Upload folder using huggingface_hub

51_128_e3_3e-5/.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

51_128_e3_3e-5/README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: ibm-granite/granite-3.3-8b-base
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- data/knowledge_lora_training_data_1000
+model-index:
+- name: 51_128_e3_3e-5
+  results: []
+---
+
+<!-- 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. -->
+
+# 51_128_e3_3e-5
+
+This model is a fine-tuned version of [ibm-granite/granite-3.3-8b-base](https://huggingface.co/ibm-granite/granite-3.3-8b-base) on the data/knowledge_lora_training_data_1000 dataset.
+
+## 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: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.2

51_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

51_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e16e73919d6d904c3a25e982c0b11ba30e460d50edfd5a4eb70e9230205c93b
+size 791751704

51_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.4334566195296993e+18,
+    "train_loss": 0.5625010207752509,
+    "train_runtime": 674.2109,
+    "train_samples": 10425,
+    "train_samples_per_second": 46.388,
+    "train_steps_per_second": 1.451
+}

51_128_e3_3e-5/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 49152
+}

51_128_e3_3e-5/special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "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": "<reponame>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

51_128_e3_3e-5/tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<reponame>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

51_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.4334566195296993e+18,
+    "train_loss": 0.5625010207752509,
+    "train_runtime": 674.2109,
+    "train_samples": 10425,
+    "train_samples_per_second": 46.388,
+    "train_steps_per_second": 1.451
+}

