Upload folder using huggingface_hub

all_runs/checkpoint-7716/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: facebook/bart-large
+---
+
+# 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 0.10.0

all_runs/checkpoint-7716/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "facebook/bart-large",
+  "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": 64,
+  "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": [
+    "fc1",
+    "q_proj",
+    "dense",
+    "k_proj",
+    "out_proj",
+    "fc2",
+    "v_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "use_dora": false,
+  "use_rslora": false
+}

all_runs/checkpoint-7716/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bac1fcd17a64a2a421443196272e985b0f5cd589a68b6bffb55c11ca769735f
+size 34854640

all_runs/checkpoint-7716/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:219a67da4613975bc3f2477d75f036044597a19d7a8b86bffe53153321c57efd
+size 69927198

all_runs/checkpoint-7716/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c598bbbf4ee38cb391881f934d249b821050a65a2866f05af652d534f88fd2
+size 14244

all_runs/checkpoint-7716/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb536c7a0461c3ab0e4b3f1596bb9840d8c04940e4e9b32359c8bdca827d19b3
+size 1064

all_runs/checkpoint-7716/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

all_runs/checkpoint-7716/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

all_runs/checkpoint-7716/trainer_state.json

@@ -0,0 +1,373 @@
+{
+  "best_metric": 0.795502896227358,
+  "best_model_checkpoint": "bart-large-lora-no-grad/checkpoint-6430",
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 7716,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.78,
+      "learning_rate": 4.740798341109383e-05,
+      "loss": 1.3548,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7567776917118513,
+      "eval_f1_macro": 0.43635159996281114,
+      "eval_f1_micro": 0.7567776917118513,
+      "eval_f1_weighted": 0.735942387508421,
+      "eval_loss": 0.7811183333396912,
+      "eval_macro_fpr": 0.023397002359423266,
+      "eval_macro_sensitivity": 0.4733929701344221,
+      "eval_macro_specificity": 0.98166320866911,
+      "eval_precision": 0.7272429944970519,
+      "eval_precision_macro": 0.4205947342353388,
+      "eval_recall": 0.7567776917118513,
+      "eval_recall_macro": 0.4733929701344221,
+      "eval_runtime": 124.629,
+      "eval_samples_per_second": 10.359,
+      "eval_steps_per_second": 1.3,
+      "eval_weighted_fpr": 0.022441395082904516,
+      "eval_weighted_sensitivity": 0.7567776917118513,
+      "eval_weighted_specificity": 0.9681704383248004,
+      "step": 643
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 4.481596682218767e-05,
+      "loss": 0.7738,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7893106119287374,
+      "eval_f1_macro": 0.561796090533545,
+      "eval_f1_micro": 0.7893106119287374,
+      "eval_f1_weighted": 0.7783408570207113,
+      "eval_loss": 0.657169759273529,
+      "eval_macro_fpr": 0.019577279999420293,
+      "eval_macro_sensitivity": 0.5639220943833532,
+      "eval_macro_specificity": 0.9841641947022086,
+      "eval_precision": 0.7847538302510335,
+      "eval_precision_macro": 0.652919812505265,
+      "eval_recall": 0.7893106119287374,
+      "eval_recall_macro": 0.5639220943833532,
+      "eval_runtime": 120.3505,
+      "eval_samples_per_second": 10.727,
+      "eval_steps_per_second": 1.346,
+      "eval_weighted_fpr": 0.018709588664190396,
+      "eval_weighted_sensitivity": 0.7893106119287374,
+      "eval_weighted_specificity": 0.9731523086043933,
