "grad_norm": 1.0548712015151978,
+      "learning_rate": 2.1332518337408312e-05,
+      "loss": 0.2136,
+      "step": 570
+    },
+    {
+      "epoch": 1.8923327895595432,
+      "grad_norm": 1.5485633611679077,
+      "learning_rate": 2.0721271393643033e-05,
+      "loss": 0.2055,
+      "step": 580
+    },
+    {
+      "epoch": 1.9249592169657421,
+      "grad_norm": 0.9844083786010742,
+      "learning_rate": 2.0110024449877753e-05,
+      "loss": 0.2142,
+      "step": 590
+    },
+    {
+      "epoch": 1.9575856443719413,
+      "grad_norm": 1.1740403175354004,
+      "learning_rate": 1.949877750611247e-05,
+      "loss": 0.1948,
+      "step": 600
+    },
+    {
+      "epoch": 1.9902120717781404,
+      "grad_norm": 0.9265509843826294,
+      "learning_rate": 1.888753056234719e-05,
+      "loss": 0.2142,
+      "step": 610
+    },
+    {
+      "epoch": 2.0228384991843393,
+      "grad_norm": 0.8141701221466064,
+      "learning_rate": 1.8276283618581907e-05,
+      "loss": 0.2023,
+      "step": 620
+    },
+    {
+      "epoch": 2.0554649265905383,
+      "grad_norm": 0.7996273040771484,
+      "learning_rate": 1.7665036674816627e-05,
+      "loss": 0.1924,
+      "step": 630
+    },
+    {
+      "epoch": 2.088091353996737,
+      "grad_norm": 0.9325422048568726,
+      "learning_rate": 1.7053789731051344e-05,
+      "loss": 0.1887,
+      "step": 640
+    },
+    {
+      "epoch": 2.1207177814029365,
+      "grad_norm": 0.9285069108009338,
+      "learning_rate": 1.6442542787286064e-05,
+      "loss": 0.1891,
+      "step": 650
+    },
+    {
+      "epoch": 2.1533442088091355,
+      "grad_norm": 1.1411644220352173,
+      "learning_rate": 1.583129584352078e-05,
+      "loss": 0.1898,
+      "step": 660
+    },
+    {
+      "epoch": 2.1859706362153344,
+      "grad_norm": 0.8324933052062988,
+      "learning_rate": 1.5220048899755501e-05,
+      "loss": 0.1854,
+      "step": 670
+    },
+    {
+      "epoch": 2.2185970636215333,
+      "grad_norm": 1.0230185985565186,
+      "learning_rate": 1.460880195599022e-05,
+      "loss": 0.1909,
+      "step": 680
+    },
+    {
+      "epoch": 2.2512234910277327,
+      "grad_norm": 1.1167818307876587,
+      "learning_rate": 1.3997555012224938e-05,
+      "loss": 0.2023,
+      "step": 690
+    },
+    {
+      "epoch": 2.2838499184339316,
+      "grad_norm": 0.8201693892478943,
+      "learning_rate": 1.3386308068459657e-05,
+      "loss": 0.1928,
+      "step": 700
+    },
+    {
+      "epoch": 2.3164763458401305,
+      "grad_norm": 1.2748645544052124,
+      "learning_rate": 1.2775061124694377e-05,
+      "loss": 0.2043,
+      "step": 710
+    },
+    {
+      "epoch": 2.3491027732463294,
+      "grad_norm": 0.9501346945762634,
+      "learning_rate": 1.2163814180929096e-05,
+      "loss": 0.1914,
+      "step": 720
+    },
+    {
+      "epoch": 2.3817292006525284,
+      "grad_norm": 0.8706419467926025,
+      "learning_rate": 1.1552567237163816e-05,
+      "loss": 0.1763,
+      "step": 730
+    },
+    {
+      "epoch": 2.4143556280587277,
+      "grad_norm": 1.8394954204559326,
+      "learning_rate": 1.0941320293398534e-05,
+      "loss": 0.1856,
+      "step": 740
+    },
+    {
+      "epoch": 2.4469820554649266,
