commit 138b42829cdac413dc48c961481b9c262234e161
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Jul 11 10:45:09 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: vandijklab/C2S-Pythia-410m-cell-type-prediction
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..6980e7a
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,54 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+ 
+ 
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+ 
+ 
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+
+optimizer.pt filter=lfs diff=lfs merge=lfs -text
+scheduler.pt filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
+rng_state.pth filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text
\ No newline at end of file
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..fde2fa9
--- /dev/null
+++ b/README.md
@@ -0,0 +1,36 @@
+---
+language:
+- en
+base_model: EleutherAI/pythia-410m
+library_name: transformers
+tags:
+- biology
+- scRNAseq
+license: cc-by-4.0
+---
+# Overview
+This is the C2S-Pythia-410m-cell-type-prediction model, based on the Pythia-410m architecture developed by EleutherAI, 
+fine-tuned using Cell2Sentence (C2S) on a diverse set of single-cell RNA sequencing (scRNA-seq) datasets from CellxGene 
+and the Human Cell Atlas. Cell2Sentence is an innovative approach for adapting large language models (LLMs) to 
+single-cell biology by transforming scRNA-seq data into "cell sentences"—sequences of gene names ordered by 
+expression levels. This transformation enables LLMs to leverage their natural language processing capabilities for 
+various single-cell tasks, with a focus on cell type prediction in this model.
+
+# Training Data
+This model was trained on over 57 million human and mouse cells gathered from over 800 single-cell RNA sequencing 
+datasets from CellxGene and the Human Cell Atlas. This dataset covers a broad range of cell types and conditions
+from multiple tissues in both human and mouse.
+
+This model was trained with the top 200 genes per cell sentence.
+
+# Tasks
+This model is designed for:
+- Cell type prediction: Predicting the cell type based on the "cell sentence" generated from scRNA-seq data.
+
+# Cell2Sentence Links
+- GitHub: https://github.com/vandijklab/cell2sentence (Note: Codebase has Apache 2.0 license, weights shared on HuggingFace are CC-by-4.0)
+- Paper: https://www.biorxiv.org/content/10.1101/2023.09.11.557287v3
+
+# Pythia Links
+- Paper: https://arxiv.org/pdf/2304.01373
+- Hugging Face: https://huggingface.co/EleutherAI/pythia-410m
\ No newline at end of file
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..7cf1b5f
--- /dev/null
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/sr2464/scratch/C2S_Files/C2S_training_runs/multicell_v2_pretraining_runs/finetuning-EleutherAI/pythia-410m-multicell_v2_pretraining-2024-07-28_13-55-51/checkpoint-7200",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 4096,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "use_cache": false,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}
diff --git a/configuration.json b/configuration.json
new file mode 100644
index 0000000..bbeeda1
--- /dev/null
+++ b/configuration.json
@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
\ No newline at end of file
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..ea61db8
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.41.0",
+  "use_cache": false
+}
diff --git a/model.safetensors b/model.safetensors
new file mode 100644
index 0000000..6b8ac83
--- /dev/null
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25a0bfc2d97293ff39184488ea89c7b5ad07fe67745c388b5b9cd4f6a7c494ce
+size 1621370224
diff --git a/optimizer.pt b/optimizer.pt
new file mode 100644
index 0000000..5b48232
--- /dev/null
+++ b/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efc8249e4df93ed7ce99cf0986ad5b3e20280ca47b873640e85cba198a4c579d
+size 3242843770
diff --git a/rng_state.pth b/rng_state.pth
new file mode 100644
index 0000000..564890d
--- /dev/null
+++ b/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0477ab216c87ec817c24cdfbeefe105cf1affbe1688d2bda68b3ba77f8f2d771
+size 14244
diff --git a/scheduler.pt b/scheduler.pt
new file mode 100644
index 0000000..2dc1444
--- /dev/null
+++ b/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bc91de8b9f047f525dab31bc781984519a1b5efbdc072fc5a246caf05d38e32
+size 1064
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..330140f
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..614d056
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:870f4e2baa6b683221fa52004d5d6f40ab8c9d31961617304b78c910c2c3caf2
