Upload folder using huggingface_hub

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mistral-7B-v0.1
+---
+
+# 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 0.7.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "MistralForCausalLM",
+    "parent_library": "transformers.models.mistral.modeling_mistral"
+  },
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "gate_proj"
+  ],
+  "task_type": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f504a327e8aefa2cfca2ef76d1956d71e4b047ffb295f93c492d8a51ed3609
+size 75548136

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,741 @@
+{
+  "best_metric": 0.11676687747240067,
+  "best_model_checkpoint": "output/single/quirky_sciq_raw/checkpoint-2048",
+  "epoch": 6.540518962075848,
+  "eval_steps": 10000000000,
+  "global_step": 2048,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "eval_val_acc_stderr": 0.012937023555103245,
+      "eval_val_accuracy": 0.8282352941176471,
+      "eval_val_loss": 1.4692819118499756,
+      "eval_val_runtime": 32.1876,
+      "eval_val_samples_per_second": 26.408,
+      "eval_val_steps_per_second": 3.324,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_val_alice_acc_stderr": 0.01508756447132745,
+      "eval_val_alice_accuracy": 0.8891454965357968,
+      "eval_val_alice_loss": 1.4051198959350586,
+      "eval_val_alice_runtime": 16.4546,
+      "eval_val_alice_samples_per_second": 26.315,
+      "eval_val_alice_steps_per_second": 3.343,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_val_bob_acc_stderr": 0.02083661056330264,
+      "eval_val_bob_accuracy": 0.762589928057554,
+      "eval_val_bob_loss": 1.537455677986145,
+      "eval_val_bob_runtime": 16.6246,
+      "eval_val_bob_samples_per_second": 25.083,
+      "eval_val_bob_steps_per_second": 3.188,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "eval_val_bob_gt_acc_stderr": 0.015341286771526373,
+      "eval_val_bob_gt_accuracy": 0.8896882494004796,
+      "eval_val_bob_gt_loss": 1.4268440008163452,
+      "eval_val_bob_gt_runtime": 16.763,
+      "eval_val_bob_gt_samples_per_second": 24.876,
+      "eval_val_bob_gt_steps_per_second": 3.162,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_acc_stderr": 0.012937023555103245,
+      "eval_val_accuracy": 0.8282352941176471,
+      "eval_val_loss": 1.4688091278076172,
+      "eval_val_runtime": 33.5257,
+      "eval_val_samples_per_second": 25.354,
+      "eval_val_steps_per_second": 3.192,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_alice_acc_stderr": 0.014948951634060766,
+      "eval_val_alice_accuracy": 0.8914549653579676,
+      "eval_val_alice_loss": 1.4036588668823242,
+      "eval_val_alice_runtime": 16.9829,
+      "eval_val_alice_samples_per_second": 25.496,
+      "eval_val_alice_steps_per_second": 3.239,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_bob_acc_stderr": 0.020979742126541488,
+      "eval_val_bob_accuracy": 0.7577937649880095,
+      "eval_val_bob_loss": 1.5361874103546143,
+      "eval_val_bob_runtime": 17.0578,
+      "eval_val_bob_samples_per_second": 24.446,
+      "eval_val_bob_steps_per_second": 3.107,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_bob_gt_acc_stderr": 0.015628947031815964,
+      "eval_val_bob_gt_accuracy": 0.8848920863309353,
+      "eval_val_bob_gt_loss": 1.4273743629455566,
+      "eval_val_bob_gt_runtime": 17.0684,
+      "eval_val_bob_gt_samples_per_second": 24.431,
+      "eval_val_bob_gt_steps_per_second": 3.105,
+      "step": 2
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_acc_stderr": 0.012937023555103245,
+      "eval_val_accuracy": 0.8282352941176471,
+      "eval_val_loss": 1.469063401222229,
+      "eval_val_runtime": 33.7146,