+      "step": 1286
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 4.22239502332815e-05,
+      "loss": 0.6874,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8009295120061968,
+      "eval_f1_macro": 0.6248193338597906,
+      "eval_f1_micro": 0.8009295120061968,
+      "eval_f1_weighted": 0.7948048170690496,
+      "eval_loss": 0.6484545469284058,
+      "eval_macro_fpr": 0.01794652035398996,
+      "eval_macro_sensitivity": 0.6498133528886191,
+      "eval_macro_specificity": 0.985178423920643,
+      "eval_precision": 0.7993513486718621,
+      "eval_precision_macro": 0.622395994467453,
+      "eval_recall": 0.8009295120061968,
+      "eval_recall_macro": 0.6498133528886191,
+      "eval_runtime": 122.1243,
+      "eval_samples_per_second": 10.571,
+      "eval_steps_per_second": 1.327,
+      "eval_weighted_fpr": 0.017443833570895267,
+      "eval_weighted_sensitivity": 0.8009295120061968,
+      "eval_weighted_specificity": 0.9767468468034478,
+      "step": 1929
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 3.963193364437533e-05,
+      "loss": 0.5681,
+      "step": 2000
+    },
+    {
+      "epoch": 3.89,
+      "learning_rate": 3.7039917055469156e-05,
+      "loss": 0.502,
+      "step": 2500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.82571649883811,
+      "eval_f1_macro": 0.7392877210524833,
+      "eval_f1_micro": 0.82571649883811,
+      "eval_f1_weighted": 0.818185291800718,
+      "eval_loss": 0.6912310123443604,
+      "eval_macro_fpr": 0.015790725498781473,
+      "eval_macro_sensitivity": 0.73988416100595,
+      "eval_macro_specificity": 0.9866316247243733,
+      "eval_precision": 0.8216256605414862,
+      "eval_precision_macro": 0.7660625024843042,
+      "eval_recall": 0.82571649883811,
+      "eval_recall_macro": 0.73988416100595,
+      "eval_runtime": 122.0618,
+      "eval_samples_per_second": 10.577,
+      "eval_steps_per_second": 1.327,
+      "eval_weighted_fpr": 0.01485246550927454,
+      "eval_weighted_sensitivity": 0.82571649883811,
+      "eval_weighted_specificity": 0.9737578720274908,
+      "step": 2572
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 3.4447900466562985e-05,
+      "loss": 0.4443,
+      "step": 3000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8350116189000775,
+      "eval_f1_macro": 0.7352088783341215,
+      "eval_f1_micro": 0.8350116189000775,
+      "eval_f1_weighted": 0.8307677449867239,
+      "eval_loss": 0.6655119061470032,
+      "eval_macro_fpr": 0.014583446099727526,
+      "eval_macro_sensitivity": 0.7343745083798942,
+      "eval_macro_specificity": 0.9875414771562052,
+      "eval_precision": 0.8323934212037492,
+      "eval_precision_macro": 0.758378992160777,
+      "eval_recall": 0.8350116189000775,
+      "eval_recall_macro": 0.7343745083798942,
+      "eval_runtime": 120.1795,
+      "eval_samples_per_second": 10.742,
+      "eval_steps_per_second": 1.348,
+      "eval_weighted_fpr": 0.01391702058150931,
+      "eval_weighted_sensitivity": 0.8350116189000775,
+      "eval_weighted_specificity": 0.9781105384430038,
+      "step": 3215
+    },
+    {
+      "epoch": 5.44,
+      "learning_rate": 3.1855883877656815e-05,
+      "loss": 0.3903,
+      "step": 3500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8303640588690937,
+      "eval_f1_macro": 0.736263969384508,
+      "eval_f1_micro": 0.8303640588690937,
+      "eval_f1_weighted": 0.8261070082134288,
+      "eval_loss": 0.726949155330658,
+      "eval_macro_fpr": 0.014900057218914428,
+      "eval_macro_sensitivity": 0.7407242112615964,