+size 2114042
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..67bcd0e
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,214 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}
diff --git a/trainer_state.json b/trainer_state.json
new file mode 100644
index 0000000..df68cd2
--- /dev/null
+++ b/trainer_state.json
@@ -0,0 +1,1173 @@
+{
+  "best_metric": 1.7627220153808594,
+  "best_model_checkpoint": "/home/sr2464/scratch/C2S_Files/C2S_training_runs/multicell_v2_pretraining_runs/finetuning-EleutherAI/pythia-410m-multicell_v2_pretraining-2024-07-28_13-55-51/checkpoint-7600",
+  "epoch": 0.02637866105155987,
+  "eval_steps": 100,
+  "global_step": 7600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00034708764541526143,
+      "grad_norm": 11.82771110534668,
+      "learning_rate": 3.470776065528252e-07,
+      "loss": 4.0944,
+      "step": 100
+    },
+    {
+      "epoch": 0.00034708764541526143,
+      "eval_loss": 3.7496891021728516,
+      "eval_runtime": 24.9132,
+      "eval_samples_per_second": 17.621,
+      "eval_steps_per_second": 0.401,
+      "step": 100
+    },
+    {
+      "epoch": 0.0006941752908305229,
+      "grad_norm": 6.635104656219482,
+      "learning_rate": 6.941552131056504e-07,
+      "loss": 3.4557,
+      "step": 200
+    },
+    {
+      "epoch": 0.0006941752908305229,
+      "eval_loss": 3.1241986751556396,
+      "eval_runtime": 24.3825,
+      "eval_samples_per_second": 18.005,
+      "eval_steps_per_second": 0.41,
+      "step": 200
+    },
+    {
+      "epoch": 0.0010412629362457843,
+      "grad_norm": 5.158722400665283,
+      "learning_rate": 1.0412328196584756e-06,
+      "loss": 2.9713,
+      "step": 300
+    },
+    {
+      "epoch": 0.0010412629362457843,
+      "eval_loss": 2.807060956954956,
+      "eval_runtime": 24.5493,
+      "eval_samples_per_second": 17.882,
+      "eval_steps_per_second": 0.407,
+      "step": 300
+    },
+    {
+      "epoch": 0.0013883505816610457,
+      "grad_norm": 4.5594987869262695,
+      "learning_rate": 1.3883104262113009e-06,
+      "loss": 2.7438,
+      "step": 400
+    },
+    {
+      "epoch": 0.0013883505816610457,
+      "eval_loss": 2.6474108695983887,
+      "eval_runtime": 24.8652,
+      "eval_samples_per_second": 17.655,
+      "eval_steps_per_second": 0.402,
+      "step": 400
+    },
+    {
+      "epoch": 0.0017354382270763071,
+      "grad_norm": 4.926589488983154,
+      "learning_rate": 1.7353880327641261e-06,
+      "loss": 2.6108,
+      "step": 500
+    },
+    {
+      "epoch": 0.0017354382270763071,
+      "eval_loss": 2.5452585220336914,
+      "eval_runtime": 24.5027,
+      "eval_samples_per_second": 17.916,
+      "eval_steps_per_second": 0.408,
+      "step": 500
+    },
+    {
+      "epoch": 0.0020825258724915686,
+      "grad_norm": 4.601032733917236,
+      "learning_rate": 2.082465639316951e-06,
+      "loss": 2.5207,
+      "step": 600
+    },
+    {
+      "epoch": 0.0020825258724915686,
+      "eval_loss": 2.4688005447387695,
+      "eval_runtime": 24.9309,
+      "eval_samples_per_second": 17.609,
+      "eval_steps_per_second": 0.401,
+      "step": 600
+    },
+    {
+      "epoch": 0.00242961351790683,
+      "grad_norm": 7.157230377197266,
+      "learning_rate": 2.429543245869777e-06,
+      "loss": 2.4464,
+      "step": 700
+    },
+    {
+      "epoch": 0.00242961351790683,
+      "eval_loss": 2.404836416244507,
+      "eval_runtime": 24.5241,
+      "eval_samples_per_second": 17.901,
+      "eval_steps_per_second": 0.408,
+      "step": 700
+    },
+    {
+      "epoch": 0.0027767011633220914,
+      "grad_norm": 5.524389266967773,
+      "learning_rate": 2.7766208524226017e-06,
+      "loss": 2.3814,
+      "step": 800
+    },
+    {
+      "epoch": 0.0027767011633220914,
+      "eval_loss": 2.342756748199463,
+      "eval_runtime": 24.889,
+      "eval_samples_per_second": 17.638,
+      "eval_steps_per_second": 0.402,
+      "step": 800
+    },
+    {
+      "epoch": 0.003123788808737353,
+      "grad_norm": 9.947836875915527,
+      "learning_rate": 3.123698458975427e-06,
+      "loss": 2.3277,
+      "step": 900
+    },
+    {
+      "epoch": 0.003123788808737353,
+      "eval_loss": 2.2919700145721436,
+      "eval_runtime": 24.3758,
+      "eval_samples_per_second": 18.01,
+      "eval_steps_per_second": 0.41,
+      "step": 900
+    },
+    {
+      "epoch": 0.0034708764541526143,
+      "grad_norm": 3.7194149494171143,
+      "learning_rate": 3.4707760655282523e-06,
+      "loss": 2.2745,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0034708764541526143,