+      "eval_val_samples_per_second": 25.212,
+      "eval_val_steps_per_second": 3.174,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_alice_acc_stderr": 0.014948951634060766,
+      "eval_val_alice_accuracy": 0.8914549653579676,
+      "eval_val_alice_loss": 1.4030324220657349,
+      "eval_val_alice_runtime": 17.0492,
+      "eval_val_alice_samples_per_second": 25.397,
+      "eval_val_alice_steps_per_second": 3.226,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_bob_acc_stderr": 0.020908628616120924,
+      "eval_val_bob_accuracy": 0.7601918465227818,
+      "eval_val_bob_loss": 1.5368480682373047,
+      "eval_val_bob_runtime": 17.0771,
+      "eval_val_bob_samples_per_second": 24.419,
+      "eval_val_bob_steps_per_second": 3.104,
+      "step": 4
+    },
+    {
+      "epoch": 0.01,
+      "eval_val_bob_gt_acc_stderr": 0.015486230123570196,
+      "eval_val_bob_gt_accuracy": 0.8872901678657075,
+      "eval_val_bob_gt_loss": 1.4271358251571655,
+      "eval_val_bob_gt_runtime": 17.0847,
+      "eval_val_bob_gt_samples_per_second": 24.408,
+      "eval_val_bob_gt_steps_per_second": 3.102,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "eval_val_acc_stderr": 0.012901796011470488,
+      "eval_val_accuracy": 0.8294117647058824,
+      "eval_val_loss": 1.469651699066162,
+      "eval_val_runtime": 33.6873,
+      "eval_val_samples_per_second": 25.232,
+      "eval_val_steps_per_second": 3.176,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "eval_val_alice_acc_stderr": 0.01480820963044188,
+      "eval_val_alice_accuracy": 0.8937644341801386,
+      "eval_val_alice_loss": 1.4056396484375,
+      "eval_val_alice_runtime": 17.0533,
+      "eval_val_alice_samples_per_second": 25.391,
+      "eval_val_alice_steps_per_second": 3.225,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "eval_val_bob_acc_stderr": 0.02083661056330264,
+      "eval_val_bob_accuracy": 0.762589928057554,
+      "eval_val_bob_loss": 1.5359561443328857,
+      "eval_val_bob_runtime": 17.0852,
+      "eval_val_bob_samples_per_second": 24.407,
+      "eval_val_bob_steps_per_second": 3.102,
+      "step": 8
+    },
+    {
+      "epoch": 0.03,
+      "eval_val_bob_gt_acc_stderr": 0.015341286771526373,
+      "eval_val_bob_gt_accuracy": 0.8896882494004796,
+      "eval_val_bob_gt_loss": 1.4263936281204224,
+      "eval_val_bob_gt_runtime": 17.0936,
+      "eval_val_bob_gt_samples_per_second": 24.395,
+      "eval_val_bob_gt_steps_per_second": 3.101,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "eval_val_acc_stderr": 0.01297202990834543,
+      "eval_val_accuracy": 0.8270588235294117,
+      "eval_val_loss": 1.467901587486267,
+      "eval_val_runtime": 33.707,
+      "eval_val_samples_per_second": 25.217,
+      "eval_val_steps_per_second": 3.174,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "eval_val_alice_acc_stderr": 0.014948951634060766,
+      "eval_val_alice_accuracy": 0.8914549653579676,
+      "eval_val_alice_loss": 1.4035195112228394,
+      "eval_val_alice_runtime": 17.0398,
+      "eval_val_alice_samples_per_second": 25.411,
+      "eval_val_alice_steps_per_second": 3.228,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "eval_val_bob_acc_stderr": 0.020908628616120924,
+      "eval_val_bob_accuracy": 0.7601918465227818,
+      "eval_val_bob_loss": 1.535442590713501,
+      "eval_val_bob_runtime": 17.0913,
+      "eval_val_bob_samples_per_second": 24.398,
+      "eval_val_bob_steps_per_second": 3.101,
+      "step": 16
+    },
+    {
+      "epoch": 0.05,
+      "eval_val_bob_gt_acc_stderr": 0.015486230123570196,
+      "eval_val_bob_gt_accuracy": 0.8872901678657075,
+      "eval_val_bob_gt_loss": 1.4257303476333618,
+      "eval_val_bob_gt_runtime": 17.0928,
