Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-2-7b-hf
+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 +1,23 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_weights": false,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "modules_to_save": null,
+  "n_frequency": 10000,
+  "n_frequency_pattern": {},
+  "peft_type": "FOURIERFT",
+  "random_loc_seed": 777,
+  "revision": null,
+  "scaling": 512.0,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99fec53b9d7ac9661286e0b9ec167485eef462f32a50aa35fec1b66b9f887139
+size 2568672

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7080751f30569d335a9917d30626530873ed3cd573691abd4dafcc06d959dd7d
+size 5173498

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c66118f6263dfd2560392c72baf79d90482a44024b4d62803f77bcee6c9b7c
+size 14180

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f53f50db80ffeeb9eaa4e7efc15d2519eece6c3dede9e688a2379b3d91dedc2
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,944 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1294,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015455950540958269,
+      "grad_norm": 0.007970565930008888,
+      "learning_rate": 3.8461538461538456e-05,
+      "loss": 1.028,
+      "step": 10
+    },
+    {
+      "epoch": 0.030911901081916538,
+      "grad_norm": 0.008583859540522099,
+      "learning_rate": 7.692307692307691e-05,
+      "loss": 1.0222,
+      "step": 20
+    },
+    {
+      "epoch": 0.04636785162287481,
+      "grad_norm": 0.007609015330672264,
+      "learning_rate": 0.00011538461538461538,
+      "loss": 1.0227,
+      "step": 30
+    },
+    {
+      "epoch": 0.061823802163833076,
+      "grad_norm": 0.008803783915936947,
+      "learning_rate": 0.00015384615384615382,
+      "loss": 1.0317,
+      "step": 40
+    },
+    {
+      "epoch": 0.07727975270479134,
+      "grad_norm": 0.007184555754065514,
+      "learning_rate": 0.0001923076923076923,
+      "loss": 1.0294,
+      "step": 50
+    },
+    {
+      "epoch": 0.09273570324574962,
+      "grad_norm": 0.006438443902879953,
+      "learning_rate": 0.00023076923076923076,
+      "loss": 1.0083,
+      "step": 60
+    },
+    {
+      "epoch": 0.10819165378670788,
+      "grad_norm": 0.0059270295314490795,
+      "learning_rate": 0.0002692307692307692,
+      "loss": 1.0117,
+      "step": 70
+    },
+    {
+      "epoch": 0.12364760432766615,
+      "grad_norm": 0.006088848225772381,
+      "learning_rate": 0.0002995065789473684,
+      "loss": 1.0056,
+      "step": 80
+    },
+    {
+      "epoch": 0.1391035548686244,
+      "grad_norm": 0.005350991617888212,
+      "learning_rate": 0.00029703947368421054,
+      "loss": 0.9981,
+      "step": 90
+    },
+    {
+      "epoch": 0.1545595054095827,
+      "grad_norm": 0.005426456686109304,
+      "learning_rate": 0.0002945723684210526,
+      "loss": 1.0031,
+      "step": 100
+    },
+    {
+      "epoch": 0.17001545595054096,
+      "grad_norm": 0.005492262076586485,
+      "learning_rate": 0.0002921052631578947,
+      "loss": 0.9788,
+      "step": 110
+    },
+    {
+      "epoch": 0.18547140649149924,
+      "grad_norm": 0.004791167099028826,
+      "learning_rate": 0.00028963815789473683,
+      "loss": 0.9798,
+      "step": 120
+    },
+    {
+      "epoch": 0.2009273570324575,
+      "grad_norm": 0.00411441083997488,
+      "learning_rate": 0.0002871710526315789,
+      "loss": 0.9816,
+      "step": 130
+    },
+    {
+      "epoch": 0.21638330757341576,
+      "grad_norm": 0.004373603034764528,
+      "learning_rate": 0.00028470394736842104,
