Super-squash branch 'main' using huggingface_hub

Co-authored-by: leaderboard-pr-bot <leaderboard-pr-bot@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,228 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- bees
+- bzz
+- honey
+- oprah winfrey
+datasets:
+- BEE-spoke-data/bees-internal
+metrics:
+- accuracy
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+inference:
+  parameters:
+    max_new_tokens: 64
+    do_sample: true
+    renormalize_logits: true
+    repetition_penalty: 1.05
+    no_repeat_ngram_size: 6
+    temperature: 0.9
+    top_p: 0.95
+    epsilon_cutoff: 0.0008
+widget:
+- text: In beekeeping, the term "queen excluder" refers to
+  example_title: Queen Excluder
+- text: One way to encourage a honey bee colony to produce more honey is by
+  example_title: Increasing Honey Production
+- text: The lifecycle of a worker bee consists of several stages, starting with
+  example_title: Lifecycle of a Worker Bee
+- text: Varroa destructor is a type of mite that
+  example_title: Varroa Destructor
+- text: In the world of beekeeping, the acronym PPE stands for
+  example_title: Beekeeping PPE
+- text: The term "robbing" in beekeeping refers to the act of
+  example_title: Robbing in Beekeeping
+- text: 'Question: What''s the primary function of drone bees in a hive?
+
+    Answer:'
+  example_title: Role of Drone Bees
+- text: To harvest honey from a hive, beekeepers often use a device known as a
+  example_title: Honey Harvesting Device
+- text: 'Problem: You have a hive that produces 60 pounds of honey per year. You decide
+    to split the hive into two. Assuming each hive now produces at a 70% rate compared
+    to before, how much honey will you get from both hives next year?
+
+    To calculate'
+  example_title: Beekeeping Math Problem
+- text: In beekeeping, "swarming" is the process where
+  example_title: Swarming
+pipeline_tag: text-generation
+model-index:
+- name: TinyLlama-3T-1.1bee
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 33.79
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 60.29
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 25.86
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 38.13
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 60.22
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 0.45
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/TinyLlama-3T-1.1bee
+      name: Open LLM Leaderboard
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# TinyLlama-3T-1.1bee
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/I6AfPId0Xo_vVobtkAP12.png)
+
+A grand successor to [the original](https://huggingface.co/BEE-spoke-data/TinyLlama-1.1bee). This one has the following improvements:
+
+- start from [finished 3T TinyLlama](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T)
+- vastly improved and expanded SoTA beekeeping dataset
+
+
+## Model description
+
+This model is a fine-tuned version of TinyLlama-1.1b-3T on the BEE-spoke-data/bees-internal dataset.
+
+It achieves the following results on the evaluation set:
+- Loss: 2.1640
+- Accuracy: 0.5406
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 4
+- eval_batch_size: 2
+- seed: 13707
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 2.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 2.4432        | 0.19  | 50   | 2.3850          | 0.5033   |
+| 2.3655        | 0.39  | 100  | 2.3124          | 0.5129   |
+| 2.374         | 0.58  | 150  | 2.2588          | 0.5215   |
+| 2.3558        | 0.78  | 200  | 2.2132          | 0.5291   |
+| 2.2677        | 0.97  | 250  | 2.1828          | 0.5348   |
+| 2.0701        | 1.17  | 300  | 2.1788          | 0.5373   |
+| 2.0766        | 1.36  | 350  | 2.1673          | 0.5398   |
+| 2.0669        | 1.56  | 400  | 2.1651          | 0.5402   |
+| 2.0314        | 1.75  | 450  | 2.1641          | 0.5406   |
+| 2.0281        | 1.95  | 500  | 2.1639          | 0.5407   |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.0
+- Datasets 2.16.1
+- Tokenizers 0.15.0
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_BEE-spoke-data__TinyLlama-3T-1.1bee)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |36.46|
+|AI2 Reasoning Challenge (25-Shot)|33.79|
+|HellaSwag (10-Shot)              |60.29|
+|MMLU (5-Shot)                    |25.86|
+|TruthfulQA (0-shot)              |38.13|
+|Winogrande (5-shot)              |60.22|
+|GSM8k (5-shot)                   | 0.45|
+

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.5406350757205667,
+    "eval_loss": 2.1639890670776367,
+    "eval_runtime": 14.336,
+    "eval_samples": 300,
+    "eval_samples_per_second": 20.926,
+    "eval_steps_per_second": 10.463,
+    "perplexity": 8.705796490465838,
+    "train_loss": 2.223597173579037,
+    "train_runtime": 8040.0291,
+    "train_samples": 16416,
+    "train_samples_per_second": 4.084,
+    "train_steps_per_second": 0.064,
+    "train_tokens_per_second": 8363.146
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "pszemraj/tinyllama-1.1b-3T",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.5406350757205667,
+    "eval_loss": 2.1639890670776367,
+    "eval_runtime": 14.336,
+    "eval_samples": 300,
+    "eval_samples_per_second": 20.926,
+    "eval_steps_per_second": 10.463,
