Super-squash branch 'main' using huggingface_hub

Co-authored-by: amazingvince <amazingvince@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 +1,66 @@
+---
+license: apache-2.0
+base_model: BEE-spoke-data/smol_llama-220M-openhermes
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-220m-sft-full
+  results: []
+datasets:
+- HuggingFaceH4/ultrachat_200k
+---
+
+<!-- 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. -->
+
+# zephyr-220m-sft-full
+
+This model is a fine-tuned version of [BEE-spoke-data/smol_llama-220M-openhermes](https://huggingface.co/BEE-spoke-data/smol_llama-220M-openhermes) on the Ultrachat_200k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6579
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.6447        | 1.0   | 1624 | 1.6579          |
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0
+
+https://wandb.ai/amazingvince/huggingface/runs/5rffzk3x/workspace?workspace=user-amazingvince

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|assistant|>": 32001,
+  "<|system|>": 32002,
+  "<|user|>": 32000
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.6579183340072632,
+    "eval_runtime": 192.8742,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 119.819,
+    "eval_steps_per_second": 3.749,
+    "train_loss": 1.737739272305531,
+    "train_runtime": 6874.8829,
+    "train_samples": 207865,
+    "train_samples_per_second": 30.235,
+    "train_steps_per_second": 0.236
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "BEE-spoke-data/smol_llama-220M-openhermes",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 2048,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 10,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32128
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.6579183340072632,
+    "eval_runtime": 192.8742,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 119.819,
+    "eval_steps_per_second": 3.749
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c096b823052ca5f6019f43d2b7ad42ad56099f82340c5d7603db6bd0ef09c345
+size 435736840

runs/Jan04_10-57-14_VincentPC/events.out.tfevents.1704383930.VincentPC.16500.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d489f624cd023081181a15228ef3f5d13911eee8165d5ab3f7c9c067a43266a2
+size 4510

runs/Jan04_10-59-27_VincentPC/events.out.tfevents.1704383987.VincentPC.18585.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f80683af1b15bfaa97bd452ae7ae51fdfa28ef827ce37396e09bd2e0570180bc
+size 56082

runs/Jan04_10-59-27_VincentPC/events.out.tfevents.1704391055.VincentPC.18585.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fe1d4b475dd77000130d87496121cc3a841435b37e01036b627091ed59017db
+size 359

special_tokens_map.json

@@ -0,0 +1,47 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,74 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|user|>",
+    "<|assistant|>",
+    "<|system|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.737739272305531,
+    "train_runtime": 6874.8829,
+    "train_samples": 207865,
+    "train_samples_per_second": 30.235,
+    "train_steps_per_second": 0.236
+}

trainer_state.json

@@ -0,0 +1,1988 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9999981288975627e-05,
+      "loss": 2.7383,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9999532227891695e-05,
+      "loss": 2.4961,
+      "step": 5
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9998128955328933e-05,
+      "loss": 2.3199,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9995790313594056e-05,
+      "loss": 2.257,
+      "step": 15
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.999251652147735e-05,
+      "loss": 2.1969,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.998830788525654e-05,
+      "loss": 2.1591,
+      "step": 25
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9983164798668152e-05,
+      "loss": 2.1406,
+      "step": 30
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.9977087742870683e-05,
+      "loss": 2.1177,
+      "step": 35
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.997007728639956e-05,
+      "loss": 2.0871,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9962134085114e-05,
+      "loss": 2.0855,
+      "step": 45
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9953258882135594e-05,
+      "loss": 2.1094,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.9943452507778832e-05,
+      "loss": 2.0664,
+      "step": 55
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9932715879473385e-05,
+      "loss": 2.0543,
+      "step": 60
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9921050001678316e-05,
+      "loss": 2.0443,
+      "step": 65
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.990845596578807e-05,
+      "loss": 2.0297,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.989493495003039e-05,
+      "loss": 1.9811,
+      "step": 75
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9880488219356086e-05,
+      "loss": 1.9493,
+      "step": 80
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9865117125320693e-05,
+      "loss": 1.9918,
+      "step": 85
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9848823105958023e-05,
+      "loss": 1.9872,
+      "step": 90
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9831607685645636e-05,
+      "loss": 1.9735,
+      "step": 95
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.981347247496222e-05,
+      "loss": 1.9586,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9794419170536918e-05,
+      "loss": 1.9715,
+      "step": 105
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.9774449554890615e-05,
+      "loss": 1.9288,
+      "step": 110
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.975356549626915e-05,
+      "loss": 1.9482,
+      "step": 115
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.973176894846855e-05,
+      "loss": 1.9518,
+      "step": 120
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.9709061950652237e-05,