+      "loss": 0.9684,
+      "step": 140
+    },
+    {
+      "epoch": 0.23183925811437403,
+      "grad_norm": 0.004107773303985596,
+      "learning_rate": 0.0002822368421052631,
+      "loss": 0.985,
+      "step": 150
+    },
+    {
+      "epoch": 0.2472952086553323,
+      "grad_norm": 0.004051375202834606,
+      "learning_rate": 0.0002797697368421052,
+      "loss": 0.9601,
+      "step": 160
+    },
+    {
+      "epoch": 0.26275115919629055,
+      "grad_norm": 0.00420128321275115,
+      "learning_rate": 0.00027730263157894734,
+      "loss": 0.9797,
+      "step": 170
+    },
+    {
+      "epoch": 0.2782071097372488,
+      "grad_norm": 0.004539657384157181,
+      "learning_rate": 0.0002748355263157894,
+      "loss": 0.9969,
+      "step": 180
+    },
+    {
+      "epoch": 0.2936630602782071,
+      "grad_norm": 0.004144193138927221,
+      "learning_rate": 0.00027236842105263155,
+      "loss": 0.9626,
+      "step": 190
+    },
+    {
+      "epoch": 0.3091190108191654,
+      "grad_norm": 0.003976389765739441,
+      "learning_rate": 0.0002699013157894737,
+      "loss": 0.9852,
+      "step": 200
+    },
+    {
+      "epoch": 0.32457496136012365,
+      "grad_norm": 0.004358563106507063,
+      "learning_rate": 0.00026743421052631577,
+      "loss": 0.9598,
+      "step": 210
+    },
+    {
+      "epoch": 0.3400309119010819,
+      "grad_norm": 0.0033344165422022343,
+      "learning_rate": 0.00026496710526315785,
+      "loss": 0.966,
+      "step": 220
+    },
+    {
+      "epoch": 0.3554868624420402,
+      "grad_norm": 0.0035989703610539436,
+      "learning_rate": 0.0002625,
+      "loss": 0.9638,
+      "step": 230
+    },
+    {
+      "epoch": 0.37094281298299847,
+      "grad_norm": 0.0036743590608239174,
+      "learning_rate": 0.00026003289473684206,
+      "loss": 0.9399,
+      "step": 240
+    },
+    {
+      "epoch": 0.38639876352395675,
+      "grad_norm": 0.0036671815905719995,
+      "learning_rate": 0.0002575657894736842,
+      "loss": 0.9765,
+      "step": 250
+    },
+    {
+      "epoch": 0.401854714064915,
+      "grad_norm": 0.00362190417945385,
+      "learning_rate": 0.0002550986842105263,
+      "loss": 0.9475,
+      "step": 260
+    },
+    {
+      "epoch": 0.41731066460587324,
+      "grad_norm": 0.0036270206328481436,
+      "learning_rate": 0.00025263157894736836,
+      "loss": 0.9643,
+      "step": 270
+    },
+    {
+      "epoch": 0.4327666151468315,
+      "grad_norm": 0.003056731540709734,
+      "learning_rate": 0.0002501644736842105,
+      "loss": 0.9501,
+      "step": 280
+    },
+    {
+      "epoch": 0.4482225656877898,
+      "grad_norm": 0.003415195969864726,
+      "learning_rate": 0.00024769736842105263,
+      "loss": 0.9416,
+      "step": 290
+    },
+    {
+      "epoch": 0.46367851622874806,
+      "grad_norm": 0.0030140345916152,
+      "learning_rate": 0.0002452302631578947,
+      "loss": 0.9543,
+      "step": 300
+    },
+    {
+      "epoch": 0.47913446676970634,
+      "grad_norm": 0.0031111338175833225,
+      "learning_rate": 0.00024276315789473682,
+      "loss": 0.9511,
+      "step": 310
+    },
+    {
+      "epoch": 0.4945904173106646,
+      "grad_norm": 0.0030552814714610577,
+      "learning_rate": 0.00024029605263157892,
+      "loss": 0.9473,
+      "step": 320
+    },
+    {
+      "epoch": 0.5100463678516228,
+      "grad_norm": 0.002919870661571622,
+      "learning_rate": 0.00023782894736842103,
+      "loss": 0.954,
+      "step": 330
+    },
+    {
+      "epoch": 0.5255023183925811,
+      "grad_norm": 0.0027907874900847673,