51_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1408 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 978,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015337423312883436,
+      "grad_norm": 0.9479827880859375,
+      "learning_rate": 2.4489795918367347e-06,
+      "loss": 1.2914,
+      "step": 5
+    },
+    {
+      "epoch": 0.03067484662576687,
+      "grad_norm": 0.6532108187675476,
+      "learning_rate": 5.510204081632653e-06,
+      "loss": 1.2724,
+      "step": 10
+    },
+    {
+      "epoch": 0.046012269938650305,
+      "grad_norm": 0.7648320198059082,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 1.2327,
+      "step": 15
+    },
+    {
+      "epoch": 0.06134969325153374,
+      "grad_norm": 0.5440880060195923,
+      "learning_rate": 1.163265306122449e-05,
+      "loss": 1.236,
+      "step": 20
+    },
+    {
+      "epoch": 0.07668711656441718,
+      "grad_norm": 0.5116869807243347,
+      "learning_rate": 1.4693877551020408e-05,
+      "loss": 1.2763,
+      "step": 25
+    },
+    {
+      "epoch": 0.09202453987730061,
+      "grad_norm": 0.5124427080154419,
+      "learning_rate": 1.7755102040816327e-05,
+      "loss": 1.2272,
+      "step": 30
+    },
+    {
+      "epoch": 0.10736196319018405,
+      "grad_norm": 0.4724956750869751,
+      "learning_rate": 2.0816326530612247e-05,
+      "loss": 1.1925,
+      "step": 35
+    },
+    {
+      "epoch": 0.12269938650306748,
+      "grad_norm": 0.468453586101532,
+      "learning_rate": 2.3877551020408164e-05,
+      "loss": 1.2061,
+      "step": 40
+    },
+    {
+      "epoch": 0.13803680981595093,
+      "grad_norm": 0.46370843052864075,
+      "learning_rate": 2.6938775510204084e-05,
+      "loss": 1.2048,
+      "step": 45
+    },
+    {
+      "epoch": 0.15337423312883436,
+      "grad_norm": 0.445858359336853,
+      "learning_rate": 3e-05,
+      "loss": 1.1646,
+      "step": 50
+    },
+    {
+      "epoch": 0.1687116564417178,
+      "grad_norm": 0.48852217197418213,
+      "learning_rate": 2.999785582986574e-05,
+      "loss": 1.193,
+      "step": 55
+    },
+    {
+      "epoch": 0.18404907975460122,
+      "grad_norm": 0.4960137605667114,
+      "learning_rate": 2.9991423932458366e-05,
+      "loss": 1.0939,
+      "step": 60
+    },
+    {
+      "epoch": 0.19938650306748465,
+      "grad_norm": 0.5038251876831055,
+      "learning_rate": 2.9980706146588852e-05,
+      "loss": 1.1392,
+      "step": 65
+    },
+    {
+      "epoch": 0.2147239263803681,
+      "grad_norm": 0.5848245024681091,
+      "learning_rate": 2.9965705536358054e-05,
+      "loss": 1.0737,
+      "step": 70
+    },
+    {
+      "epoch": 0.23006134969325154,
+      "grad_norm": 0.4853243827819824,
+      "learning_rate": 2.9946426390280696e-05,
+      "loss": 1.1028,
+      "step": 75
+    },
+    {
+      "epoch": 0.24539877300613497,
+      "grad_norm": 0.4873882830142975,
+      "learning_rate": 2.992287422005934e-05,
+      "loss": 1.1089,
+      "step": 80
+    },
+    {
+      "epoch": 0.2607361963190184,
+      "grad_norm": 0.503591775894165,
+      "learning_rate": 2.9895055759008655e-05,
+      "loss": 1.077,
+      "step": 85
+    },
+    {
+      "epoch": 0.27607361963190186,
+      "grad_norm": 0.4841548502445221,
+      "learning_rate": 2.9862978960130418e-05,
+      "loss": 1.0475,
+      "step": 90
+    },
+    {
+      "epoch": 0.29141104294478526,
+      "grad_norm": 0.5389356017112732,
+      "learning_rate": 2.9826652993839853e-05,
+      "loss": 1.0377,
+      "step": 95
+    },
+    {
+      "epoch": 0.3067484662576687,
+      "grad_norm": 0.4708312451839447,
+      "learning_rate": 2.9786088245343896e-05,
+      "loss": 1.0261,
+      "step": 100
+    },
+    {
+      "epoch": 0.3220858895705521,
+      "grad_norm": 0.6129530072212219,
+      "learning_rate": 2.974129631167218e-05,
+      "loss": 1.0388,
+      "step": 105
+    },
+    {
+      "epoch": 0.3374233128834356,
+      "grad_norm": 0.6659024357795715,
+      "learning_rate": 2.969228999836156e-05,
+      "loss": 1.0287,
