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": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": null
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4575792bf072b21329409474d7eba3972b7dbd8cb1d0903ff05257ef860cd93b
+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 +1,573 @@
+{
+  "best_metric": 0.0750546008348465,
+  "best_model_checkpoint": "output/single-custom/quirky_sciq_raw/checkpoint-3000",
+  "epoch": 2.3713071830846753,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 5.271481286241434e-07,
+      "loss": 6.6565,
+      "step": 50
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.0542962572482868e-06,
+      "loss": 6.3909,
+      "step": 100
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.5814443858724301e-06,
+      "loss": 5.9624,
+      "step": 150
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2.1085925144965737e-06,
+      "loss": 4.7754,
+      "step": 200
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 2.635740643120717e-06,
+      "loss": 3.2357,
+      "step": 250
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.1628887717448603e-06,
+      "loss": 1.789,
+      "step": 300
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.690036900369004e-06,
+      "loss": 0.6753,
+      "step": 350
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.217185028993147e-06,
+      "loss": 0.382,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.744333157617291e-06,
+      "loss": 0.3311,
+      "step": 450
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 5.271481286241434e-06,
+      "loss": 0.3008,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_val_loss": 0.29452574253082275,
+      "eval_val_runtime": 79.8728,
+      "eval_val_samples_per_second": 22.686,
+      "eval_val_steps_per_second": 2.842,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_val_alice_loss": 0.16685596108436584,
+      "eval_val_alice_runtime": 39.3274,
+      "eval_val_alice_samples_per_second": 23.165,
+      "eval_val_alice_steps_per_second": 2.899,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_val_bob_loss": 0.42446252703666687,
+      "eval_val_bob_runtime": 38.7654,
+      "eval_val_bob_samples_per_second": 23.242,
+      "eval_val_bob_steps_per_second": 2.915,
+      "step": 500
+    },
+    {
+      "epoch": 0.4,
+      "eval_val_bob_gt_loss": 0.16960681974887848,
+      "eval_val_bob_gt_runtime": 38.7527,
+      "eval_val_bob_gt_samples_per_second": 23.25,
+      "eval_val_bob_gt_steps_per_second": 2.916,
+      "step": 500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 5.798629414865578e-06,
+      "loss": 0.2991,
+      "step": 550
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 6.325777543489721e-06,
+      "loss": 0.286,
+      "step": 600
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 6.852925672113865e-06,
+      "loss": 0.2509,
+      "step": 650
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 7.380073800738008e-06,
+      "loss": 0.2708,
+      "step": 700
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.907221929362151e-06,
+      "loss": 0.2296,
+      "step": 750
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.434370057986295e-06,
+      "loss": 0.2405,
+      "step": 800
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 8.961518186610438e-06,
+      "loss": 0.2393,
+      "step": 850
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.488666315234582e-06,
+      "loss": 0.2311,
+      "step": 900
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.0015814443858725e-05,
+      "loss": 0.2079,
+      "step": 950
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0542962572482869e-05,
+      "loss": 0.1969,
+      "step": 1000
+    },
+    {
+      "epoch": 0.79,
+      "eval_val_loss": 0.1757764369249344,
+      "eval_val_runtime": 80.2328,
+      "eval_val_samples_per_second": 22.584,
+      "eval_val_steps_per_second": 2.829,
+      "step": 1000
+    },
+    {
+      "epoch": 0.79,
+      "eval_val_alice_loss": 0.11201322823762894,
+      "eval_val_alice_runtime": 39.4556,
+      "eval_val_alice_samples_per_second": 23.089,
+      "eval_val_alice_steps_per_second": 2.889,
+      "step": 1000
+    },
+    {
+      "epoch": 0.79,
+      "eval_val_bob_loss": 0.2400250881910324,
+      "eval_val_bob_runtime": 38.8802,
+      "eval_val_bob_samples_per_second": 23.174,
+      "eval_val_bob_steps_per_second": 2.906,
+      "step": 1000
+    },
+    {
+      "epoch": 0.79,
+      "eval_val_bob_gt_loss": 0.15817159414291382,