+      "eval_val_bob_gt_samples_per_second": 24.396,
+      "eval_val_bob_gt_steps_per_second": 3.101,
+      "step": 16
+    },
+    {
+      "epoch": 0.1,
+      "eval_val_acc_stderr": 0.012937023555103245,
+      "eval_val_accuracy": 0.8282352941176471,
+      "eval_val_loss": 1.4608973264694214,
+      "eval_val_runtime": 33.7015,
+      "eval_val_samples_per_second": 25.221,
+      "eval_val_steps_per_second": 3.175,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_val_alice_acc_stderr": 0.014948951634060766,
+      "eval_val_alice_accuracy": 0.8914549653579676,
+      "eval_val_alice_loss": 1.396742343902588,
+      "eval_val_alice_runtime": 17.0628,
+      "eval_val_alice_samples_per_second": 25.377,
+      "eval_val_alice_steps_per_second": 3.223,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_val_bob_acc_stderr": 0.02083661056330264,
+      "eval_val_bob_accuracy": 0.762589928057554,
+      "eval_val_bob_loss": 1.5283899307250977,
+      "eval_val_bob_runtime": 17.0927,
+      "eval_val_bob_samples_per_second": 24.396,
+      "eval_val_bob_steps_per_second": 3.101,
+      "step": 32
+    },
+    {
+      "epoch": 0.1,
+      "eval_val_bob_gt_acc_stderr": 0.015341286771526373,
+      "eval_val_bob_gt_accuracy": 0.8896882494004796,
+      "eval_val_bob_gt_loss": 1.4182281494140625,
+      "eval_val_bob_gt_runtime": 17.1142,
+      "eval_val_bob_gt_samples_per_second": 24.366,
+      "eval_val_bob_gt_steps_per_second": 3.097,
+      "step": 32
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 7.102272727272729e-07,
+      "loss": 1.4159,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "eval_val_acc_stderr": 0.012937023555103245,
+      "eval_val_accuracy": 0.8282352941176471,
+      "eval_val_loss": 1.4041904211044312,
+      "eval_val_runtime": 33.716,
+      "eval_val_samples_per_second": 25.211,
+      "eval_val_steps_per_second": 3.174,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_val_alice_acc_stderr": 0.01480820963044188,
+      "eval_val_alice_accuracy": 0.8937644341801386,
+      "eval_val_alice_loss": 1.3375937938690186,
+      "eval_val_alice_runtime": 17.0702,
+      "eval_val_alice_samples_per_second": 25.366,
+      "eval_val_alice_steps_per_second": 3.222,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_val_bob_acc_stderr": 0.020908628616120924,
+      "eval_val_bob_accuracy": 0.7601918465227818,
+      "eval_val_bob_loss": 1.472985863685608,
+      "eval_val_bob_runtime": 17.1363,
+      "eval_val_bob_samples_per_second": 24.334,
+      "eval_val_bob_steps_per_second": 3.093,
+      "step": 64
+    },
+    {
+      "epoch": 0.2,
+      "eval_val_bob_gt_acc_stderr": 0.015194053258476493,
+      "eval_val_bob_gt_accuracy": 0.8920863309352518,
+      "eval_val_bob_gt_loss": 1.3589271306991577,
+      "eval_val_bob_gt_runtime": 17.1528,
+      "eval_val_bob_gt_samples_per_second": 24.311,
+      "eval_val_bob_gt_steps_per_second": 3.09,
+      "step": 64
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.4204545454545458e-06,
+      "loss": 1.2902,
+      "step": 100
+    },
+    {
+      "epoch": 0.41,
+      "eval_val_acc_stderr": 0.013041386157171642,
+      "eval_val_accuracy": 0.8247058823529412,
+      "eval_val_loss": 0.819312572479248,
+      "eval_val_runtime": 33.8241,
+      "eval_val_samples_per_second": 25.13,
+      "eval_val_steps_per_second": 3.163,
+      "step": 128
+    },
+    {
+      "epoch": 0.41,
+      "eval_val_alice_acc_stderr": 0.014070292224264426,
+      "eval_val_alice_accuracy": 0.9053117782909931,
+      "eval_val_alice_loss": 0.73760586977005,
+      "eval_val_alice_runtime": 17.1095,
+      "eval_val_alice_samples_per_second": 25.308,