+      "step": 110
+    },
+    {
+      "epoch": 0.35276073619631904,
+      "grad_norm": 0.539665162563324,
+      "learning_rate": 2.963908331579515e-05,
+      "loss": 1.0355,
+      "step": 115
+    },
+    {
+      "epoch": 0.36809815950920244,
+      "grad_norm": 0.6108341217041016,
+      "learning_rate": 2.9581691475196915e-05,
+      "loss": 0.9654,
+      "step": 120
+    },
+    {
+      "epoch": 0.3834355828220859,
+      "grad_norm": 0.5414963960647583,
+      "learning_rate": 2.9520130884282933e-05,
+      "loss": 0.9653,
+      "step": 125
+    },
+    {
+      "epoch": 0.3987730061349693,
+      "grad_norm": 0.623569130897522,
+      "learning_rate": 2.94544191425706e-05,
+      "loss": 0.9541,
+      "step": 130
+    },
+    {
+      "epoch": 0.41411042944785276,
+      "grad_norm": 0.6428107619285583,
+      "learning_rate": 2.938457503634712e-05,
+      "loss": 0.928,
+      "step": 135
+    },
+    {
+      "epoch": 0.4294478527607362,
+      "grad_norm": 0.7320411205291748,
+      "learning_rate": 2.931061853329871e-05,
+      "loss": 0.9412,
+      "step": 140
+    },
+    {
+      "epoch": 0.4447852760736196,
+      "grad_norm": 0.6268852949142456,
+      "learning_rate": 2.9232570776802047e-05,
+      "loss": 0.9467,
+      "step": 145
+    },
+    {
+      "epoch": 0.4601226993865031,
+      "grad_norm": 0.7097761631011963,
+      "learning_rate": 2.9150454079879597e-05,
+      "loss": 0.9425,
+      "step": 150
+    },
+    {
+      "epoch": 0.4754601226993865,
+      "grad_norm": 0.7176456451416016,
+      "learning_rate": 2.9064291918820576e-05,
+      "loss": 0.9134,
+      "step": 155
+    },
+    {
+      "epoch": 0.49079754601226994,
+      "grad_norm": 0.6366844773292542,
+      "learning_rate": 2.8974108926469306e-05,
+      "loss": 0.8768,
+      "step": 160
+    },
+    {
+      "epoch": 0.5061349693251533,
+      "grad_norm": 0.7397588491439819,
+      "learning_rate": 2.8879930885182965e-05,
+      "loss": 0.9381,
+      "step": 165
+    },
+    {
+      "epoch": 0.5214723926380368,
+      "grad_norm": 0.7433550953865051,
+      "learning_rate": 2.8781784719460674e-05,
+      "loss": 0.9354,
+      "step": 170
+    },
+    {
+      "epoch": 0.5368098159509203,
+      "grad_norm": 0.7571491599082947,
+      "learning_rate": 2.8679698488246075e-05,
+      "loss": 0.8806,
+      "step": 175
+    },
+    {
+      "epoch": 0.5521472392638037,
+      "grad_norm": 0.8180937170982361,
+      "learning_rate": 2.8573701376905585e-05,
+      "loss": 0.8255,
+      "step": 180
+    },
+    {
+      "epoch": 0.5674846625766872,
+      "grad_norm": 0.820141613483429,
+      "learning_rate": 2.8463823688884598e-05,
+      "loss": 0.8304,
+      "step": 185
+    },
+    {
+      "epoch": 0.5828220858895705,
+      "grad_norm": 0.6901472210884094,
+      "learning_rate": 2.835009683704406e-05,
+      "loss": 0.8722,
+      "step": 190
+    },
+    {
+      "epoch": 0.598159509202454,
+      "grad_norm": 0.7843679189682007,
+      "learning_rate": 2.823255333467985e-05,
+      "loss": 0.8664,
+      "step": 195
+    },
+    {
+      "epoch": 0.6134969325153374,
+      "grad_norm": 0.8625418543815613,
+      "learning_rate": 2.8111226786227614e-05,
+      "loss": 0.8202,
+      "step": 200
+    },
+    {
+      "epoch": 0.6288343558282209,
+      "grad_norm": 0.8017191886901855,
+      "learning_rate": 2.798615187765557e-05,
+      "loss": 0.7733,
+      "step": 205
+    },
+    {
+      "epoch": 0.6441717791411042,
+      "grad_norm": 0.9335097074508667,
+      "learning_rate": 2.7857364366548185e-05,
+      "loss": 0.8315,
+      "step": 210
+    },
+    {
+      "epoch": 0.6595092024539877,
+      "grad_norm": 0.8092615604400635,
+      "learning_rate": 2.7724901071883457e-05,
+      "loss": 0.8307,
+      "step": 215
+    },
+    {
+      "epoch": 0.6748466257668712,
+      "grad_norm": 0.8395926356315613,
+      "learning_rate": 2.7588799863506762e-05,
+      "loss": 0.8117,
+      "step": 220
+    },
+    {
+      "epoch": 0.6901840490797546,