+      "learning_rate": 0.00023536184210526314,
+      "loss": 0.9423,
+      "step": 340
+    },
+    {
+      "epoch": 0.5409582689335394,
+      "grad_norm": 0.002565987640991807,
+      "learning_rate": 0.00023289473684210524,
+      "loss": 0.9578,
+      "step": 350
+    },
+    {
+      "epoch": 0.5564142194744977,
+      "grad_norm": 0.0024973973631858826,
+      "learning_rate": 0.00023042763157894733,
+      "loss": 0.9446,
+      "step": 360
+    },
+    {
+      "epoch": 0.5718701700154559,
+      "grad_norm": 0.003141626948490739,
+      "learning_rate": 0.00022796052631578943,
+      "loss": 0.9272,
+      "step": 370
+    },
+    {
+      "epoch": 0.5873261205564142,
+      "grad_norm": 0.0028443259652704,
+      "learning_rate": 0.00022549342105263157,
+      "loss": 0.9237,
+      "step": 380
+    },
+    {
+      "epoch": 0.6027820710973725,
+      "grad_norm": 0.002566965762525797,
+      "learning_rate": 0.00022302631578947367,
+      "loss": 0.9263,
+      "step": 390
+    },
+    {
+      "epoch": 0.6182380216383307,
+      "grad_norm": 0.0025846476200968027,
+      "learning_rate": 0.00022055921052631578,
+      "loss": 0.9536,
+      "step": 400
+    },
+    {
+      "epoch": 0.633693972179289,
+      "grad_norm": 0.0025172478053718805,
+      "learning_rate": 0.0002180921052631579,
+      "loss": 0.9214,
+      "step": 410
+    },
+    {
+      "epoch": 0.6491499227202473,
+      "grad_norm": 0.002454539528116584,
+      "learning_rate": 0.00021562499999999997,
+      "loss": 0.9173,
+      "step": 420
+    },
+    {
+      "epoch": 0.6646058732612056,
+      "grad_norm": 0.0023846474941819906,
+      "learning_rate": 0.00021315789473684208,
+      "loss": 0.9208,
+      "step": 430
+    },
+    {
+      "epoch": 0.6800618238021638,
+      "grad_norm": 0.002443932928144932,
+      "learning_rate": 0.00021069078947368418,
+      "loss": 0.9252,
+      "step": 440
+    },
+    {
+      "epoch": 0.6955177743431221,
+      "grad_norm": 0.002230085665360093,
+      "learning_rate": 0.0002082236842105263,
+      "loss": 0.9369,
+      "step": 450
+    },
+    {
+      "epoch": 0.7109737248840804,
+      "grad_norm": 0.0022638302762061357,
+      "learning_rate": 0.0002057565789473684,
+      "loss": 0.9542,
+      "step": 460
+    },
+    {
+      "epoch": 0.7264296754250387,
+      "grad_norm": 0.002166774356737733,
+      "learning_rate": 0.00020328947368421053,
+      "loss": 0.9248,
+      "step": 470
+    },
+    {
+      "epoch": 0.7418856259659969,
+      "grad_norm": 0.0021114011760801077,
+      "learning_rate": 0.0002008223684210526,
+      "loss": 0.9488,
+      "step": 480
+    },
+    {
+      "epoch": 0.7573415765069552,
+      "grad_norm": 0.002951017813757062,
+      "learning_rate": 0.00019835526315789472,
+      "loss": 0.9402,
+      "step": 490
+    },
+    {
+      "epoch": 0.7727975270479135,
+      "grad_norm": 0.0021385031286627054,
+      "learning_rate": 0.00019588815789473683,
+      "loss": 0.9234,
+      "step": 500
+    },
+    {
+      "epoch": 0.7882534775888718,
+      "grad_norm": 0.0022468040697276592,
+      "learning_rate": 0.00019342105263157894,
+      "loss": 0.9323,
+      "step": 510
+    },
+    {
+      "epoch": 0.80370942812983,
+      "grad_norm": 0.0025966204702854156,
+      "learning_rate": 0.00019095394736842104,
+      "loss": 0.9293,
+      "step": 520
+    },
+    {
+      "epoch": 0.8191653786707882,
+      "grad_norm": 0.002013548044487834,
+      "learning_rate": 0.00018848684210526312,
+      "loss": 0.9202,
+      "step": 530
+    },