+      "eval_loss": 2.2262797355651855,
+      "eval_runtime": 24.8001,
+      "eval_samples_per_second": 17.702,
+      "eval_steps_per_second": 0.403,
+      "step": 1000
+    },
+    {
+      "epoch": 0.0038179640995678757,
+      "grad_norm": 3.318101167678833,
+      "learning_rate": 3.817853672081077e-06,
+      "loss": 2.1989,
+      "step": 1100
+    },
+    {
+      "epoch": 0.0038179640995678757,
+      "eval_loss": 2.1580822467803955,
+      "eval_runtime": 24.9395,
+      "eval_samples_per_second": 17.603,
+      "eval_steps_per_second": 0.401,
+      "step": 1100
+    },
+    {
+      "epoch": 0.004165051744983137,
+      "grad_norm": 3.5991110801696777,
+      "learning_rate": 4.164931278633902e-06,
+      "loss": 2.1452,
+      "step": 1200
+    },
+    {
+      "epoch": 0.004165051744983137,
+      "eval_loss": 2.103646755218506,
+      "eval_runtime": 24.7561,
+      "eval_samples_per_second": 17.733,
+      "eval_steps_per_second": 0.404,
+      "step": 1200
+    },
+    {
+      "epoch": 0.004512139390398399,
+      "grad_norm": 4.609652519226074,
+      "learning_rate": 4.5120088851867285e-06,
+      "loss": 2.0965,
+      "step": 1300
+    },
+    {
+      "epoch": 0.004512139390398399,
+      "eval_loss": 2.0649664402008057,
+      "eval_runtime": 24.3571,
+      "eval_samples_per_second": 18.023,
+      "eval_steps_per_second": 0.411,
+      "step": 1300
+    },
+    {
+      "epoch": 0.00485922703581366,
+      "grad_norm": 2.850724697113037,
+      "learning_rate": 4.859086491739554e-06,
+      "loss": 2.0605,
+      "step": 1400
+    },
+    {
+      "epoch": 0.00485922703581366,
+      "eval_loss": 2.035384178161621,
+      "eval_runtime": 24.7396,
+      "eval_samples_per_second": 17.745,
+      "eval_steps_per_second": 0.404,
+      "step": 1400
+    },
+    {
+      "epoch": 0.0052063146812289214,
+      "grad_norm": 2.408285140991211,
+      "learning_rate": 5.206164098292378e-06,
+      "loss": 2.0304,
+      "step": 1500
+    },
+    {
+      "epoch": 0.0052063146812289214,
+      "eval_loss": 2.007747173309326,
+      "eval_runtime": 24.3422,
+      "eval_samples_per_second": 18.035,
+      "eval_steps_per_second": 0.411,
+      "step": 1500
+    },
+    {
+      "epoch": 0.005553402326644183,
+      "grad_norm": 2.4324307441711426,
+      "learning_rate": 5.5532417048452035e-06,
+      "loss": 2.0107,
+      "step": 1600
+    },
+    {
+      "epoch": 0.005553402326644183,
+      "eval_loss": 1.9913328886032104,
+      "eval_runtime": 24.7711,
+      "eval_samples_per_second": 17.722,
+      "eval_steps_per_second": 0.404,
+      "step": 1600
+    },
+    {
+      "epoch": 0.005900489972059444,
+      "grad_norm": 2.5259335041046143,
+      "learning_rate": 5.900319311398029e-06,
+      "loss": 1.9932,
+      "step": 1700
+    },
+    {
+      "epoch": 0.005900489972059444,
+      "eval_loss": 1.9759337902069092,
+      "eval_runtime": 24.3525,
+      "eval_samples_per_second": 18.027,
+      "eval_steps_per_second": 0.411,
+      "step": 1700
+    },
+    {
+      "epoch": 0.006247577617474706,
+      "grad_norm": 2.625298500061035,
+      "learning_rate": 6.247396917950854e-06,
+      "loss": 1.9784,
+      "step": 1800
+    },
+    {
+      "epoch": 0.006247577617474706,
+      "eval_loss": 1.9598480463027954,
+      "eval_runtime": 24.7491,
+      "eval_samples_per_second": 17.738,
+      "eval_steps_per_second": 0.404,
+      "step": 1800
+    },
+    {
+      "epoch": 0.006594665262889967,
+      "grad_norm": 3.4950461387634277,
+      "learning_rate": 6.59447452450368e-06,
+      "loss": 1.962,
+      "step": 1900
+    },
+    {
+      "epoch": 0.006594665262889967,
+      "eval_loss": 1.9490702152252197,
+      "eval_runtime": 24.3735,
+      "eval_samples_per_second": 18.011,
+      "eval_steps_per_second": 0.41,
+      "step": 1900
+    },
+    {
+      "epoch": 0.006941752908305229,
+      "grad_norm": 2.0300960540771484,
+      "learning_rate": 6.9415521310565046e-06,
+      "loss": 1.9562,
+      "step": 2000
+    },
+    {
+      "epoch": 0.006941752908305229,
+      "eval_loss": 1.9372752904891968,
+      "eval_runtime": 24.82,
+      "eval_samples_per_second": 17.687,
+      "eval_steps_per_second": 0.403,
+      "step": 2000
+    },
+    {
+      "epoch": 0.00728884055372049,
+      "grad_norm": 2.2911906242370605,
+      "learning_rate": 7.28862973760933e-06,
+      "loss": 1.9433,
+      "step": 2100
+    },
+    {
+      "epoch": 0.00728884055372049,
+      "eval_loss": 1.9285736083984375,
+      "eval_runtime": 24.3516,