+      "grad_norm": 0.8694223165512085,
+      "learning_rate": 2.7449099651304265e-05,
+      "loss": 0.7547,
+      "step": 225
+    },
+    {
+      "epoch": 0.7055214723926381,
+      "grad_norm": 1.063184380531311,
+      "learning_rate": 2.7305840374078997e-05,
+      "loss": 0.7945,
+      "step": 230
+    },
+    {
+      "epoch": 0.7208588957055214,
+      "grad_norm": 0.874076783657074,
+      "learning_rate": 2.7159062988132788e-05,
+      "loss": 0.7991,
+      "step": 235
+    },
+    {
+      "epoch": 0.7361963190184049,
+      "grad_norm": 0.8423658013343811,
+      "learning_rate": 2.7008809455557276e-05,
+      "loss": 0.7501,
+      "step": 240
+    },
+    {
+      "epoch": 0.7515337423312883,
+      "grad_norm": 0.7731667757034302,
+      "learning_rate": 2.6855122732237414e-05,
+      "loss": 0.7446,
+      "step": 245
+    },
+    {
+      "epoch": 0.7668711656441718,
+      "grad_norm": 0.9163995385169983,
+      "learning_rate": 2.6698046755570824e-05,
+      "loss": 0.7705,
+      "step": 250
+    },
+    {
+      "epoch": 0.7822085889570553,
+      "grad_norm": 0.8659682869911194,
+      "learning_rate": 2.6537626431906568e-05,
+      "loss": 0.7091,
+      "step": 255
+    },
+    {
+      "epoch": 0.7975460122699386,
+      "grad_norm": 0.8967508673667908,
+      "learning_rate": 2.63739076237069e-05,
+      "loss": 0.7324,
+      "step": 260
+    },
+    {
+      "epoch": 0.8128834355828221,
+      "grad_norm": 0.9549793004989624,
+      "learning_rate": 2.6206937136435696e-05,
+      "loss": 0.7469,
+      "step": 265
+    },
+    {
+      "epoch": 0.8282208588957055,
+      "grad_norm": 0.8499115705490112,
+      "learning_rate": 2.603676270517722e-05,
+      "loss": 0.7105,
+      "step": 270
+    },
+    {
+      "epoch": 0.843558282208589,
+      "grad_norm": 0.9262447357177734,
+      "learning_rate": 2.586343298098923e-05,
+      "loss": 0.7193,
+      "step": 275
+    },
+    {
+      "epoch": 0.8588957055214724,
+      "grad_norm": 0.8585225939750671,
+      "learning_rate": 2.5686997516994123e-05,
+      "loss": 0.7058,
+      "step": 280
+    },
+    {
+      "epoch": 0.8742331288343558,
+      "grad_norm": 0.9979948997497559,
+      "learning_rate": 2.5507506754212233e-05,
+      "loss": 0.7128,
+      "step": 285
+    },
+    {
+      "epoch": 0.8895705521472392,
+      "grad_norm": 0.9485252499580383,
+      "learning_rate": 2.532501200714129e-05,
+      "loss": 0.6953,
+      "step": 290
+    },
+    {
+      "epoch": 0.9049079754601227,
+      "grad_norm": 0.9380909204483032,
+      "learning_rate": 2.5139565449086128e-05,
+      "loss": 0.719,
+      "step": 295
+    },
+    {
+      "epoch": 0.9202453987730062,
+      "grad_norm": 1.0208559036254883,
+      "learning_rate": 2.4951220097242927e-05,
+      "loss": 0.7207,
+      "step": 300
+    },
+    {
+      "epoch": 0.9355828220858896,
+      "grad_norm": 0.933393120765686,
+      "learning_rate": 2.4760029797542133e-05,
+      "loss": 0.7175,
+      "step": 305
+    },
+    {
+      "epoch": 0.950920245398773,
+      "grad_norm": 0.971408486366272,
+      "learning_rate": 2.456604920925448e-05,
+      "loss": 0.6762,
+      "step": 310
+    },
+    {
+      "epoch": 0.9662576687116564,
+      "grad_norm": 1.1367558240890503,
+      "learning_rate": 2.4369333789364523e-05,
+      "loss": 0.673,
+      "step": 315
+    },
+    {
+      "epoch": 0.9815950920245399,
+      "grad_norm": 0.9299585819244385,
+      "learning_rate": 2.4169939776716013e-05,
+      "loss": 0.6968,
+      "step": 320
+    },
+    {
+      "epoch": 0.9969325153374233,
+      "grad_norm": 1.0021302700042725,
+      "learning_rate": 2.396792417593388e-05,
+      "loss": 0.6546,
+      "step": 325
+    },
+    {
+      "epoch": 1.0122699386503067,
+      "grad_norm": 1.3160091638565063,
+      "learning_rate": 2.3763344741127168e-05,
+      "loss": 0.6162,
+      "step": 330
+    },
+    {
+      "epoch": 1.0276073619631902,
+      "grad_norm": 1.0747168064117432,
+      "learning_rate": 2.355625995937776e-05,