+      "loss": 1.9736,
+      "step": 125
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.968544662716026e-05,
+      "loss": 1.9507,
+      "step": 130
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 1.966092518731055e-05,
+      "loss": 1.8726,
+      "step": 135
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.963549992519223e-05,
+      "loss": 1.8853,
+      "step": 140
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9609173219450998e-05,
+      "loss": 1.9182,
+      "step": 145
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9581947533066577e-05,
+      "loss": 1.9311,
+      "step": 150
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9553825413122313e-05,
+      "loss": 1.9183,
+      "step": 155
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9524809490566878e-05,
+      "loss": 1.9088,
+      "step": 160
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.949490247996812e-05,
+      "loss": 1.9063,
+      "step": 165
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9464107179259126e-05,
+      "loss": 1.9035,
+      "step": 170
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9432426469476432e-05,
+      "loss": 1.8725,
+      "step": 175
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.939986331449053e-05,
+      "loss": 1.8753,
+      "step": 180
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9366420760728546e-05,
+      "loss": 1.8905,
+      "step": 185
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9332101936889262e-05,
+      "loss": 1.8586,
+      "step": 190
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9296910053650388e-05,
+      "loss": 1.8485,
+      "step": 195
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.926084840336821e-05,
+      "loss": 1.8745,
+      "step": 200
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.922392035976957e-05,
+      "loss": 1.8652,
+      "step": 205
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.918612937763622e-05,
+      "loss": 1.8583,
+      "step": 210
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 1.9147478992481642e-05,
+      "loss": 1.8399,
+      "step": 215
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.910797282022027e-05,
+      "loss": 1.8574,
+      "step": 220
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9067614556829195e-05,
+      "loss": 1.879,
+      "step": 225
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9026407978002415e-05,
+      "loss": 1.8242,
+      "step": 230
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.8984356938797573e-05,
+      "loss": 1.8655,
+      "step": 235
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.894146537327533e-05,
+      "loss": 1.8377,
+      "step": 240
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8897737294131288e-05,
+      "loss": 1.8284,
+      "step": 245
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8853176792320598e-05,
+      "loss": 1.8311,
+      "step": 250
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8807788036675243e-05,
+      "loss": 1.8281,
+      "step": 255
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8761575273514005e-05,
+      "loss": 1.8315,
+      "step": 260
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8714542826245214e-05,
+      "loss": 1.7864,
+      "step": 265
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.866669509496227e-05,
+      "loss": 1.8318,
+      "step": 270
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.861803655603201e-05,
+      "loss": 1.7969,
+      "step": 275
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8568571761675893e-05,
+      "loss": 1.8212,
+      "step": 280
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8518305339544157e-05,
+      "loss": 1.8123,
+      "step": 285
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8467241992282842e-05,
+      "loss": 1.7934,
+      "step": 290
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.841538649709388e-05,
+      "loss": 1.7995,
+      "step": 295
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8362743705288127e-05,
+      "loss": 1.8107,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.830931854183153e-05,
+      "loss": 1.7984,
+      "step": 305
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.825511600488435e-05,
+      "loss": 1.8106,
+      "step": 310
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.8200141165333592e-05,
+      "loss": 1.7949,
+      "step": 315
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.814439916631857e-05,
+      "loss": 1.812,
+      "step": 320
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8087895222749773e-05,
+      "loss": 1.8188,
+      "step": 325
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.803063462082095e-05,
+      "loss": 1.813,
+      "step": 330
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.7972622717514608e-05,
+      "loss": 1.7995,
+      "step": 335
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.791386494010081e-05,
+      "loss": 1.7753,
+      "step": 340
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.7854366785629435e-05,
+      "loss": 1.7839,
+      "step": 345
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7794133820415916e-05,
+      "loss": 1.7682,
+      "step": 350
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7733171679520485e-05,
+      "loss": 1.8059,
+      "step": 355
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7671486066220965e-05,
+      "loss": 1.7501,
+      "step": 360
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.7609082751479246e-05,
+      "loss": 1.8109,
+      "step": 365
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7545967573401336e-05,
+      "loss": 1.7731,
+      "step": 370
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7482146436691227e-05,
+      "loss": 1.7785,
+      "step": 375
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.7417625312098453e-05,