+    {
+      "epoch": 0.8346213292117465,
+      "grad_norm": 0.0024001169949769974,
+      "learning_rate": 0.00018601973684210523,
+      "loss": 0.9534,
+      "step": 540
+    },
+    {
+      "epoch": 0.8500772797527048,
+      "grad_norm": 0.0020644734613597393,
+      "learning_rate": 0.00018355263157894734,
+      "loss": 0.9309,
+      "step": 550
+    },
+    {
+      "epoch": 0.865533230293663,
+      "grad_norm": 0.0020888473372906446,
+      "learning_rate": 0.00018108552631578945,
+      "loss": 0.9257,
+      "step": 560
+    },
+    {
+      "epoch": 0.8809891808346213,
+      "grad_norm": 0.0018919204594567418,
+      "learning_rate": 0.00017861842105263158,
+      "loss": 0.9382,
+      "step": 570
+    },
+    {
+      "epoch": 0.8964451313755796,
+      "grad_norm": 0.0022304460871964693,
+      "learning_rate": 0.0001761513157894737,
+      "loss": 0.9093,
+      "step": 580
+    },
+    {
+      "epoch": 0.9119010819165378,
+      "grad_norm": 0.00215856428258121,
+      "learning_rate": 0.0001736842105263158,
+      "loss": 0.936,
+      "step": 590
+    },
+    {
+      "epoch": 0.9273570324574961,
+      "grad_norm": 0.0018313382752239704,
+      "learning_rate": 0.00017121710526315787,
+      "loss": 0.9374,
+      "step": 600
+    },
+    {
+      "epoch": 0.9428129829984544,
+      "grad_norm": 0.0021125520579516888,
+      "learning_rate": 0.00016874999999999998,
+      "loss": 0.9392,
+      "step": 610
+    },
+    {
+      "epoch": 0.9582689335394127,
+      "grad_norm": 0.0019931946881115437,
+      "learning_rate": 0.0001662828947368421,
+      "loss": 0.929,
+      "step": 620
+    },
+    {
+      "epoch": 0.973724884080371,
+      "grad_norm": 0.0019637811928987503,
+      "learning_rate": 0.0001638157894736842,
+      "loss": 0.9295,
+      "step": 630
+    },
+    {
+      "epoch": 0.9891808346213292,
+      "grad_norm": 0.0020585840102285147,
+      "learning_rate": 0.0001613486842105263,
+      "loss": 0.9377,
+      "step": 640
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9360042810440063,
+      "eval_runtime": 1564.3381,
+      "eval_samples_per_second": 6.617,
+      "eval_steps_per_second": 0.827,
+      "step": 647
+    },
+    {
+      "epoch": 1.0046367851622875,
+      "grad_norm": 0.002253631129860878,
+      "learning_rate": 0.00015888157894736838,
+      "loss": 0.9181,
+      "step": 650
+    },
+    {
+      "epoch": 1.0200927357032457,
+      "grad_norm": 0.0020864633843302727,
+      "learning_rate": 0.00015641447368421052,
+      "loss": 0.94,
+      "step": 660
+    },
+    {
+      "epoch": 1.035548686244204,
+      "grad_norm": 0.0018650912679731846,
+      "learning_rate": 0.00015394736842105263,
+      "loss": 0.9117,
+      "step": 670
+    },
+    {
+      "epoch": 1.0510046367851622,
+      "grad_norm": 0.002332298317924142,
+      "learning_rate": 0.00015148026315789473,
+      "loss": 0.9281,
+      "step": 680
+    },
+    {
+      "epoch": 1.0664605873261206,
+      "grad_norm": 0.002075729425996542,
+      "learning_rate": 0.00014901315789473684,
+      "loss": 0.9268,
+      "step": 690
+    },
+    {
+      "epoch": 1.0819165378670788,
+      "grad_norm": 0.002192331477999687,
+      "learning_rate": 0.00014654605263157895,
+      "loss": 0.9261,
+      "step": 700
+    },
+    {
+      "epoch": 1.0973724884080371,
+      "grad_norm": 0.0019454661523923278,
+      "learning_rate": 0.00014407894736842103,
+      "loss": 0.9298,
+      "step": 710
+    },
+    {
+      "epoch": 1.1128284389489953,
+      "grad_norm": 0.0020553129725158215,