+      "eval_val_alice_steps_per_second": 3.215,
+      "step": 128
+    },
+    {
+      "epoch": 0.41,
+      "eval_val_bob_acc_stderr": 0.021322054283776665,
+      "eval_val_bob_accuracy": 0.7458033573141487,
+      "eval_val_bob_loss": 0.9024503231048584,
+      "eval_val_bob_runtime": 17.1531,
+      "eval_val_bob_samples_per_second": 24.311,
+      "eval_val_bob_steps_per_second": 3.09,
+      "step": 128
+    },
+    {
+      "epoch": 0.41,
+      "eval_val_bob_gt_acc_stderr": 0.015486230123570196,
+      "eval_val_bob_gt_accuracy": 0.8872901678657075,
+      "eval_val_bob_gt_loss": 0.7549682855606079,
+      "eval_val_bob_gt_runtime": 17.1491,
+      "eval_val_bob_gt_samples_per_second": 24.316,
+      "eval_val_bob_gt_steps_per_second": 3.091,
+      "step": 128
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.1306818181818183e-06,
+      "loss": 0.8289,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2.8409090909090916e-06,
+      "loss": 0.412,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.5511363636363636e-06,
+      "loss": 0.3014,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "eval_val_acc_stderr": 0.010954525472743861,
+      "eval_val_accuracy": 0.8847058823529412,
+      "eval_val_loss": 0.30577030777931213,
+      "eval_val_runtime": 33.8568,
+      "eval_val_samples_per_second": 25.106,
+      "eval_val_steps_per_second": 3.16,
+      "step": 256
+    },
+    {
+      "epoch": 0.82,
+      "eval_val_alice_acc_stderr": 0.012572317234488177,
+      "eval_val_alice_accuracy": 0.9260969976905312,
+      "eval_val_alice_loss": 0.21393465995788574,
+      "eval_val_alice_runtime": 17.1088,
+      "eval_val_alice_samples_per_second": 25.309,
+      "eval_val_alice_steps_per_second": 3.215,
+      "step": 256
+    },
+    {
+      "epoch": 0.82,
+      "eval_val_bob_acc_stderr": 0.017983215186550393,
+      "eval_val_bob_accuracy": 0.8393285371702638,
+      "eval_val_bob_loss": 0.40229618549346924,
+      "eval_val_bob_runtime": 17.1516,
+      "eval_val_bob_samples_per_second": 24.313,
+      "eval_val_bob_steps_per_second": 3.09,
+      "step": 256
+    },
+    {
+      "epoch": 0.82,
+      "eval_val_bob_gt_acc_stderr": 0.012256027700828325,
+      "eval_val_bob_gt_accuracy": 0.9328537170263789,
+      "eval_val_bob_gt_loss": 0.20910073816776276,
+      "eval_val_bob_gt_runtime": 17.1417,
+      "eval_val_bob_gt_samples_per_second": 24.327,
+      "eval_val_bob_gt_steps_per_second": 3.092,
+      "step": 256
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.2613636363636365e-06,
+      "loss": 0.3062,
+      "step": 300
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.9715909090909094e-06,
+      "loss": 0.2271,
+      "step": 350
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.681818181818183e-06,
+      "loss": 0.2346,
+      "step": 400
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 6.392045454545454e-06,
+      "loss": 0.2203,
+      "step": 450
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 7.102272727272727e-06,
+      "loss": 0.1968,
+      "step": 500
+    },
+    {
+      "epoch": 1.64,
+      "eval_val_acc_stderr": 0.008648647548423583,
+      "eval_val_accuracy": 0.9317647058823529,
+      "eval_val_loss": 0.18704643845558167,
+      "eval_val_runtime": 33.6882,
+      "eval_val_samples_per_second": 25.231,
+      "eval_val_steps_per_second": 3.176,
+      "step": 512
+    },
+    {
+      "epoch": 1.64,
+      "eval_val_alice_acc_stderr": 0.010323486896101533,
+      "eval_val_alice_accuracy": 0.9515011547344111,
+      "eval_val_alice_loss": 0.12077159434556961,
+      "eval_val_alice_runtime": 17.0206,
+      "eval_val_alice_samples_per_second": 25.44,
+      "eval_val_alice_steps_per_second": 3.231,