+      "grad_norm": 0.9215448498725891,
+      "learning_rate": 1.0330073349633253e-05,
+      "loss": 0.181,
+      "step": 750
+    },
+    {
+      "epoch": 2.4796084828711256,
+      "grad_norm": 0.8978357911109924,
+      "learning_rate": 9.718826405867972e-06,
+      "loss": 0.18,
+      "step": 760
+    },
+    {
+      "epoch": 2.5122349102773245,
+      "grad_norm": 0.9564265608787537,
+      "learning_rate": 9.10757946210269e-06,
+      "loss": 0.1961,
+      "step": 770
+    },
+    {
+      "epoch": 2.544861337683524,
+      "grad_norm": 1.1424188613891602,
+      "learning_rate": 8.496332518337409e-06,
+      "loss": 0.1812,
+      "step": 780
+    },
+    {
+      "epoch": 2.5774877650897228,
+      "grad_norm": 1.0267794132232666,
+      "learning_rate": 7.885085574572127e-06,
+      "loss": 0.1861,
+      "step": 790
+    },
+    {
+      "epoch": 2.6101141924959217,
+      "grad_norm": 0.8952123522758484,
+      "learning_rate": 7.273838630806847e-06,
+      "loss": 0.1716,
+      "step": 800
+    },
+    {
+      "epoch": 2.6427406199021206,
+      "grad_norm": 1.2367416620254517,
+      "learning_rate": 6.662591687041565e-06,
+      "loss": 0.1863,
+      "step": 810
+    },
+    {
+      "epoch": 2.6753670473083195,
+      "grad_norm": 1.0904302597045898,
+      "learning_rate": 6.051344743276284e-06,
+      "loss": 0.1823,
+      "step": 820
+    },
+    {
+      "epoch": 2.707993474714519,
+      "grad_norm": 1.0542256832122803,
+      "learning_rate": 5.440097799511003e-06,
+      "loss": 0.1764,
+      "step": 830
+    },
+    {
+      "epoch": 2.740619902120718,
+      "grad_norm": 0.8970702886581421,
+      "learning_rate": 4.828850855745722e-06,
+      "loss": 0.1866,
+      "step": 840
+    },
+    {
+      "epoch": 2.7732463295269167,
+      "grad_norm": 0.8508768081665039,
+      "learning_rate": 4.21760391198044e-06,
+      "loss": 0.1791,
+      "step": 850
+    },
+    {
+      "epoch": 2.8058727569331157,
+      "grad_norm": 0.9417251944541931,
+      "learning_rate": 3.606356968215159e-06,
+      "loss": 0.18,
+      "step": 860
+    },
+    {
+      "epoch": 2.838499184339315,
+      "grad_norm": 0.8804249167442322,
+      "learning_rate": 2.9951100244498777e-06,
+      "loss": 0.1844,
+      "step": 870
+    },
+    {
+      "epoch": 2.871125611745514,
+      "grad_norm": 0.8565665483474731,
+      "learning_rate": 2.3838630806845967e-06,
+      "loss": 0.1781,
+      "step": 880
+    },
+    {
+      "epoch": 2.903752039151713,
+      "grad_norm": 0.9489305019378662,
+      "learning_rate": 1.7726161369193154e-06,
+      "loss": 0.1809,
+      "step": 890
+    },
+    {
+      "epoch": 2.936378466557912,
+      "grad_norm": 0.7006880044937134,
+      "learning_rate": 1.1613691931540342e-06,
+      "loss": 0.1712,
+      "step": 900
+    },
+    {
+      "epoch": 2.9690048939641107,
+      "grad_norm": 0.8745304942131042,
+      "learning_rate": 5.501222493887531e-07,
+      "loss": 0.1773,
+      "step": 910
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 918,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.1375621636321444e+18,
+  "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 sha256:77ba78976253b3542ab7eb1a1d64ca981b07acfce5a8999e871f286812fec44c
+size 5176