+      "loss": 1.7725,
+      "step": 380
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.7352410235859503e-05,
+      "loss": 1.7871,
+      "step": 385
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.728650730913312e-05,
+      "loss": 1.7813,
+      "step": 390
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.721992269742951e-05,
+      "loss": 1.7974,
+      "step": 395
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7152662630033506e-05,
+      "loss": 1.7728,
+      "step": 400
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7084733399421808e-05,
+      "loss": 1.7433,
+      "step": 405
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7016141360674307e-05,
+      "loss": 1.7666,
+      "step": 410
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6946892930879516e-05,
+      "loss": 1.7702,
+      "step": 415
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6876994588534234e-05,
+      "loss": 1.751,
+      "step": 420
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.680645287293746e-05,
+      "loss": 1.7605,
+      "step": 425
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.6735274383578593e-05,
+      "loss": 1.7526,
+      "step": 430
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6663465779520042e-05,
+      "loss": 1.7307,
+      "step": 435
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.659103377877423e-05,
+      "loss": 1.7677,
+      "step": 440
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6517985157675097e-05,
+      "loss": 1.7596,
+      "step": 445
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.6444326750244145e-05,
+      "loss": 1.7166,
+      "step": 450
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.637006544755108e-05,
+      "loss": 1.7815,
+      "step": 455
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.629520819706912e-05,
+      "loss": 1.7601,
+      "step": 460
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6219762002025055e-05,
+      "loss": 1.7615,
+      "step": 465
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.614373392074402e-05,
+      "loss": 1.7749,
+      "step": 470
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 1.6067131065989188e-05,
+      "loss": 1.7434,
+      "step": 475
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.598996060429634e-05,
+      "loss": 1.7306,
+      "step": 480
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.591222975530338e-05,
+      "loss": 1.7351,
+      "step": 485
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5833945791074943e-05,
+      "loss": 1.7239,
+      "step": 490
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5755116035422015e-05,
+      "loss": 1.7589,
+      "step": 495
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.56757478632168e-05,
+      "loss": 1.7227,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5595848699702752e-05,
+      "loss": 1.7233,
+      "step": 505
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5515426019799898e-05,
+      "loss": 1.7503,
+      "step": 510
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5434487347405553e-05,
+      "loss": 1.7409,
+      "step": 515
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5353040254690396e-05,
+      "loss": 1.7619,
+      "step": 520
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5271092361390078e-05,
+      "loss": 1.7512,
+      "step": 525
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5188651334092373e-05,
+      "loss": 1.7376,
+      "step": 530
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5105724885519908e-05,
+      "loss": 1.7316,
+      "step": 535
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5022320773808612e-05,
+      "loss": 1.7358,
+      "step": 540
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4938446801781932e-05,
+      "loss": 1.7175,
+      "step": 545
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4854110816220805e-05,
+      "loss": 1.693,
+      "step": 550
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4769320707129588e-05,
+      "loss": 1.7571,
+      "step": 555
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4684084406997903e-05,
+      "loss": 1.6738,
+      "step": 560
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.459840989005851e-05,
+      "loss": 1.7263,
+      "step": 565
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4512305171541287e-05,
+      "loss": 1.7324,
+      "step": 570
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.4425778306923388e-05,
+      "loss": 1.6998,
+      "step": 575
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4338837391175582e-05,
+      "loss": 1.7016,
+      "step": 580
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4251490558004965e-05,
+      "loss": 1.7399,
+      "step": 585
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4163745979093997e-05,
+      "loss": 1.709,
+      "step": 590
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4075611863336012e-05,
+      "loss": 1.7097,
+      "step": 595
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.3987096456067236e-05,
+      "loss": 1.7057,
+      "step": 600
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.3898208038295407e-05,
+      "loss": 1.7015,
+      "step": 605
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3808954925925042e-05,
+      "loss": 1.7264,
+      "step": 610
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3719345468979448e-05,
+      "loss": 1.7223,
+      "step": 615
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3629388050819547e-05,
+      "loss": 1.7125,
+      "step": 620
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.353909108735957e-05,
+      "loss": 1.7057,
+      "step": 625
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3448463026279706e-05,
+      "loss": 1.6828,
+      "step": 630
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.33575123462358e-05,