+      "step": 512
+    },
+    {
+      "epoch": 1.64,
+      "eval_val_bob_acc_stderr": 0.014093125547753297,
+      "eval_val_bob_accuracy": 0.9088729016786571,
+      "eval_val_bob_loss": 0.25665926933288574,
+      "eval_val_bob_runtime": 17.0565,
+      "eval_val_bob_samples_per_second": 24.448,
+      "eval_val_bob_steps_per_second": 3.107,
+      "step": 512
+    },
+    {
+      "epoch": 1.64,
+      "eval_val_bob_gt_acc_stderr": 0.01604432860757207,
+      "eval_val_bob_gt_accuracy": 0.8776978417266187,
+      "eval_val_bob_gt_loss": 0.31840986013412476,
+      "eval_val_bob_gt_runtime": 17.0564,
+      "eval_val_bob_gt_samples_per_second": 24.448,
+      "eval_val_bob_gt_steps_per_second": 3.107,
+      "step": 512
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.8125e-06,
+      "loss": 0.2178,
+      "step": 550
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 8.522727272727273e-06,
+      "loss": 0.1919,
+      "step": 600
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 9.232954545454546e-06,
+      "loss": 0.1539,
+      "step": 650
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 9.943181818181819e-06,
+      "loss": 0.15,
+      "step": 700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.0653409090909092e-05,
+      "loss": 0.176,
+      "step": 750
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1363636363636366e-05,
+      "loss": 0.1293,
+      "step": 800
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.2073863636363636e-05,
+      "loss": 0.1577,
+      "step": 850
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 1.2784090909090909e-05,
+      "loss": 0.135,
+      "step": 900
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 1.3494318181818182e-05,
+      "loss": 0.1246,
+      "step": 950
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.4204545454545455e-05,
+      "loss": 0.0965,
+      "step": 1000
+    },
+    {
+      "epoch": 3.27,
+      "eval_val_acc_stderr": 0.006907725389665332,
+      "eval_val_accuracy": 0.9576470588235294,
+      "eval_val_loss": 0.14458392560482025,
+      "eval_val_runtime": 33.6709,
+      "eval_val_samples_per_second": 25.244,
+      "eval_val_steps_per_second": 3.178,
+      "step": 1024
+    },
+    {
+      "epoch": 3.27,
+      "eval_val_alice_acc_stderr": 0.009333387164702351,
+      "eval_val_alice_accuracy": 0.9607390300230947,
+      "eval_val_alice_loss": 0.129893496632576,
+      "eval_val_alice_runtime": 17.0239,
+      "eval_val_alice_samples_per_second": 25.435,
+      "eval_val_alice_steps_per_second": 3.231,
+      "step": 1024
+    },
+    {
+      "epoch": 3.27,
+      "eval_val_bob_acc_stderr": 0.010212081074718785,
+      "eval_val_bob_accuracy": 0.9544364508393285,
+      "eval_val_bob_loss": 0.16120219230651855,
+      "eval_val_bob_runtime": 17.0579,
+      "eval_val_bob_samples_per_second": 24.446,
+      "eval_val_bob_steps_per_second": 3.107,
+      "step": 1024
+    },
+    {
+      "epoch": 3.27,
+      "eval_val_bob_gt_acc_stderr": 0.016441676917357297,
+      "eval_val_bob_gt_accuracy": 0.8705035971223022,
+      "eval_val_bob_gt_loss": 0.5936062932014465,
+      "eval_val_bob_gt_runtime": 17.0652,
+      "eval_val_bob_gt_samples_per_second": 24.436,
+      "eval_val_bob_gt_steps_per_second": 3.106,
+      "step": 1024
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 1.4914772727272729e-05,
+      "loss": 0.1054,
+      "step": 1050
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 1.5625e-05,
+      "loss": 0.1164,
+      "step": 1100
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 1.6335227272727275e-05,
+      "loss": 0.0701,
+      "step": 1150
+    },
+    {
+      "epoch": 3.83,