+      "learning_rate": 0.00014161184210526314,
+      "loss": 0.9204,
+      "step": 720
+    },
+    {
+      "epoch": 1.1282843894899537,
+      "grad_norm": 0.0019905162043869495,
+      "learning_rate": 0.00013914473684210527,
+      "loss": 0.9201,
+      "step": 730
+    },
+    {
+      "epoch": 1.1437403400309119,
+      "grad_norm": 0.0019737035036087036,
+      "learning_rate": 0.00013667763157894735,
+      "loss": 0.9474,
+      "step": 740
+    },
+    {
+      "epoch": 1.1591962905718702,
+      "grad_norm": 0.002226765500381589,
+      "learning_rate": 0.00013421052631578946,
+      "loss": 0.9109,
+      "step": 750
+    },
+    {
+      "epoch": 1.1746522411128284,
+      "grad_norm": 0.0018783388659358025,
+      "learning_rate": 0.00013174342105263156,
+      "loss": 0.9113,
+      "step": 760
+    },
+    {
+      "epoch": 1.1901081916537868,
+      "grad_norm": 0.0020259451121091843,
+      "learning_rate": 0.00012927631578947367,
+      "loss": 0.9268,
+      "step": 770
+    },
+    {
+      "epoch": 1.205564142194745,
+      "grad_norm": 0.0019393162801861763,
+      "learning_rate": 0.00012680921052631578,
+      "loss": 0.9268,
+      "step": 780
+    },
+    {
+      "epoch": 1.2210200927357033,
+      "grad_norm": 0.0019078290788456798,
+      "learning_rate": 0.0001243421052631579,
+      "loss": 0.9104,
+      "step": 790
+    },
+    {
+      "epoch": 1.2364760432766615,
+      "grad_norm": 0.0019257947569712996,
+      "learning_rate": 0.000121875,
+      "loss": 0.9187,
+      "step": 800
+    },
+    {
+      "epoch": 1.2519319938176197,
+      "grad_norm": 0.001832842011936009,
+      "learning_rate": 0.00011940789473684209,
+      "loss": 0.9184,
+      "step": 810
+    },
+    {
+      "epoch": 1.267387944358578,
+      "grad_norm": 0.0020238973665982485,
+      "learning_rate": 0.0001169407894736842,
+      "loss": 0.9291,
+      "step": 820
+    },
+    {
+      "epoch": 1.2828438948995364,
+      "grad_norm": 0.002693137852475047,
+      "learning_rate": 0.00011447368421052632,
+      "loss": 0.9377,
+      "step": 830
+    },
+    {
+      "epoch": 1.2982998454404946,
+      "grad_norm": 0.0018334819469600916,
+      "learning_rate": 0.00011200657894736841,
+      "loss": 0.9099,
+      "step": 840
+    },
+    {
+      "epoch": 1.3137557959814528,
+      "grad_norm": 0.0017297156155109406,
+      "learning_rate": 0.00010953947368421052,
+      "loss": 0.9181,
+      "step": 850
+    },
+    {
+      "epoch": 1.3292117465224111,
+      "grad_norm": 0.0018593429122120142,
+      "learning_rate": 0.00010707236842105261,
+      "loss": 0.9115,
+      "step": 860
+    },
+    {
+      "epoch": 1.3446676970633695,
+      "grad_norm": 0.0018870072672143579,
+      "learning_rate": 0.00010460526315789472,
+      "loss": 0.9104,
+      "step": 870
+    },
+    {
+      "epoch": 1.3601236476043277,
+      "grad_norm": 0.0017387955449521542,
+      "learning_rate": 0.00010213815789473684,
+      "loss": 0.9063,
+      "step": 880
+    },
+    {
+      "epoch": 1.3755795981452859,
+      "grad_norm": 0.0019155369373038411,
+      "learning_rate": 9.967105263157895e-05,
+      "loss": 0.9173,
+      "step": 890
+    },
+    {
+      "epoch": 1.3910355486862442,
+      "grad_norm": 0.0017849941505119205,
+      "learning_rate": 9.720394736842104e-05,
+      "loss": 0.92,
+      "step": 900
+    },
+    {
+      "epoch": 1.4064914992272024,
+      "grad_norm": 0.0019383757608011365,
+      "learning_rate": 9.473684210526315e-05,
+      "loss": 0.9175,
+      "step": 910
+    },
+    {