+      "loss": 1.7265,
+      "step": 635
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3266247556066122e-05,
+      "loss": 1.7114,
+      "step": 640
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.317467719399534e-05,
+      "loss": 1.6962,
+      "step": 645
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.3082809826835707e-05,
+      "loss": 1.7133,
+      "step": 650
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 1.2990654049185636e-05,
+      "loss": 1.7091,
+      "step": 655
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2898218482625606e-05,
+      "loss": 1.6789,
+      "step": 660
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2805511774911585e-05,
+      "loss": 1.7187,
+      "step": 665
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2712542599165998e-05,
+      "loss": 1.6827,
+      "step": 670
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.261931965306632e-05,
+      "loss": 1.7348,
+      "step": 675
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.252585165803135e-05,
+      "loss": 1.6851,
+      "step": 680
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2432147358405313e-05,
+      "loss": 1.7282,
+      "step": 685
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.233821552063977e-05,
+      "loss": 1.7057,
+      "step": 690
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2244064932473467e-05,
+      "loss": 1.6941,
+      "step": 695
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2149704402110243e-05,
+      "loss": 1.7276,
+      "step": 700
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.2055142757394936e-05,
+      "loss": 1.6835,
+      "step": 705
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1960388844987529e-05,
+      "loss": 1.7125,
+      "step": 710
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1865451529535496e-05,
+      "loss": 1.7159,
+      "step": 715
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1770339692844484e-05,
+      "loss": 1.7277,
+      "step": 720
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1675062233047365e-05,
+      "loss": 1.7185,
+      "step": 725
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.157962806377179e-05,
+      "loss": 1.695,
+      "step": 730
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 1.1484046113306262e-05,
+      "loss": 1.6746,
+      "step": 735
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1388325323764889e-05,
+      "loss": 1.6676,
+      "step": 740
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1292474650250776e-05,
+      "loss": 1.719,
+      "step": 745
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1196503060018243e-05,
+      "loss": 1.7027,
+      "step": 750
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1100419531633917e-05,
+      "loss": 1.7071,
+      "step": 755
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1004233054136726e-05,
+      "loss": 1.7111,
+      "step": 760
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.090795262619694e-05,
+      "loss": 1.6992,
+      "step": 765
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.0811587255274313e-05,
+      "loss": 1.6798,
+      "step": 770
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0715145956775395e-05,
+      "loss": 1.6773,
+      "step": 775
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0618637753210086e-05,
+      "loss": 1.6725,
+      "step": 780
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0522071673347558e-05,
+      "loss": 1.6964,
+      "step": 785
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0425456751371564e-05,
+      "loss": 1.69,
+      "step": 790
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0328802026035254e-05,
+      "loss": 1.7064,
+      "step": 795
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0232116539815558e-05,
+      "loss": 1.6781,
+      "step": 800
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.013540933806722e-05,
+      "loss": 1.6886,
+      "step": 805
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.0038689468176575e-05,
+      "loss": 1.6965,
+      "step": 810
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.941965978715105e-06,
+      "loss": 1.6827,
+      "step": 815
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.845247918592937e-06,
+      "loss": 1.6701,
+      "step": 820
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.748544336212246e-06,
+      "loss": 1.6855,
+      "step": 825
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.651864278620752e-06,
+      "loss": 1.7222,
+      "step": 830
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.555216790665334e-06,
+      "loss": 1.6852,
+      "step": 835
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.458610914145826e-06,
+      "loss": 1.6909,
+      "step": 840
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.362055686969141e-06,
+      "loss": 1.6741,
+      "step": 845
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.26556014230371e-06,
+      "loss": 1.6589,
+      "step": 850
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.169133307734415e-06,
+      "loss": 1.6874,
+      "step": 855
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.072784204417995e-06,
+      "loss": 1.7062,
+      "step": 860
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 8.976521846239076e-06,
+      "loss": 1.6747,
+      "step": 865
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.880355238966923e-06,
+      "loss": 1.6951,
+      "step": 870
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.784293379412851e-06,
+      "loss": 1.6919,
+      "step": 875
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.688345254588579e-06,
+      "loss": 1.6852,
+      "step": 880
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.592519840865432e-06,
+      "loss": 1.67,
+      "step": 885