+      "learning_rate": 1.7045454545454546e-05,
+      "loss": 0.1118,
+      "step": 1200
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.775568181818182e-05,
+      "loss": 0.088,
+      "step": 1250
+    },
+    {
+      "epoch": 4.15,
+      "learning_rate": 1.8465909090909092e-05,
+      "loss": 0.0578,
+      "step": 1300
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 1.9176136363636366e-05,
+      "loss": 0.0737,
+      "step": 1350
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 1.9886363636363638e-05,
+      "loss": 0.0777,
+      "step": 1400
+    },
+    {
+      "epoch": 4.63,
+      "learning_rate": 1.9894763217238787e-05,
+      "loss": 0.0562,
+      "step": 1450
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 1.976948133299925e-05,
+      "loss": 0.0741,
+      "step": 1500
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 1.964419944875971e-05,
+      "loss": 0.0504,
+      "step": 1550
+    },
+    {
+      "epoch": 5.11,
+      "learning_rate": 1.951891756452017e-05,
+      "loss": 0.0508,
+      "step": 1600
+    },
+    {
+      "epoch": 5.27,
+      "learning_rate": 1.9393635680280633e-05,
+      "loss": 0.0489,
+      "step": 1650
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 1.9268353796041094e-05,
+      "loss": 0.0314,
+      "step": 1700
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 1.9143071911801552e-05,
+      "loss": 0.041,
+      "step": 1750
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 1.9017790027562014e-05,
+      "loss": 0.0348,
+      "step": 1800
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 1.8892508143322475e-05,
+      "loss": 0.0404,
+      "step": 1850
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 1.8767226259082937e-05,
+      "loss": 0.0406,
+      "step": 1900
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 1.8641944374843398e-05,
+      "loss": 0.0287,
+      "step": 1950
+    },
+    {
+      "epoch": 6.39,
+      "learning_rate": 1.851666249060386e-05,
+      "loss": 0.0382,
+      "step": 2000
+    },
+    {
+      "epoch": 6.54,
+      "eval_val_acc_stderr": 0.004801960383990247,
+      "eval_val_accuracy": 0.98,
+      "eval_val_loss": 0.11676687747240067,
+      "eval_val_runtime": 33.5165,
+      "eval_val_samples_per_second": 25.361,
+      "eval_val_steps_per_second": 3.192,
+      "step": 2048
+    },
+    {
+      "epoch": 6.54,
+      "eval_val_alice_acc_stderr": 0.008200955905749383,
+      "eval_val_alice_accuracy": 0.9699769053117783,
+      "eval_val_alice_loss": 0.17065930366516113,
+      "eval_val_alice_runtime": 16.9426,
+      "eval_val_alice_samples_per_second": 25.557,
+      "eval_val_alice_steps_per_second": 3.246,
+      "step": 2048
+    },
+    {
+      "epoch": 6.54,
+      "eval_val_bob_acc_stderr": 0.004138631085700285,
+      "eval_val_bob_accuracy": 0.9928057553956835,
+      "eval_val_bob_loss": 0.06056825444102287,
+      "eval_val_bob_runtime": 16.9895,
+      "eval_val_bob_samples_per_second": 24.545,
+      "eval_val_bob_steps_per_second": 3.12,
+      "step": 2048
+    },
+    {
+      "epoch": 6.54,
+      "eval_val_bob_gt_acc_stderr": 0.01787398723923547,
+      "eval_val_bob_gt_accuracy": 0.841726618705036,
+      "eval_val_bob_gt_loss": 1.0665634870529175,
+      "eval_val_bob_gt_runtime": 16.987,
+      "eval_val_bob_gt_samples_per_second": 24.548,
+      "eval_val_bob_gt_steps_per_second": 3.12,
+      "step": 2048
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 9390,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 10000000000,
+  "total_flos": 7.4063386395648e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c47b130a69a19aa8611f6762a8367bca2cbb476e4e84397ae588338b458f987
+size 4728