+    "perplexity": 8.705796490465838
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.36.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f3d457305c6406245fc2b6e735e15f0721cadf7d2119ac006cf6bd5ff6d7527
+size 2200119864

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": "</s>",
+    "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 sha256:7aedb3582ecda9fa99ee9242c17a9658f6744db083ee6ebdc8fb14857f84d220
+size 499723

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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "train_loss": 2.223597173579037,
+    "train_runtime": 8040.0291,
+    "train_samples": 16416,
+    "train_samples_per_second": 4.084,
+    "train_steps_per_second": 0.064,
+    "train_tokens_per_second": 8363.146
+}

trainer_state.json

@@ -0,0 +1,733 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.996101364522417,
+  "eval_steps": 50,
+  "global_step": 512,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.923076923076923e-05,
+      "loss": 2.7497,
+      "step": 5
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 2.7052,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 5.769230769230769e-05,
+      "loss": 2.6213,
+      "step": 15
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 7.692307692307693e-05,
+      "loss": 2.6018,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.615384615384617e-05,
+      "loss": 2.5872,
+      "step": 25
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.998328666948438e-05,
+      "loss": 2.5665,
+      "step": 30
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.991540791356342e-05,
+      "loss": 2.5494,
+      "step": 35
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.979538999730047e-05,
+      "loss": 2.5143,
+      "step": 40
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.962335828546048e-05,
+      "loss": 2.441,
+      "step": 45
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.939949247384046e-05,
+      "loss": 2.4432,
+      "step": 50
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.5032714541605602,
+      "eval_loss": 2.3850491046905518,
+      "eval_runtime": 14.1442,
+      "eval_samples_per_second": 21.21,
+      "eval_steps_per_second": 10.605,
+      "step": 50
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.912402640156811e-05,
+      "loss": 2.4841,
+      "step": 55
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.879724780684519e-05,
+      "loss": 2.4121,
+      "step": 60
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.84194980263903e-05,
+      "loss": 2.4448,
+      "step": 65
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.799117163889559e-05,
+      "loss": 2.4297,
+      "step": 70
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 9.751271605286941e-05,
+      "loss": 2.4581,
+      "step": 75
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 9.698463103929542e-05,
+      "loss": 2.435,
+      "step": 80
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 9.640746820959684e-05,
+      "loss": 2.3842,
+      "step": 85
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.57818304394503e-05,
+      "loss": 2.3872,
+      "step": 90
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.51083712390519e-05,
+      "loss": 2.426,
+      "step": 95
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.438779407049281e-05,
+      "loss": 2.3655,
+      "step": 100
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.5129278619117408,
+      "eval_loss": 2.3123531341552734,
+      "eval_runtime": 14.1415,
+      "eval_samples_per_second": 21.214,
+      "eval_steps_per_second": 10.607,
+      "step": 100
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.362085161295769e-05,
+      "loss": 2.402,
+      "step": 105
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.280834497651334e-05,
+      "loss": 2.3523,
+      "step": 110
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 9.195112286530873e-05,
+      "loss": 2.3354,
+      "step": 115
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.105008069106093e-05,
+      "loss": 2.37,
+      "step": 120
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 9.01061596377522e-05,
+      "loss": 2.3597,
+      "step": 125
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 8.912034567851599e-05,
+      "loss": 2.3646,
+      "step": 130
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.809366854573831e-05,
+      "loss": 2.3601,
+      "step": 135
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.702720065545024e-05,
+      "loss": 2.3424,
+      "step": 140
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.592205598713539e-05,
+      "loss": 2.3362,
+      "step": 145
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.47793889201221e-05,
+      "loss": 2.374,
+      "step": 150
+    },
+    {
+      "epoch": 0.58,
+      "eval_accuracy": 0.5214769581501384,
+      "eval_loss": 2.258837938308716,
+      "eval_runtime": 14.3574,
+      "eval_samples_per_second": 20.895,
+      "eval_steps_per_second": 10.448,
+      "step": 150
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 8.360039302777612e-05,
+      "loss": 2.3383,
+      "step": 155
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 8.238629983075294e-05,