+      "eval_samples_per_second": 18.028,
+      "eval_steps_per_second": 0.411,
+      "step": 2100
+    },
+    {
+      "epoch": 0.0076359281991357515,
+      "grad_norm": 2.4398937225341797,
+      "learning_rate": 7.635707344162154e-06,
+      "loss": 1.9336,
+      "step": 2200
+    },
+    {
+      "epoch": 0.0076359281991357515,
+      "eval_loss": 1.917083978652954,
+      "eval_runtime": 24.7637,
+      "eval_samples_per_second": 17.728,
+      "eval_steps_per_second": 0.404,
+      "step": 2200
+    },
+    {
+      "epoch": 0.007983015844551014,
+      "grad_norm": 2.05511474609375,
+      "learning_rate": 7.982784950714981e-06,
+      "loss": 1.9206,
+      "step": 2300
+    },
+    {
+      "epoch": 0.007983015844551014,
+      "eval_loss": 1.9095990657806396,
+      "eval_runtime": 24.3373,
+      "eval_samples_per_second": 18.038,
+      "eval_steps_per_second": 0.411,
+      "step": 2300
+    },
+    {
+      "epoch": 0.008330103489966274,
+      "grad_norm": 2.751636266708374,
+      "learning_rate": 8.329862557267805e-06,
+      "loss": 1.9171,
+      "step": 2400
+    },
+    {
+      "epoch": 0.008330103489966274,
+      "eval_loss": 1.9016169309616089,
+      "eval_runtime": 24.8006,
+      "eval_samples_per_second": 17.701,
+      "eval_steps_per_second": 0.403,
+      "step": 2400
+    },
+    {
+      "epoch": 0.008677191135381537,
+      "grad_norm": 2.362074375152588,
+      "learning_rate": 8.67694016382063e-06,
+      "loss": 1.9019,
+      "step": 2500
+    },
+    {
+      "epoch": 0.008677191135381537,
+      "eval_loss": 1.8958009481430054,
+      "eval_runtime": 24.3568,
+      "eval_samples_per_second": 18.024,
+      "eval_steps_per_second": 0.411,
+      "step": 2500
+    },
+    {
+      "epoch": 0.009024278780796797,
+      "grad_norm": 2.2177438735961914,
+      "learning_rate": 9.024017770373457e-06,
+      "loss": 1.9017,
+      "step": 2600
+    },
+    {
+      "epoch": 0.009024278780796797,
+      "eval_loss": 1.887508749961853,
+      "eval_runtime": 24.7322,
+      "eval_samples_per_second": 17.75,
+      "eval_steps_per_second": 0.404,
+      "step": 2600
+    },
+    {
+      "epoch": 0.00937136642621206,
+      "grad_norm": 1.9819880723953247,
+      "learning_rate": 9.37109537692628e-06,
+      "loss": 1.8884,
+      "step": 2700
+    },
+    {
+      "epoch": 0.00937136642621206,
+      "eval_loss": 1.883723258972168,
+      "eval_runtime": 24.3493,
+      "eval_samples_per_second": 18.029,
+      "eval_steps_per_second": 0.411,
+      "step": 2700
+    },
+    {
+      "epoch": 0.00971845407162732,
+      "grad_norm": 1.854220986366272,
+      "learning_rate": 9.718172983479108e-06,
+      "loss": 1.8849,
+      "step": 2800
+    },
+    {
+      "epoch": 0.00971845407162732,
+      "eval_loss": 1.8750510215759277,
+      "eval_runtime": 24.761,
+      "eval_samples_per_second": 17.729,
+      "eval_steps_per_second": 0.404,
+      "step": 2800
+    },
+    {
+      "epoch": 0.010065541717042582,
+      "grad_norm": 1.6808480024337769,
+      "learning_rate": 1.0065250590031931e-05,
+      "loss": 1.8835,
+      "step": 2900
+    },
+    {
+      "epoch": 0.010065541717042582,
+      "eval_loss": 1.8682337999343872,
+      "eval_runtime": 24.3525,
+      "eval_samples_per_second": 18.027,
+      "eval_steps_per_second": 0.411,
+      "step": 2900
+    },
+    {
+      "epoch": 0.010412629362457843,
+      "grad_norm": 2.1851375102996826,
+      "learning_rate": 1.0412328196584756e-05,
+      "loss": 1.8679,
+      "step": 3000
+    },
+    {
+      "epoch": 0.010412629362457843,
+      "eval_loss": 1.8666459321975708,
+      "eval_runtime": 24.7696,
+      "eval_samples_per_second": 17.723,
+      "eval_steps_per_second": 0.404,
+      "step": 3000
+    },
+    {
+      "epoch": 0.010759717007873105,
+      "grad_norm": 2.1571567058563232,
+      "learning_rate": 1.0759405803137582e-05,
+      "loss": 1.8684,
+      "step": 3100
+    },
+    {
+      "epoch": 0.010759717007873105,
+      "eval_loss": 1.8589407205581665,
+      "eval_runtime": 24.3459,
+      "eval_samples_per_second": 18.032,
+      "eval_steps_per_second": 0.411,
+      "step": 3100
+    },
+    {
+      "epoch": 0.011106804653288366,
+      "grad_norm": 1.878134846687317,
+      "learning_rate": 1.1106483409690407e-05,
+      "loss": 1.8671,
+      "step": 3200
+    },
+    {
+      "epoch": 0.011106804653288366,
+      "eval_loss": 1.8569821119308472,
+      "eval_runtime": 24.8145,
+      "eval_samples_per_second": 17.691,
+      "eval_steps_per_second": 0.403,
+      "step": 3200
+    },