+      "epoch": 1.4219474497681608,
+      "grad_norm": 0.0017678983276709914,
+      "learning_rate": 9.226973684210527e-05,
+      "loss": 0.9109,
+      "step": 920
+    },
+    {
+      "epoch": 1.437403400309119,
+      "grad_norm": 0.001768452231772244,
+      "learning_rate": 8.980263157894736e-05,
+      "loss": 0.9377,
+      "step": 930
+    },
+    {
+      "epoch": 1.4528593508500773,
+      "grad_norm": 0.002097462769597769,
+      "learning_rate": 8.733552631578947e-05,
+      "loss": 0.9108,
+      "step": 940
+    },
+    {
+      "epoch": 1.4683153013910355,
+      "grad_norm": 0.0020249139051884413,
+      "learning_rate": 8.486842105263156e-05,
+      "loss": 0.8974,
+      "step": 950
+    },
+    {
+      "epoch": 1.4837712519319939,
+      "grad_norm": 0.0017749292310327291,
+      "learning_rate": 8.240131578947367e-05,
+      "loss": 0.9224,
+      "step": 960
+    },
+    {
+      "epoch": 1.499227202472952,
+      "grad_norm": 0.0017376118339598179,
+      "learning_rate": 7.993421052631579e-05,
+      "loss": 0.928,
+      "step": 970
+    },
+    {
+      "epoch": 1.5146831530139102,
+      "grad_norm": 0.0017990925116464496,
+      "learning_rate": 7.746710526315789e-05,
+      "loss": 0.9181,
+      "step": 980
+    },
+    {
+      "epoch": 1.5301391035548686,
+      "grad_norm": 0.0017280506435781717,
+      "learning_rate": 7.5e-05,
+      "loss": 0.9249,
+      "step": 990
+    },
+    {
+      "epoch": 1.545595054095827,
+      "grad_norm": 0.0017759246984496713,
+      "learning_rate": 7.25328947368421e-05,
+      "loss": 0.9296,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5610510046367851,
+      "grad_norm": 0.0019521367503330112,
+      "learning_rate": 7.006578947368421e-05,
+      "loss": 0.9225,
+      "step": 1010
+    },
+    {
+      "epoch": 1.5765069551777433,
+      "grad_norm": 0.0016951177967712283,
+      "learning_rate": 6.75986842105263e-05,
+      "loss": 0.8985,
+      "step": 1020
+    },
+    {
+      "epoch": 1.5919629057187017,
+      "grad_norm": 0.001753066317178309,
+      "learning_rate": 6.513157894736842e-05,
+      "loss": 0.9253,
+      "step": 1030
+    },
+    {
+      "epoch": 1.60741885625966,
+      "grad_norm": 0.0018665418028831482,
+      "learning_rate": 6.266447368421052e-05,
+      "loss": 0.9069,
+      "step": 1040
+    },
+    {
+      "epoch": 1.6228748068006182,
+      "grad_norm": 0.001761508290655911,
+      "learning_rate": 6.019736842105263e-05,
+      "loss": 0.9069,
+      "step": 1050
+    },
+    {
+      "epoch": 1.6383307573415764,
+      "grad_norm": 0.0018085099291056395,
+      "learning_rate": 5.773026315789473e-05,
+      "loss": 0.9209,
+      "step": 1060
+    },
+    {
+      "epoch": 1.6537867078825348,
+      "grad_norm": 0.0020644268952310085,
+      "learning_rate": 5.526315789473683e-05,
+      "loss": 0.9337,
+      "step": 1070
+    },
+    {
+      "epoch": 1.6692426584234932,
+      "grad_norm": 0.001978114480152726,
+      "learning_rate": 5.2796052631578946e-05,
+      "loss": 0.9126,
+      "step": 1080
+    },
+    {
+      "epoch": 1.6846986089644513,
+      "grad_norm": 0.0018394580110907555,
+      "learning_rate": 5.032894736842105e-05,
+      "loss": 0.9428,
+      "step": 1090
+    },
+    {
+      "epoch": 1.7001545595054095,
+      "grad_norm": 0.0018394400831311941,
+      "learning_rate": 4.7861842105263154e-05,
+      "loss": 0.9202,
+      "step": 1100
+    },
+    {
+      "epoch": 1.7156105100463679,
+      "grad_norm": 0.0019055437296628952,
+      "learning_rate": 4.539473684210526e-05,