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.496826103134572e-06,
+      "loss": 1.6754,
+      "step": 890
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.401272993968288e-06,
+      "loss": 1.7049,
+      "step": 895
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.305869452782446e-06,
+      "loss": 1.6438,
+      "step": 900
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.210624405000169e-06,
+      "loss": 1.6763,
+      "step": 905
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.115546761216822e-06,
+      "loss": 1.6959,
+      "step": 910
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.020645416366367e-06,
+      "loss": 1.6773,
+      "step": 915
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.92592924888925e-06,
+      "loss": 1.6438,
+      "step": 920
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.831407119901737e-06,
+      "loss": 1.6768,
+      "step": 925
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.73708787236694e-06,
+      "loss": 1.6818,
+      "step": 930
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.642980330267516e-06,
+      "loss": 1.6896,
+      "step": 935
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.549093297780133e-06,
+      "loss": 1.6689,
+      "step": 940
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.455435558451824e-06,
+      "loss": 1.6703,
+      "step": 945
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.362015874378219e-06,
+      "loss": 1.6764,
+      "step": 950
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.268842985383841e-06,
+      "loss": 1.6803,
+      "step": 955
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.175925608204428e-06,
+      "loss": 1.6987,
+      "step": 960
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.0832724356714715e-06,
+      "loss": 1.6871,
+      "step": 965
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.990892135898937e-06,
+      "loss": 1.6649,
+      "step": 970
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.898793351472341e-06,
+      "loss": 1.6634,
+      "step": 975
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.806984698640202e-06,
+      "loss": 1.6781,
+      "step": 980
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.715474766507932e-06,
+      "loss": 1.6664,
+      "step": 985
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.624272116234319e-06,
+      "loss": 1.6742,
+      "step": 990
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.5333852802305556e-06,
+      "loss": 1.6522,
+      "step": 995
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.442822761362015e-06,
+      "loss": 1.6804,
+      "step": 1000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.352593032152787e-06,
+      "loss": 1.6621,
+      "step": 1005
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.262704533992995e-06,
+      "loss": 1.6974,
+      "step": 1010
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 1.6718,
+      "step": 1015
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.083984835977154e-06,
+      "loss": 1.6715,
+      "step": 1020
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.995170356139088e-06,
+      "loss": 1.6818,
+      "step": 1025
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.9067305458222054e-06,
+      "loss": 1.6836,
+      "step": 1030
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.8186736789618105e-06,
+      "loss": 1.6396,
+      "step": 1035
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.731007993667155e-06,
+      "loss": 1.6463,
+      "step": 1040
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.643741691450733e-06,
+      "loss": 1.6292,
+      "step": 1045
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.556882936460966e-06,
+      "loss": 1.6474,
+      "step": 1050
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.4704398547184535e-06,
+      "loss": 1.6677,
+      "step": 1055
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.38442053335571e-06,
+      "loss": 1.635,
+      "step": 1060
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.298833019860599e-06,
+      "loss": 1.644,
+      "step": 1065
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.213685321323451e-06,
+      "loss": 1.6371,
+      "step": 1070
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.128985403687949e-06,
+      "loss": 1.6414,
+      "step": 1075
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.044741191005908e-06,
+      "loss": 1.6706,
+      "step": 1080
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.960960564695922e-06,
+      "loss": 1.6551,
+      "step": 1085
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.877651362806038e-06,
+      "loss": 1.6686,
+      "step": 1090
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.7948213792804475e-06,
+      "loss": 1.6816,
+      "step": 1095
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.712478363230361e-06,
+      "loss": 1.6884,
+      "step": 1100
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.630630018209027e-06,
+      "loss": 1.6359,
+      "step": 1105
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.5492840014910145e-06,
+      "loss": 1.6626,
+      "step": 1110
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.468447923355888e-06,
+      "loss": 1.6579,
+      "step": 1115
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.388129346376177e-06,
+      "loss": 1.6557,
+      "step": 1120
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.308335784709902e-06,
+      "loss": 1.6414,
+      "step": 1125
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.22907470339758e-06,
+      "loss": 1.6701,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.1503535176638264e-06,
+      "loss": 1.6913,
+      "step": 1135
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.07217959222365e-06,
+      "loss": 1.6954,
+      "step": 1140
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.994560240593433e-06,