+      "loss": 2.319,
+      "step": 160
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.113837751061246e-05,
+      "loss": 2.3517,
+      "step": 165
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 7.985792958513931e-05,
+      "loss": 2.307,
+      "step": 170
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.854629354675291e-05,
+      "loss": 2.2915,
+      "step": 175
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 7.720483946542914e-05,
+      "loss": 2.3198,
+      "step": 180
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.583496855759316e-05,
+      "loss": 2.3304,
+      "step": 185
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.443811172247821e-05,
+      "loss": 2.2926,
+      "step": 190
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 7.30157280474793e-05,
+      "loss": 2.2753,
+      "step": 195
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 7.156930328406268e-05,
+      "loss": 2.3558,
+      "step": 200
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.5291418335775933,
+      "eval_loss": 2.2132091522216797,
+      "eval_runtime": 14.0805,
+      "eval_samples_per_second": 21.306,
+      "eval_steps_per_second": 10.653,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 7.01003482958237e-05,
+      "loss": 2.3026,
+      "step": 205
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 6.861039748031351e-05,
+      "loss": 2.3327,
+      "step": 210
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.3047,
+      "step": 215
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.557375398802123e-05,
+      "loss": 2.2849,
+      "step": 220
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.403023323847695e-05,
+      "loss": 2.2972,
+      "step": 225
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.247205720289907e-05,
+      "loss": 2.3069,
+      "step": 230
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 6.09008534747213e-05,
+      "loss": 2.3305,
+      "step": 235
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5.9318263255459116e-05,
+      "loss": 2.2845,
+      "step": 240
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 5.772593964039203e-05,
+      "loss": 2.2698,
+      "step": 245
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.6125545891822274e-05,
+      "loss": 2.2677,
+      "step": 250
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.5348330890734408,
+      "eval_loss": 2.182823896408081,
+      "eval_runtime": 14.0998,
+      "eval_samples_per_second": 21.277,
+      "eval_steps_per_second": 10.638,
+      "step": 250
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.451875370171341e-05,
+      "loss": 2.2776,
+      "step": 255
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 5.290724144552379e-05,
+      "loss": 2.1158,
+      "step": 260
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 5.129269242905882e-05,
+      "loss": 2.0758,
+      "step": 265
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 4.967679313017303e-05,
+      "loss": 2.053,
+      "step": 270
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 4.806123143715916e-05,
+      "loss": 2.0824,
+      "step": 275
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 4.6447694885663514e-05,
+      "loss": 2.062,
+      "step": 280
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.4837868895969936e-05,
+      "loss": 2.0986,
+      "step": 285
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 4.323343501249346e-05,
+      "loss": 2.0749,
+      "step": 290
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 4.1636069147322246e-05,
+      "loss": 2.0365,
+      "step": 295
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.004743982964298e-05,
+      "loss": 2.0701,
+      "step": 300
+    },
+    {
+      "epoch": 1.17,
+      "eval_accuracy": 0.5372854583943983,
+      "eval_loss": 2.178772211074829,
+      "eval_runtime": 14.087,
+      "eval_samples_per_second": 21.296,
+      "eval_steps_per_second": 10.648,
+      "step": 300
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.846920646287799e-05,
+      "loss": 2.0554,
+      "step": 305
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.6903017591354706e-05,
+      "loss": 2.0432,
+      "step": 310
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 3.535050917831797e-05,
+      "loss": 2.0663,
+      "step": 315
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.381330289708396e-05,
+      "loss": 2.0673,
+      "step": 320
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 3.2293004437120624e-05,
+      "loss": 2.0106,
+      "step": 325
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.079120182682412e-05,
+      "loss": 2.0177,
+      "step": 330
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.9309463774743046e-05,
+      "loss": 2.0314,
+      "step": 335
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.7849338030983257e-05,
+      "loss": 2.06,
+      "step": 340
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.641234977050484e-05,
+      "loss": 2.0765,
+      "step": 345
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.0766,
+      "step": 350
+    },
+    {
+      "epoch": 1.36,
+      "eval_accuracy": 0.5397508549096238,