+      "eval_val_bob_gt_runtime": 38.8537,
+      "eval_val_bob_gt_samples_per_second": 23.19,
+      "eval_val_bob_gt_steps_per_second": 2.908,
+      "step": 1000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.1070110701107012e-05,
+      "loss": 0.1825,
+      "step": 1050
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1597258829731156e-05,
+      "loss": 0.1826,
+      "step": 1100
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.21244069583553e-05,
+      "loss": 0.177,
+      "step": 1150
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2651555086979441e-05,
+      "loss": 0.1951,
+      "step": 1200
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.3178703215603585e-05,
+      "loss": 0.2114,
+      "step": 1250
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 1.370585134422773e-05,
+      "loss": 0.1543,
+      "step": 1300
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.4232999472851872e-05,
+      "loss": 0.1454,
+      "step": 1350
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.4760147601476015e-05,
+      "loss": 0.1458,
+      "step": 1400
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 1.528729573010016e-05,
+      "loss": 0.1637,
+      "step": 1450
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.5814443858724302e-05,
+      "loss": 0.1329,
+      "step": 1500
+    },
+    {
+      "epoch": 1.19,
+      "eval_val_loss": 0.12391708046197891,
+      "eval_val_runtime": 80.057,
+      "eval_val_samples_per_second": 22.634,
+      "eval_val_steps_per_second": 2.835,
+      "step": 1500
+    },
+    {
+      "epoch": 1.19,
+      "eval_val_alice_loss": 0.11775108426809311,
+      "eval_val_alice_runtime": 39.3993,
+      "eval_val_alice_samples_per_second": 23.122,
+      "eval_val_alice_steps_per_second": 2.893,
+      "step": 1500
+    },
+    {
+      "epoch": 1.19,
+      "eval_val_bob_loss": 0.13003212213516235,
+      "eval_val_bob_runtime": 38.8672,
+      "eval_val_bob_samples_per_second": 23.182,
+      "eval_val_bob_steps_per_second": 2.907,
+      "step": 1500
+    },
+    {
+      "epoch": 1.19,
+      "eval_val_bob_gt_loss": 0.25759872794151306,
+      "eval_val_bob_gt_runtime": 38.8511,
+      "eval_val_bob_gt_samples_per_second": 23.191,
+      "eval_val_bob_gt_steps_per_second": 2.909,
+      "step": 1500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6341591987348446e-05,
+      "loss": 0.1552,
+      "step": 1550
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.686874011597259e-05,
+      "loss": 0.1518,
+      "step": 1600
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 1.7395888244596733e-05,
+      "loss": 0.1137,
+      "step": 1650
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 1.7923036373220876e-05,
+      "loss": 0.1424,
+      "step": 1700
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 1.845018450184502e-05,
+      "loss": 0.1131,
+      "step": 1750
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 1.8977332630469163e-05,
+      "loss": 0.0887,
+      "step": 1800
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.9504480759093307e-05,
+      "loss": 0.1046,
+      "step": 1850
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.9994420161815308e-05,
+      "loss": 0.1071,
+      "step": 1900
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.99014228587371e-05,
+      "loss": 0.092,
+      "step": 1950
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.980842555565889e-05,
+      "loss": 0.1167,
+      "step": 2000
+    },
+    {
+      "epoch": 1.58,
+      "eval_val_loss": 0.09470801800489426,
+      "eval_val_runtime": 79.8646,
+      "eval_val_samples_per_second": 22.688,
+      "eval_val_steps_per_second": 2.842,
+      "step": 2000
+    },
+    {
+      "epoch": 1.58,
+      "eval_val_alice_loss": 0.09601828455924988,
+      "eval_val_alice_runtime": 39.3347,
+      "eval_val_alice_samples_per_second": 23.16,
+      "eval_val_alice_steps_per_second": 2.898,
+      "step": 2000
+    },
+    {
+      "epoch": 1.58,
+      "eval_val_bob_loss": 0.09395376592874527,
+      "eval_val_bob_runtime": 38.7824,
+      "eval_val_bob_samples_per_second": 23.232,
+      "eval_val_bob_steps_per_second": 2.914,
+      "step": 2000
+    },
+    {
+      "epoch": 1.58,
+      "eval_val_bob_gt_loss": 0.4563288986682892,
+      "eval_val_bob_gt_runtime": 38.7783,
+      "eval_val_bob_gt_samples_per_second": 23.235,
+      "eval_val_bob_gt_steps_per_second": 2.914,
+      "step": 2000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.971542825258068e-05,