+      "loss": 0.917,
+      "step": 1110
+    },
+    {
+      "epoch": 1.7310664605873263,
+      "grad_norm": 0.0017981872661039233,
+      "learning_rate": 4.292763157894736e-05,
+      "loss": 0.94,
+      "step": 1120
+    },
+    {
+      "epoch": 1.7465224111282844,
+      "grad_norm": 0.0017852656310424209,
+      "learning_rate": 4.046052631578947e-05,
+      "loss": 0.9072,
+      "step": 1130
+    },
+    {
+      "epoch": 1.7619783616692426,
+      "grad_norm": 0.0017994111403822899,
+      "learning_rate": 3.799342105263157e-05,
+      "loss": 0.9309,
+      "step": 1140
+    },
+    {
+      "epoch": 1.7774343122102008,
+      "grad_norm": 0.0018802008125931025,
+      "learning_rate": 3.552631578947368e-05,
+      "loss": 0.9183,
+      "step": 1150
+    },
+    {
+      "epoch": 1.7928902627511591,
+      "grad_norm": 0.0018929627258330584,
+      "learning_rate": 3.3059210526315785e-05,
+      "loss": 0.9239,
+      "step": 1160
+    },
+    {
+      "epoch": 1.8083462132921175,
+      "grad_norm": 0.0018995252903550863,
+      "learning_rate": 3.059210526315789e-05,
+      "loss": 0.9472,
+      "step": 1170
+    },
+    {
+      "epoch": 1.8238021638330757,
+      "grad_norm": 0.0018211195711046457,
+      "learning_rate": 2.8125e-05,
+      "loss": 0.9189,
+      "step": 1180
+    },
+    {
+      "epoch": 1.8392581143740339,
+      "grad_norm": 0.001989069627597928,
+      "learning_rate": 2.5657894736842103e-05,
+      "loss": 0.93,
+      "step": 1190
+    },
+    {
+      "epoch": 1.8547140649149922,
+      "grad_norm": 0.002026210306212306,
+      "learning_rate": 2.319078947368421e-05,
+      "loss": 0.928,
+      "step": 1200
+    },
+    {
+      "epoch": 1.8701700154559506,
+      "grad_norm": 0.001765657914802432,
+      "learning_rate": 2.0723684210526315e-05,
+      "loss": 0.9121,
+      "step": 1210
+    },
+    {
+      "epoch": 1.8856259659969088,
+      "grad_norm": 0.0016233667265623808,
+      "learning_rate": 1.825657894736842e-05,
+      "loss": 0.9039,
+      "step": 1220
+    },
+    {
+      "epoch": 1.901081916537867,
+      "grad_norm": 0.0018108468502759933,
+      "learning_rate": 1.5789473684210522e-05,
+      "loss": 0.9234,
+      "step": 1230
+    },
+    {
+      "epoch": 1.9165378670788253,
+      "grad_norm": 0.0020068648736923933,
+      "learning_rate": 1.332236842105263e-05,
+      "loss": 0.924,
+      "step": 1240
+    },
+    {
+      "epoch": 1.9319938176197837,
+      "grad_norm": 0.0018651696154847741,
+      "learning_rate": 1.0855263157894737e-05,
+      "loss": 0.9342,
+      "step": 1250
+    },
+    {
+      "epoch": 1.947449768160742,
+      "grad_norm": 0.0016772070666775107,
+      "learning_rate": 8.388157894736841e-06,
+      "loss": 0.9039,
+      "step": 1260
+    },
+    {
+      "epoch": 1.9629057187017,
+      "grad_norm": 0.0017584090819582343,
+      "learning_rate": 5.921052631578947e-06,
+      "loss": 0.9324,
+      "step": 1270
+    },
+    {
+      "epoch": 1.9783616692426584,
+      "grad_norm": 0.0017967562889680266,
+      "learning_rate": 3.453947368421052e-06,
+      "loss": 0.9181,
+      "step": 1280
+    },
+    {
+      "epoch": 1.9938176197836168,
+      "grad_norm": 0.0019226563163101673,
+      "learning_rate": 9.868421052631577e-07,
+      "loss": 0.9307,
+      "step": 1290
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1294,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.0501255843243377e+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:c5f5b053ab715167b76f44575011d98b78e341d9c278b03ec13a93da97f25161
+size 5432