+      "eval_loss": 2.1673190593719482,
+      "eval_runtime": 14.2515,
+      "eval_samples_per_second": 21.05,
+      "eval_steps_per_second": 10.525,
+      "step": 350
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 2.361376399001592e-05,
+      "loss": 2.0481,
+      "step": 355
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.225508973396016e-05,
+      "loss": 2.0246,
+      "step": 360
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.0925396435598664e-05,
+      "loss": 2.0563,
+      "step": 365
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.9626073026625818e-05,
+      "loss": 2.0373,
+      "step": 370
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 1.835847671585526e-05,
+      "loss": 2.0495,
+      "step": 375
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 1.7123931571546827e-05,
+      "loss": 2.0612,
+      "step": 380
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 1.592372713835055e-05,
+      "loss": 2.0543,
+      "step": 385
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 1.4759117090312197e-05,
+      "loss": 2.0719,
+      "step": 390
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 1.3631317921347563e-05,
+      "loss": 2.0468,
+      "step": 395
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 1.25415076745532e-05,
+      "loss": 2.0669,
+      "step": 400
+    },
+    {
+      "epoch": 1.56,
+      "eval_accuracy": 0.5402182055039896,
+      "eval_loss": 2.165104866027832,
+      "eval_runtime": 14.1201,
+      "eval_samples_per_second": 21.246,
+      "eval_steps_per_second": 10.623,
+      "step": 400
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 1.1490824711681025e-05,
+      "loss": 2.0491,
+      "step": 405
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.0480366524062042e-05,
+      "loss": 2.0686,
+      "step": 410
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.511188586221376e-06,
+      "loss": 2.0816,
+      "step": 415
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 8.584303253381847e-06,
+      "loss": 2.0808,
+      "step": 420
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 7.700678704007947e-06,
+      "loss": 2.0244,
+      "step": 425
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 6.861237928494579e-06,
+      "loss": 2.0715,
+      "step": 430
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.066857765057055e-06,
+      "loss": 2.0629,
+      "step": 435
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 5.318367983829392e-06,
+      "loss": 2.0738,
+      "step": 440
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.616550420127563e-06,
+      "loss": 2.0449,
+      "step": 445
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 3.962138157783085e-06,
+      "loss": 2.0314,
+      "step": 450
+    },
+    {
+      "epoch": 1.75,
+      "eval_accuracy": 0.5405943657384791,
+      "eval_loss": 2.1640877723693848,
+      "eval_runtime": 14.1591,
+      "eval_samples_per_second": 21.188,
+      "eval_steps_per_second": 10.594,
+      "step": 450
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 3.3558147633999728e-06,
+      "loss": 2.0818,
+      "step": 455
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.798213572335001e-06,
+      "loss": 2.0991,
+      "step": 460
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2.2899170271469428e-06,
+      "loss": 2.0317,
+      "step": 465
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.8314560692059835e-06,
+      "loss": 2.0518,
+      "step": 470
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.4233095840986753e-06,
+      "loss": 2.013,
+      "step": 475
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.0659039014077944e-06,
+      "loss": 2.0317,
+      "step": 480
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.038,
+      "step": 485
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 5.047548650136513e-07,
+      "loss": 2.0414,
+      "step": 490
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 3.0159765977250673e-07,
+      "loss": 2.0509,
+      "step": 495
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.503529416103988e-07,
+      "loss": 2.0281,
+      "step": 500
+    },
+    {
+      "epoch": 1.95,
+      "eval_accuracy": 0.5406627585083863,
+      "eval_loss": 2.163918972015381,
+      "eval_runtime": 14.1546,
+      "eval_samples_per_second": 21.194,
+      "eval_steps_per_second": 10.597,
+      "step": 500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 5.11786932613223e-08,
+      "loss": 2.0471,
+      "step": 505
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 4.178507228136397e-09,
+      "loss": 2.055,
+      "step": 510
+    },
+    {
+      "epoch": 2.0,
+      "step": 512,
+      "total_flos": 4.1654970530503066e+17,
+      "train_loss": 2.223597173579037,
+      "train_runtime": 8040.0291,
+      "train_samples_per_second": 4.084,
+      "train_steps_per_second": 0.064,
+      "train_tokens_per_second": 8363.146
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 512,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "total_flos": 4.1654970530503066e+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 sha256:10a490548d555fb913ec0cfae7548bdcecd3e54899c358e05458a6be28ff2352
+size 4856