+    {
+      "epoch": 0.011453892298703628,
+      "grad_norm": 1.3475431203842163,
+      "learning_rate": 1.1453561016243232e-05,
+      "loss": 1.8574,
+      "step": 3300
+    },
+    {
+      "epoch": 0.011453892298703628,
+      "eval_loss": 1.8536343574523926,
+      "eval_runtime": 24.3402,
+      "eval_samples_per_second": 18.036,
+      "eval_steps_per_second": 0.411,
+      "step": 3300
+    },
+    {
+      "epoch": 0.011800979944118889,
+      "grad_norm": 1.7545586824417114,
+      "learning_rate": 1.1800638622796058e-05,
+      "loss": 1.8544,
+      "step": 3400
+    },
+    {
+      "epoch": 0.011800979944118889,
+      "eval_loss": 1.848755955696106,
+      "eval_runtime": 24.8444,
+      "eval_samples_per_second": 17.67,
+      "eval_steps_per_second": 0.403,
+      "step": 3400
+    },
+    {
+      "epoch": 0.012148067589534151,
+      "grad_norm": 1.378000020980835,
+      "learning_rate": 1.2147716229348883e-05,
+      "loss": 1.8531,
+      "step": 3500
+    },
+    {
+      "epoch": 0.012148067589534151,
+      "eval_loss": 1.8428057432174683,
+      "eval_runtime": 24.3454,
+      "eval_samples_per_second": 18.032,
+      "eval_steps_per_second": 0.411,
+      "step": 3500
+    },
+    {
+      "epoch": 0.012495155234949411,
+      "grad_norm": 1.6506402492523193,
+      "learning_rate": 1.2494793835901708e-05,
+      "loss": 1.8481,
+      "step": 3600
+    },
+    {
+      "epoch": 0.012495155234949411,
+      "eval_loss": 1.8448010683059692,
+      "eval_runtime": 24.8196,
+      "eval_samples_per_second": 17.688,
+      "eval_steps_per_second": 0.403,
+      "step": 3600
+    },
+    {
+      "epoch": 0.012842242880364674,
+      "grad_norm": 1.8429005146026611,
+      "learning_rate": 1.2841871442454533e-05,
+      "loss": 1.8502,
+      "step": 3700
+    },
+    {
+      "epoch": 0.012842242880364674,
+      "eval_loss": 1.8411270380020142,
+      "eval_runtime": 24.3415,
+      "eval_samples_per_second": 18.035,
+      "eval_steps_per_second": 0.411,
+      "step": 3700
+    },
+    {
+      "epoch": 0.013189330525779934,
+      "grad_norm": 1.3569915294647217,
+      "learning_rate": 1.318894904900736e-05,
+      "loss": 1.8439,
+      "step": 3800
+    },
+    {
+      "epoch": 0.013189330525779934,
+      "eval_loss": 1.8359909057617188,
+      "eval_runtime": 24.808,
+      "eval_samples_per_second": 17.696,
+      "eval_steps_per_second": 0.403,
+      "step": 3800
+    },
+    {
+      "epoch": 0.013536418171195197,
+      "grad_norm": 1.4549897909164429,
+      "learning_rate": 1.3536026655560182e-05,
+      "loss": 1.8377,
+      "step": 3900
+    },
+    {
+      "epoch": 0.013536418171195197,
+      "eval_loss": 1.8364492654800415,
+      "eval_runtime": 24.3193,
+      "eval_samples_per_second": 18.051,
+      "eval_steps_per_second": 0.411,
+      "step": 3900
+    },
+    {
+      "epoch": 0.013883505816610457,
+      "grad_norm": 1.493501901626587,
+      "learning_rate": 1.3883104262113009e-05,
+      "loss": 1.8449,
+      "step": 4000
+    },
+    {
+      "epoch": 0.013883505816610457,
+      "eval_loss": 1.8301156759262085,
+      "eval_runtime": 24.8527,
+      "eval_samples_per_second": 17.664,
+      "eval_steps_per_second": 0.402,
+      "step": 4000
+    },
+    {
+      "epoch": 0.01423059346202572,
+      "grad_norm": 1.4112632274627686,
+      "learning_rate": 1.4230181868665834e-05,
+      "loss": 1.8362,
+      "step": 4100
+    },
+    {
+      "epoch": 0.01423059346202572,
+      "eval_loss": 1.827904462814331,
+      "eval_runtime": 24.3918,
+      "eval_samples_per_second": 17.998,
+      "eval_steps_per_second": 0.41,
+      "step": 4100
+    },
+    {
+      "epoch": 0.01457768110744098,
+      "grad_norm": 1.425305962562561,
+      "learning_rate": 1.457725947521866e-05,
+      "loss": 1.834,
+      "step": 4200
+    },
+    {
+      "epoch": 0.01457768110744098,
+      "eval_loss": 1.8238531351089478,
+      "eval_runtime": 25.0327,
+      "eval_samples_per_second": 17.537,
+      "eval_steps_per_second": 0.399,
+      "step": 4200
+    },
+    {
+      "epoch": 0.014924768752856242,
+      "grad_norm": 1.3402836322784424,
+      "learning_rate": 1.4924337081771487e-05,
+      "loss": 1.8272,
+      "step": 4300
+    },
+    {
+      "epoch": 0.014924768752856242,
+      "eval_loss": 1.8218436241149902,
+      "eval_runtime": 24.3405,
+      "eval_samples_per_second": 18.036,
+      "eval_steps_per_second": 0.411,
+      "step": 4300
+    },
+    {
+      "epoch": 0.015271856398271503,
+      "grad_norm": 1.3900611400604248,