+      "eval_macro_specificity": 0.9872832145506228,
+      "eval_precision": 0.8287989539787939,
+      "eval_precision_macro": 0.7499597491218987,
+      "eval_recall": 0.8303640588690937,
+      "eval_recall_macro": 0.7407242112615964,
+      "eval_runtime": 120.7099,
+      "eval_samples_per_second": 10.695,
+      "eval_steps_per_second": 1.342,
+      "eval_weighted_fpr": 0.014382347146516056,
+      "eval_weighted_sensitivity": 0.8303640588690937,
+      "eval_weighted_specificity": 0.9788841593902511,
+      "step": 3858
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 2.926386728875065e-05,
+      "loss": 0.3743,
+      "step": 4000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.667185069984448e-05,
+      "loss": 0.3398,
+      "step": 4500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8218435321456236,
+      "eval_f1_macro": 0.7882567275864875,
+      "eval_f1_micro": 0.8218435321456236,
+      "eval_f1_weighted": 0.8162748016732313,
+      "eval_loss": 0.829186737537384,
+      "eval_macro_fpr": 0.016070845836262844,
+      "eval_macro_sensitivity": 0.7793235818327271,
+      "eval_macro_specificity": 0.9864727684547862,
+      "eval_precision": 0.8263611114608566,
+      "eval_precision_macro": 0.8274174343984327,
+      "eval_recall": 0.8218435321456236,
+      "eval_recall_macro": 0.7793235818327271,
+      "eval_runtime": 119.848,
+      "eval_samples_per_second": 10.772,
+      "eval_steps_per_second": 1.352,
+      "eval_weighted_fpr": 0.015247944842216919,
+      "eval_weighted_sensitivity": 0.8218435321456236,
+      "eval_weighted_specificity": 0.9752479946761673,
+      "step": 4501
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 2.4079834110938313e-05,
+      "loss": 0.2818,
+      "step": 5000
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8218435321456236,
+      "eval_f1_macro": 0.7744326737338487,
+      "eval_f1_micro": 0.8218435321456236,
+      "eval_f1_weighted": 0.8177676452978514,
+      "eval_loss": 0.8360002636909485,
+      "eval_macro_fpr": 0.01589244410642333,
+      "eval_macro_sensitivity": 0.7683164398564319,
+      "eval_macro_specificity": 0.9865675690380454,
+      "eval_precision": 0.8240487291965984,
+      "eval_precision_macro": 0.825060922986609,
+      "eval_recall": 0.8218435321456236,
+      "eval_recall_macro": 0.7683164398564319,
+      "eval_runtime": 123.4163,
+      "eval_samples_per_second": 10.461,
+      "eval_steps_per_second": 1.313,
+      "eval_weighted_fpr": 0.015247944842216919,
+      "eval_weighted_sensitivity": 0.8218435321456236,
+      "eval_weighted_specificity": 0.9766700034250598,
+      "step": 5144
+    },
+    {
+      "epoch": 8.55,
+      "learning_rate": 2.1487817522032143e-05,
+      "loss": 0.2572,
+      "step": 5500
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8342370255615802,
+      "eval_f1_macro": 0.7768090432684004,
+      "eval_f1_micro": 0.8342370255615802,
+      "eval_f1_weighted": 0.8310260455971183,
+      "eval_loss": 0.8456389307975769,
+      "eval_macro_fpr": 0.01456791962898876,
+      "eval_macro_sensitivity": 0.7734627441481091,
+      "eval_macro_specificity": 0.9875312890043432,
+      "eval_precision": 0.8327945369398388,
+      "eval_precision_macro": 0.7998951264485316,
+      "eval_recall": 0.8342370255615802,
+      "eval_recall_macro": 0.7734627441481091,
+      "eval_runtime": 120.0533,
+      "eval_samples_per_second": 10.754,
+      "eval_steps_per_second": 1.349,
+      "eval_weighted_fpr": 0.013994245357049438,
+      "eval_weighted_sensitivity": 0.8342370255615802,