+      "loss": 1.6782,
+      "step": 1145
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.9175027244067295e-06,
+      "loss": 1.6702,
+      "step": 1150
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.841014252734896e-06,
+      "loss": 1.6912,
+      "step": 1155
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.7651019814126656e-06,
+      "loss": 1.6442,
+      "step": 1160
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.6897730123686793e-06,
+      "loss": 1.6664,
+      "step": 1165
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.615034392961071e-06,
+      "loss": 1.6679,
+      "step": 1170
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.5408931153181582e-06,
+      "loss": 1.6618,
+      "step": 1175
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.467356115684284e-06,
+      "loss": 1.6502,
+      "step": 1180
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.3944302737709246e-06,
+      "loss": 1.6806,
+      "step": 1185
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.322122412113047e-06,
+      "loss": 1.6893,
+      "step": 1190
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2504392954308193e-06,
+      "loss": 1.6609,
+      "step": 1195
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.179387629996782e-06,
+      "loss": 1.6552,
+      "step": 1200
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.108974063008389e-06,
+      "loss": 1.6719,
+      "step": 1205
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.0392051819661826e-06,
+      "loss": 1.6403,
+      "step": 1210
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.9700875140574813e-06,
+      "loss": 1.6491,
+      "step": 1215
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.901627525545726e-06,
+      "loss": 1.6285,
+      "step": 1220
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 2.8338316211655536e-06,
+      "loss": 1.6361,
+      "step": 1225
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.7667061435235876e-06,
+      "loss": 1.6595,
+      "step": 1230
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.700257372505072e-06,
+      "loss": 1.6631,
+      "step": 1235
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.634491524686341e-06,
+      "loss": 1.633,
+      "step": 1240
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5694147527532576e-06,
+      "loss": 1.6576,
+      "step": 1245
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.5050331449255873e-06,
+      "loss": 1.6664,
+      "step": 1250
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.4413527243874046e-06,
+      "loss": 1.6589,
+      "step": 1255
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3783794487236367e-06,
+      "loss": 1.6538,
+      "step": 1260
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.3161192093626604e-06,
+      "loss": 1.6764,
+      "step": 1265
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.2545778310251642e-06,
+      "loss": 1.6557,
+      "step": 1270
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.193761071179209e-06,
+      "loss": 1.6783,
+      "step": 1275
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1336746195015845e-06,
+      "loss": 1.6648,
+      "step": 1280
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.0743240973455304e-06,
+      "loss": 1.7035,
+      "step": 1285
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.015715057214823e-06,
+      "loss": 1.6505,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.957852982244309e-06,
+      "loss": 1.6531,
+      "step": 1295
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.90074328568696e-06,
+      "loss": 1.6485,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.8443913104073984e-06,
+      "loss": 1.6721,
+      "step": 1305
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7888023283820865e-06,
+      "loss": 1.6563,
+      "step": 1310
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7339815402060857e-06,
+      "loss": 1.6337,
+      "step": 1315
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.679934074606533e-06,
+      "loss": 1.6538,
+      "step": 1320
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6266649879628083e-06,
+      "loss": 1.646,
+      "step": 1325
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5741792638335096e-06,
+      "loss": 1.6483,
+      "step": 1330
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.522481812490203e-06,
+      "loss": 1.6505,
+      "step": 1335
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4715774704580454e-06,
+      "loss": 1.6378,
+      "step": 1340
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4214710000633247e-06,
+      "loss": 1.6807,
+      "step": 1345
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.3721670889878914e-06,
+      "loss": 1.7011,
+      "step": 1350
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.323670349830637e-06,
+      "loss": 1.661,
+      "step": 1355
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2759853196759454e-06,
+      "loss": 1.6486,
+      "step": 1360
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.2291164596692307e-06,
+      "loss": 1.6603,
+      "step": 1365
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.1830681545995882e-06,
+      "loss": 1.6754,
+      "step": 1370
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1378447124895687e-06,
+      "loss": 1.6419,
+      "step": 1375
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.09345036419214e-06,
+      "loss": 1.6287,
+      "step": 1380
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.049889262994883e-06,
+      "loss": 1.6336,
+      "step": 1385
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0071654842314293e-06,
+      "loss": 1.6212,
+      "step": 1390
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.65283024900191e-07,
+      "loss": 1.6574,
+      "step": 1395