+      "learning_rate": 1.527141468832431e-05,
+      "loss": 1.8267,
+      "step": 4400
+    },
+    {
+      "epoch": 0.015271856398271503,
+      "eval_loss": 1.8179056644439697,
+      "eval_runtime": 24.8888,
+      "eval_samples_per_second": 17.638,
+      "eval_steps_per_second": 0.402,
+      "step": 4400
+    },
+    {
+      "epoch": 0.015618944043686765,
+      "grad_norm": 1.8727518320083618,
+      "learning_rate": 1.5618492294877134e-05,
+      "loss": 1.8164,
+      "step": 4500
+    },
+    {
+      "epoch": 0.015618944043686765,
+      "eval_loss": 1.8159282207489014,
+      "eval_runtime": 24.4165,
+      "eval_samples_per_second": 17.98,
+      "eval_steps_per_second": 0.41,
+      "step": 4500
+    },
+    {
+      "epoch": 0.015966031689102027,
+      "grad_norm": 1.3085731267929077,
+      "learning_rate": 1.5965569901429962e-05,
+      "loss": 1.8236,
+      "step": 4600
+    },
+    {
+      "epoch": 0.015966031689102027,
+      "eval_loss": 1.8137013912200928,
+      "eval_runtime": 24.8538,
+      "eval_samples_per_second": 17.663,
+      "eval_steps_per_second": 0.402,
+      "step": 4600
+    },
+    {
+      "epoch": 0.016313119334517286,
+      "grad_norm": 1.1558576822280884,
+      "learning_rate": 1.6312647507982788e-05,
+      "loss": 1.8186,
+      "step": 4700
+    },
+    {
+      "epoch": 0.016313119334517286,
+      "eval_loss": 1.8110047578811646,
+      "eval_runtime": 24.775,
+      "eval_samples_per_second": 17.719,
+      "eval_steps_per_second": 0.404,
+      "step": 4700
+    },
+    {
+      "epoch": 0.01666020697993255,
+      "grad_norm": 1.2725753784179688,
+      "learning_rate": 1.665972511453561e-05,
+      "loss": 1.8142,
+      "step": 4800
+    },
+    {
+      "epoch": 0.01666020697993255,
+      "eval_loss": 1.8090318441390991,
+      "eval_runtime": 24.7529,
+      "eval_samples_per_second": 17.735,
+      "eval_steps_per_second": 0.404,
+      "step": 4800
+    },
+    {
+      "epoch": 0.01700729462534781,
+      "grad_norm": 1.2328158617019653,
+      "learning_rate": 1.7006802721088435e-05,
+      "loss": 1.814,
+      "step": 4900
+    },
+    {
+      "epoch": 0.01700729462534781,
+      "eval_loss": 1.8059718608856201,
+      "eval_runtime": 24.4992,
+      "eval_samples_per_second": 17.919,
+      "eval_steps_per_second": 0.408,
+      "step": 4900
+    },
+    {
+      "epoch": 0.017354382270763073,
+      "grad_norm": 1.2142012119293213,
+      "learning_rate": 1.735388032764126e-05,
+      "loss": 1.8106,
+      "step": 5000
+    },
+    {
+      "epoch": 0.017354382270763073,
+      "eval_loss": 1.8046983480453491,
+      "eval_runtime": 24.8108,
+      "eval_samples_per_second": 17.694,
+      "eval_steps_per_second": 0.403,
+      "step": 5000
+    },
+    {
+      "epoch": 0.017701469916178332,
+      "grad_norm": 1.129823923110962,
+      "learning_rate": 1.770095793419409e-05,
+      "loss": 1.8103,
+      "step": 5100
+    },
+    {
+      "epoch": 0.017701469916178332,
+      "eval_loss": 1.8018277883529663,
+      "eval_runtime": 24.402,
+      "eval_samples_per_second": 17.99,
+      "eval_steps_per_second": 0.41,
+      "step": 5100
+    },
+    {
+      "epoch": 0.018048557561593594,
+      "grad_norm": 1.4417102336883545,
+      "learning_rate": 1.8048035540746914e-05,
+      "loss": 1.809,
+      "step": 5200
+    },
+    {
+      "epoch": 0.018048557561593594,
+      "eval_loss": 1.7983735799789429,
+      "eval_runtime": 24.8186,
+      "eval_samples_per_second": 17.688,
+      "eval_steps_per_second": 0.403,
+      "step": 5200
+    },
+    {
+      "epoch": 0.018395645207008857,
+      "grad_norm": 1.1981695890426636,
+      "learning_rate": 1.8395113147299736e-05,
+      "loss": 1.8025,
+      "step": 5300
+    },
+    {
+      "epoch": 0.018395645207008857,
+      "eval_loss": 1.7986949682235718,
+      "eval_runtime": 24.3774,
+      "eval_samples_per_second": 18.009,
+      "eval_steps_per_second": 0.41,
+      "step": 5300
+    },
+    {
+      "epoch": 0.01874273285242412,
+      "grad_norm": 1.0044975280761719,
+      "learning_rate": 1.874219075385256e-05,
+      "loss": 1.8037,
+      "step": 5400
+    },
+    {
+      "epoch": 0.01874273285242412,
+      "eval_loss": 1.795265793800354,
+      "eval_runtime": 24.8161,
+      "eval_samples_per_second": 17.69,
+      "eval_steps_per_second": 0.403,
+      "step": 5400
+    },
+    {
+      "epoch": 0.019089820497839378,
+      "grad_norm": 1.0582355260849,
+      "learning_rate": 1.9089268360405386e-05,
+      "loss": 1.8043,
+      "step": 5500
+    },
+    {