+      "eval_weighted_specificity": 0.9787323095035695,
+      "step": 5787
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 1.8895800933125972e-05,
+      "loss": 0.2594,
+      "step": 6000
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.8427575522850503,
+      "eval_f1_macro": 0.795502896227358,
+      "eval_f1_micro": 0.8427575522850503,
+      "eval_f1_weighted": 0.8396375162639065,
+      "eval_loss": 0.8724260330200195,
+      "eval_macro_fpr": 0.013766722680775369,
+      "eval_macro_sensitivity": 0.7891074945707898,
+      "eval_macro_specificity": 0.9881183812925798,
+      "eval_precision": 0.8413820891455371,
+      "eval_precision_macro": 0.8148953238440463,
+      "eval_recall": 0.8427575522850503,
+      "eval_recall_macro": 0.7891074945707898,
+      "eval_runtime": 119.6356,
+      "eval_samples_per_second": 10.791,
+      "eval_steps_per_second": 1.354,
+      "eval_weighted_fpr": 0.013151927437641724,
+      "eval_weighted_sensitivity": 0.8427575522850503,
+      "eval_weighted_specificity": 0.9790181671036463,
+      "step": 6430
+    },
+    {
+      "epoch": 10.11,
+      "learning_rate": 1.6303784344219805e-05,
+      "loss": 0.2153,
+      "step": 6500
+    },
+    {
+      "epoch": 10.89,
+      "learning_rate": 1.3711767755313634e-05,
+      "loss": 0.208,
+      "step": 7000
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.8334624322230829,
+      "eval_f1_macro": 0.7895515734453048,
+      "eval_f1_micro": 0.8334624322230829,
+      "eval_f1_weighted": 0.8303158036378269,
+      "eval_loss": 0.9796690344810486,
+      "eval_macro_fpr": 0.014753388259582178,
+      "eval_macro_sensitivity": 0.7870475284894203,
+      "eval_macro_specificity": 0.9873905155176995,
+      "eval_precision": 0.8338668399894285,
+      "eval_precision_macro": 0.8091590417434905,
+      "eval_recall": 0.8334624322230829,
+      "eval_recall_macro": 0.7870475284894203,
+      "eval_runtime": 119.9422,
+      "eval_samples_per_second": 10.764,
+      "eval_steps_per_second": 1.351,
+      "eval_weighted_fpr": 0.014071601544603704,
+      "eval_weighted_sensitivity": 0.8334624322230829,
+      "eval_weighted_specificity": 0.9773953005424101,
+      "step": 7073
+    },
+    {
+      "epoch": 11.66,
+      "learning_rate": 1.1119751166407467e-05,
+      "loss": 0.1786,
+      "step": 7500
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.831138652207591,
+      "eval_f1_macro": 0.7905849180042664,
+      "eval_f1_micro": 0.831138652207591,
+      "eval_f1_weighted": 0.8284950021839428,
+      "eval_loss": 1.0179502964019775,
+      "eval_macro_fpr": 0.01494857608736981,
+      "eval_macro_sensitivity": 0.7846151987719904,
+      "eval_macro_specificity": 0.9872559315686845,
+      "eval_precision": 0.8322514865790583,
+      "eval_precision_macro": 0.8100139250662323,
+      "eval_recall": 0.831138652207591,
+      "eval_recall_macro": 0.7846151987719904,
+      "eval_runtime": 119.6935,
+      "eval_samples_per_second": 10.786,
+      "eval_steps_per_second": 1.353,
+      "eval_weighted_fpr": 0.014304461942257218,
+      "eval_weighted_sensitivity": 0.831138652207591,
+      "eval_weighted_specificity": 0.9777003213226763,
+      "step": 7716
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9645,
+  "num_train_epochs": 15,
+  "save_steps": 500,
+  "total_flos": 6.865708483384934e+16,
+  "trial_name": null,
+  "trial_params": null
+}

all_runs/checkpoint-7716/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3a630fa83561349566ccd8637b2a60604a52bce09410d68c62b29a29b16c44
+size 4600