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.242458032904311e-07,
+      "loss": 1.6675,
+      "step": 1400
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.840576586156791e-07,
+      "loss": 1.6678,
+      "step": 1405
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.447223506545698e-07,
+      "loss": 1.6787,
+      "step": 1410
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.062435593990914e-07,
+      "loss": 1.6479,
+      "step": 1415
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 7.686248847103073e-07,
+      "loss": 1.6352,
+      "step": 1420
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.318698459815654e-07,
+      "loss": 1.6515,
+      "step": 1425
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.959818818092645e-07,
+      "loss": 1.6376,
+      "step": 1430
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.609643496711349e-07,
+      "loss": 1.6493,
+      "step": 1435
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.268205256121396e-07,
+      "loss": 1.663,
+      "step": 1440
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.935536039379985e-07,
+      "loss": 1.6476,
+      "step": 1445
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 1.6569,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.296628344854749e-07,
+      "loss": 1.6645,
+      "step": 1455
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.990449639710815e-07,
+      "loss": 1.6637,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.6931594981030834e-07,
+      "loss": 1.6507,
+      "step": 1465
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.4047857328388457e-07,
+      "loss": 1.6578,
+      "step": 1470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.1253553225589215e-07,
+      "loss": 1.6527,
+      "step": 1475
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.854894409213761e-07,
+      "loss": 1.6931,
+      "step": 1480
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.593428295617685e-07,
+      "loss": 1.6372,
+      "step": 1485
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3409814430817144e-07,
+      "loss": 1.6479,
+      "step": 1490
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.097577469125168e-07,
+      "loss": 1.6481,
+      "step": 1495
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 2.863239145266028e-07,
+      "loss": 1.6769,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.6379883948907004e-07,
+      "loss": 1.6727,
+      "step": 1505
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.421846291202812e-07,
+      "loss": 1.6694,
+      "step": 1510
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.214833055251908e-07,
+      "loss": 1.6783,
+      "step": 1515
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.016968054041546e-07,
+      "loss": 1.6544,
+      "step": 1520
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.8282697987174635e-07,
+      "loss": 1.6698,
+      "step": 1525
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.6487559428358336e-07,
+      "loss": 1.6618,
+      "step": 1530
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.4784432807116057e-07,
+      "loss": 1.6705,
+      "step": 1535
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.317347745847386e-07,
+      "loss": 1.6484,
+      "step": 1540
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.1654844094427852e-07,
+      "loss": 1.6385,
+      "step": 1545
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.0228674789843906e-07,
+      "loss": 1.6564,
+      "step": 1550
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 8.895102969166625e-08,
+      "loss": 1.6573,
+      "step": 1555
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.65425339393644e-08,
+      "loss": 1.6665,
+      "step": 1560
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.506242151117726e-08,
+      "loss": 1.6638,
+      "step": 1565
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.451176642238376e-08,
+      "loss": 1.6598,
+      "step": 1570
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.4891555733418416e-08,
+      "loss": 1.6375,
+      "step": 1575
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.620268945752847e-08,
+      "loss": 1.6422,
+      "step": 1580
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.8445980476574653e-08,
+      "loss": 1.676,
+      "step": 1585
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.1622154464977508e-08,
+      "loss": 1.6581,
+      "step": 1590
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.5731849821833955e-08,
+      "loss": 1.6723,
+      "step": 1595
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.0775617611189504e-08,
+      "loss": 1.6401,
+      "step": 1600
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.753921510480599e-09,
+      "loss": 1.6414,
+      "step": 1605
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.6671377671604337e-09,
+      "loss": 1.6246,
+      "step": 1610
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.5155551634971067e-09,
+      "loss": 1.6625,
+      "step": 1615
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.9937498955745493e-10,
+      "loss": 1.6447,
+      "step": 1620
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6579183340072632,
+      "eval_runtime": 278.604,
+      "eval_samples_per_second": 82.949,
+      "eval_steps_per_second": 2.595,
+      "step": 1624
+    },
+    {
+      "epoch": 1.0,
+      "step": 1624,
+      "total_flos": 54684588736512.0,
+      "train_loss": 1.737739272305531,
+      "train_runtime": 6874.8829,
+      "train_samples_per_second": 30.235,
+      "train_steps_per_second": 0.236
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1624,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "total_flos": 54684588736512.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf55b33ea3dbe65307c6991ec327ff1c1570150dd5981dabe13c9beb7df18c89
+size 5752