+      "epoch": 0.019089820497839378,
+      "eval_loss": 1.7948534488677979,
+      "eval_runtime": 24.3738,
+      "eval_samples_per_second": 18.011,
+      "eval_steps_per_second": 0.41,
+      "step": 5500
+    },
+    {
+      "epoch": 0.01943690814325464,
+      "grad_norm": 0.9827861189842224,
+      "learning_rate": 1.9436345966958215e-05,
+      "loss": 1.7944,
+      "step": 5600
+    },
+    {
+      "epoch": 0.01943690814325464,
+      "eval_loss": 1.7950631380081177,
+      "eval_runtime": 24.8182,
+      "eval_samples_per_second": 17.689,
+      "eval_steps_per_second": 0.403,
+      "step": 5600
+    },
+    {
+      "epoch": 0.019783995788669902,
+      "grad_norm": 0.9715519547462463,
+      "learning_rate": 1.9783423573511037e-05,
+      "loss": 1.8002,
+      "step": 5700
+    },
+    {
+      "epoch": 0.019783995788669902,
+      "eval_loss": 1.7902957201004028,
+      "eval_runtime": 24.6536,
+      "eval_samples_per_second": 17.807,
+      "eval_steps_per_second": 0.406,
+      "step": 5700
+    },
+    {
+      "epoch": 0.020131083434085165,
+      "grad_norm": 1.1996351480484009,
+      "learning_rate": 2.0130501180063862e-05,
+      "loss": 1.7982,
+      "step": 5800
+    },
+    {
+      "epoch": 0.020131083434085165,
+      "eval_loss": 1.7865217924118042,
+      "eval_runtime": 24.7792,
+      "eval_samples_per_second": 17.716,
+      "eval_steps_per_second": 0.404,
+      "step": 5800
+    },
+    {
+      "epoch": 0.020478171079500423,
+      "grad_norm": 0.9313274621963501,
+      "learning_rate": 2.0477578786616688e-05,
+      "loss": 1.7917,
+      "step": 5900
+    },
+    {
+      "epoch": 0.020478171079500423,
+      "eval_loss": 1.7852766513824463,
+      "eval_runtime": 24.3762,
+      "eval_samples_per_second": 18.009,
+      "eval_steps_per_second": 0.41,
+      "step": 5900
+    },
+    {
+      "epoch": 0.020825258724915686,
+      "grad_norm": 1.2815057039260864,
+      "learning_rate": 2.0824656393169513e-05,
+      "loss": 1.7926,
+      "step": 6000
+    },
+    {
+      "epoch": 0.020825258724915686,
+      "eval_loss": 1.7834093570709229,
+      "eval_runtime": 24.8731,
+      "eval_samples_per_second": 17.65,
+      "eval_steps_per_second": 0.402,
+      "step": 6000
+    },
+    {
+      "epoch": 0.021172346370330948,
+      "grad_norm": 1.3323718309402466,
+      "learning_rate": 2.117173399972234e-05,
+      "loss": 1.7909,
+      "step": 6100
+    },
+    {
+      "epoch": 0.021172346370330948,
+      "eval_loss": 1.7828959226608276,
+      "eval_runtime": 24.4144,
+      "eval_samples_per_second": 17.981,
+      "eval_steps_per_second": 0.41,
+      "step": 6100
+    },
+    {
+      "epoch": 0.02151943401574621,
+      "grad_norm": 1.2279607057571411,
+      "learning_rate": 2.1518811606275163e-05,
+      "loss": 1.7903,
+      "step": 6200
+    },
+    {
+      "epoch": 0.02151943401574621,
+      "eval_loss": 1.7831159830093384,
+      "eval_runtime": 24.8211,
+      "eval_samples_per_second": 17.687,
+      "eval_steps_per_second": 0.403,
+      "step": 6200
+    },
+    {
+      "epoch": 0.021866521661161473,
+      "grad_norm": 0.9246248602867126,
+      "learning_rate": 2.186588921282799e-05,
+      "loss": 1.7923,
+      "step": 6300
+    },
+    {
+      "epoch": 0.021866521661161473,
+      "eval_loss": 1.7781379222869873,
+      "eval_runtime": 24.4126,
+      "eval_samples_per_second": 17.983,
+      "eval_steps_per_second": 0.41,
+      "step": 6300
+    },
+    {
+      "epoch": 0.02221360930657673,
+      "grad_norm": 1.3288153409957886,
+      "learning_rate": 2.2212966819380814e-05,
+      "loss": 1.7866,
+      "step": 6400
+    },
+    {
+      "epoch": 0.02221360930657673,
+      "eval_loss": 1.781212568283081,
+      "eval_runtime": 24.7848,
+      "eval_samples_per_second": 17.712,
+      "eval_steps_per_second": 0.403,
+      "step": 6400
+    },
+    {
+      "epoch": 0.022560696951991994,
+      "grad_norm": 0.9484734535217285,
+      "learning_rate": 2.256004442593364e-05,
+      "loss": 1.7852,
+      "step": 6500
+    },
+    {
+      "epoch": 0.022560696951991994,
+      "eval_loss": 1.7785717248916626,
+      "eval_runtime": 24.4116,
+      "eval_samples_per_second": 17.983,
+      "eval_steps_per_second": 0.41,
+      "step": 6500
+    },
+    {
+      "epoch": 0.022907784597407256,
+      "grad_norm": 1.7850075960159302,
+      "learning_rate": 2.2907122032486464e-05,
+      "loss": 1.7838,
+      "step": 6600
+    },
+    {
+      "epoch": 0.022907784597407256,
+      "eval_loss": 1.7806742191314697,
+      "eval_runtime": 24.8097,