+      "loss": 0.1076,
+      "step": 2050
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 1.9622430949502466e-05,
+      "loss": 0.0904,
+      "step": 2100
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.9529433646424256e-05,
+      "loss": 0.0718,
+      "step": 2150
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 1.9436436343346043e-05,
+      "loss": 0.0889,
+      "step": 2200
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 1.9343439040267833e-05,
+      "loss": 0.0987,
+      "step": 2250
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.9250441737189623e-05,
+      "loss": 0.0782,
+      "step": 2300
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.9157444434111413e-05,
+      "loss": 0.086,
+      "step": 2350
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.90644471310332e-05,
+      "loss": 0.094,
+      "step": 2400
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.897144982795499e-05,
+      "loss": 0.0723,
+      "step": 2450
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.887845252487678e-05,
+      "loss": 0.096,
+      "step": 2500
+    },
+    {
+      "epoch": 1.98,
+      "eval_val_loss": 0.08209705352783203,
+      "eval_val_runtime": 80.0462,
+      "eval_val_samples_per_second": 22.637,
+      "eval_val_steps_per_second": 2.836,
+      "step": 2500
+    },
+    {
+      "epoch": 1.98,
+      "eval_val_alice_loss": 0.06850626319646835,
+      "eval_val_alice_runtime": 39.4169,
+      "eval_val_alice_samples_per_second": 23.112,
+      "eval_val_alice_steps_per_second": 2.892,
+      "step": 2500
+    },
+    {
+      "epoch": 1.98,
+      "eval_val_bob_loss": 0.09484687447547913,
+      "eval_val_bob_runtime": 38.8822,
+      "eval_val_bob_samples_per_second": 23.173,
+      "eval_val_bob_steps_per_second": 2.906,
+      "step": 2500
+    },
+    {
+      "epoch": 1.98,
+      "eval_val_bob_gt_loss": 0.43703609704971313,
+      "eval_val_bob_gt_runtime": 38.8648,
+      "eval_val_bob_gt_samples_per_second": 23.183,
+      "eval_val_bob_gt_steps_per_second": 2.908,
+      "step": 2500
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.878545522179857e-05,
+      "loss": 0.0841,
+      "step": 2550
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.8692457918720358e-05,
+      "loss": 0.0527,
+      "step": 2600
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.8599460615642148e-05,
+      "loss": 0.0527,
+      "step": 2650
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.8506463312563938e-05,
+      "loss": 0.055,
+      "step": 2700
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.8413466009485725e-05,
+      "loss": 0.0642,
+      "step": 2750
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.8320468706407515e-05,
+      "loss": 0.0574,
+      "step": 2800
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 1.8227471403329305e-05,
+      "loss": 0.0752,
+      "step": 2850
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.8134474100251092e-05,
+      "loss": 0.0779,
+      "step": 2900
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.8041476797172882e-05,
+      "loss": 0.0263,
+      "step": 2950
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.7948479494094673e-05,
+      "loss": 0.0461,
+      "step": 3000
+    },
+    {
+      "epoch": 2.37,
+      "eval_val_loss": 0.0750546008348465,
+      "eval_val_runtime": 80.0194,
+      "eval_val_samples_per_second": 22.645,
+      "eval_val_steps_per_second": 2.837,
+      "step": 3000
+    },
+    {
+      "epoch": 2.37,
+      "eval_val_alice_loss": 0.07222797721624374,
+      "eval_val_alice_runtime": 39.3985,
+      "eval_val_alice_samples_per_second": 23.123,
+      "eval_val_alice_steps_per_second": 2.894,
+      "step": 3000
+    },
+    {
+      "epoch": 2.37,
+      "eval_val_bob_loss": 0.07870974391698837,
+      "eval_val_bob_runtime": 38.8401,
+      "eval_val_bob_samples_per_second": 23.198,
+      "eval_val_bob_steps_per_second": 2.909,
+      "step": 3000
+    },
+    {
+      "epoch": 2.37,
+      "eval_val_bob_gt_loss": 0.6858129501342773,
+      "eval_val_bob_gt_runtime": 38.8232,
+      "eval_val_bob_gt_samples_per_second": 23.208,
+      "eval_val_bob_gt_steps_per_second": 2.911,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 12650,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.1701103468235817e+18,
+  "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 sha256:3911bc9845479a0ed1d6207b1acb43cd7bdf2cbb3856a7d9680376e940344842
+size 4792