+      "eval_samples_per_second": 17.695,
+      "eval_steps_per_second": 0.403,
+      "step": 6600
+    },
+    {
+      "epoch": 0.02325487224282252,
+      "grad_norm": 0.8073210120201111,
+      "learning_rate": 2.325419963903929e-05,
+      "loss": 1.7817,
+      "step": 6700
+    },
+    {
+      "epoch": 0.02325487224282252,
+      "eval_loss": 1.7764739990234375,
+      "eval_runtime": 24.3455,
+      "eval_samples_per_second": 18.032,
+      "eval_steps_per_second": 0.411,
+      "step": 6700
+    },
+    {
+      "epoch": 0.023601959888237777,
+      "grad_norm": 1.089603304862976,
+      "learning_rate": 2.3601277245592115e-05,
+      "loss": 1.78,
+      "step": 6800
+    },
+    {
+      "epoch": 0.023601959888237777,
+      "eval_loss": 1.7742102146148682,
+      "eval_runtime": 24.8252,
+      "eval_samples_per_second": 17.684,
+      "eval_steps_per_second": 0.403,
+      "step": 6800
+    },
+    {
+      "epoch": 0.02394904753365304,
+      "grad_norm": 0.9081795811653137,
+      "learning_rate": 2.394835485214494e-05,
+      "loss": 1.7801,
+      "step": 6900
+    },
+    {
+      "epoch": 0.02394904753365304,
+      "eval_loss": 1.77180814743042,
+      "eval_runtime": 24.5243,
+      "eval_samples_per_second": 17.901,
+      "eval_steps_per_second": 0.408,
+      "step": 6900
+    },
+    {
+      "epoch": 0.024296135179068302,
+      "grad_norm": 0.760989248752594,
+      "learning_rate": 2.4295432458697766e-05,
+      "loss": 1.782,
+      "step": 7000
+    },
+    {
+      "epoch": 0.024296135179068302,
+      "eval_loss": 1.7700749635696411,
+      "eval_runtime": 24.8764,
+      "eval_samples_per_second": 17.647,
+      "eval_steps_per_second": 0.402,
+      "step": 7000
+    },
+    {
+      "epoch": 0.024643222824483564,
+      "grad_norm": 1.12177312374115,
+      "learning_rate": 2.464251006525059e-05,
+      "loss": 1.7819,
+      "step": 7100
+    },
+    {
+      "epoch": 0.024643222824483564,
+      "eval_loss": 1.7722524404525757,
+      "eval_runtime": 24.4905,
+      "eval_samples_per_second": 17.925,
+      "eval_steps_per_second": 0.408,
+      "step": 7100
+    },
+    {
+      "epoch": 0.024990310469898823,
+      "grad_norm": 39.85576629638672,
+      "learning_rate": 2.4989587671803416e-05,
+      "loss": 1.7812,
+      "step": 7200
+    },
+    {
+      "epoch": 0.024990310469898823,
+      "eval_loss": 1.7866556644439697,
+      "eval_runtime": 24.8928,
+      "eval_samples_per_second": 17.636,
+      "eval_steps_per_second": 0.402,
+      "step": 7200
+    },
+    {
+      "epoch": 0.025337398115314085,
+      "grad_norm": 1.0117896795272827,
+      "learning_rate": 2.533666527835624e-05,
+      "loss": 1.7824,
+      "step": 7300
+    },
+    {
+      "epoch": 0.025337398115314085,
+      "eval_loss": 1.7690812349319458,
+      "eval_runtime": 17.2093,
+      "eval_samples_per_second": 25.509,
+      "eval_steps_per_second": 0.581,
+      "step": 7300
+    },
+    {
+      "epoch": 0.025684485760729348,
+      "grad_norm": 1.1257307529449463,
+      "learning_rate": 2.5683742884909067e-05,
+      "loss": 1.7754,
+      "step": 7400
+    },
+    {
+      "epoch": 0.025684485760729348,
+      "eval_loss": 1.7678226232528687,
+      "eval_runtime": 17.576,
+      "eval_samples_per_second": 24.977,
+      "eval_steps_per_second": 0.569,
+      "step": 7400
+    },
+    {
+      "epoch": 0.02603157340614461,
+      "grad_norm": 0.8239357471466064,
+      "learning_rate": 2.6030820491461895e-05,
+      "loss": 1.7755,
+      "step": 7500
+    },
+    {
+      "epoch": 0.02603157340614461,
+      "eval_loss": 1.7637029886245728,
+      "eval_runtime": 16.9836,
+      "eval_samples_per_second": 25.848,
+      "eval_steps_per_second": 0.589,
+      "step": 7500
+    },
+    {
+      "epoch": 0.02637866105155987,
+      "grad_norm": 0.7548935413360596,
+      "learning_rate": 2.637789809801472e-05,
+      "loss": 1.7684,
+      "step": 7600
+    },
+    {
+      "epoch": 0.02637866105155987,
+      "eval_loss": 1.7627220153808594,
+      "eval_runtime": 17.2269,
+      "eval_samples_per_second": 25.483,
+      "eval_steps_per_second": 0.58,
+      "step": 7600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 288111,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.586067803209728e+18,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/training_args.bin b/training_args.bin
new file mode 100644
index 0000000..c10511b
--- /dev/null
+++ b/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4abf9186ebab50081ab8bb83e647eb73c8b9bc405acfdfaab3a6eaaa4d02444c
+size 5368