+      "loss": 0.593,
+      "step": 335
+    },
+    {
+      "epoch": 1.0429447852760736,
+      "grad_norm": 1.2322441339492798,
+      "learning_rate": 2.3346729034019575e-05,
+      "loss": 0.5646,
+      "step": 340
+    },
+    {
+      "epoch": 1.058282208588957,
+      "grad_norm": 1.1179224252700806,
+      "learning_rate": 2.3134811867712926e-05,
+      "loss": 0.5695,
+      "step": 345
+    },
+    {
+      "epoch": 1.0736196319018405,
+      "grad_norm": 1.0664554834365845,
+      "learning_rate": 2.292056904531899e-05,
+      "loss": 0.5865,
+      "step": 350
+    },
+    {
+      "epoch": 1.0889570552147239,
+      "grad_norm": 0.969951331615448,
+      "learning_rate": 2.2704061816579282e-05,
+      "loss": 0.5797,
+      "step": 355
+    },
+    {
+      "epoch": 1.1042944785276074,
+      "grad_norm": 0.9852150082588196,
+      "learning_rate": 2.248535207860496e-05,
+      "loss": 0.5176,
+      "step": 360
+    },
+    {
+      "epoch": 1.1196319018404908,
+      "grad_norm": 1.1692544221878052,
+      "learning_rate": 2.226450235818112e-05,
+      "loss": 0.555,
+      "step": 365
+    },
+    {
+      "epoch": 1.1349693251533743,
+      "grad_norm": 1.2176973819732666,
+      "learning_rate": 2.2041575793891056e-05,
+      "loss": 0.5477,
+      "step": 370
+    },
+    {
+      "epoch": 1.1503067484662577,
+      "grad_norm": 1.351145625114441,
+      "learning_rate": 2.1816636118065607e-05,
+      "loss": 0.5521,
+      "step": 375
+    },
+    {
+      "epoch": 1.165644171779141,
+      "grad_norm": 1.1659549474716187,
+      "learning_rate": 2.1589747638562763e-05,
+      "loss": 0.5499,
+      "step": 380
+    },
+    {
+      "epoch": 1.1809815950920246,
+      "grad_norm": 1.0642236471176147,
+      "learning_rate": 2.1360975220382722e-05,
+      "loss": 0.5265,
+      "step": 385
+    },
+    {
+      "epoch": 1.196319018404908,
+      "grad_norm": 1.2559146881103516,
+      "learning_rate": 2.113038426712371e-05,
+      "loss": 0.5594,
+      "step": 390
+    },
+    {
+      "epoch": 1.2116564417177913,
+      "grad_norm": 1.134261131286621,
+      "learning_rate": 2.089804070228375e-05,
+      "loss": 0.5242,
+      "step": 395
+    },
+    {
+      "epoch": 1.2269938650306749,
+      "grad_norm": 1.1124902963638306,
+      "learning_rate": 2.066401095041386e-05,
+      "loss": 0.5316,
+      "step": 400
+    },
+    {
+      "epoch": 1.2423312883435582,
+      "grad_norm": 1.0494729280471802,
+      "learning_rate": 2.0428361918127962e-05,
+      "loss": 0.5169,
+      "step": 405
+    },
+    {
+      "epoch": 1.2576687116564418,
+      "grad_norm": 1.053193211555481,
+      "learning_rate": 2.019116097497503e-05,
+      "loss": 0.5259,
+      "step": 410
+    },
+    {
+      "epoch": 1.2730061349693251,
+      "grad_norm": 1.1603937149047852,
+      "learning_rate": 1.9952475934178798e-05,
+      "loss": 0.4998,
+      "step": 415
+    },
+    {
+      "epoch": 1.2883435582822087,
+      "grad_norm": 1.0774054527282715,
+      "learning_rate": 1.971237503325075e-05,
+      "loss": 0.4797,
+      "step": 420
+    },
+    {
+      "epoch": 1.303680981595092,
+      "grad_norm": 0.9619120955467224,
+      "learning_rate": 1.947092691448166e-05,
+      "loss": 0.5213,
+      "step": 425
+    },
+    {
+      "epoch": 1.3190184049079754,
+      "grad_norm": 1.1378053426742554,
+      "learning_rate": 1.9228200605317574e-05,
+      "loss": 0.4757,
+      "step": 430
+    },
+    {
+      "epoch": 1.334355828220859,
+      "grad_norm": 1.149680495262146,
+      "learning_rate": 1.8984265498625546e-05,
+      "loss": 0.4801,
+      "step": 435
+    },
+    {
+      "epoch": 1.3496932515337423,
+      "grad_norm": 1.0541986227035522,
+      "learning_rate": 1.8739191332854967e-05,
+      "loss": 0.518,
+      "step": 440
+    },
+    {
+      "epoch": 1.3650306748466257,
+      "grad_norm": 1.0434142351150513,
+      "learning_rate": 1.8493048172100095e-05,
+      "loss": 0.4935,
+      "step": 445
+    },
+    {
+      "epoch": 1.3803680981595092,
+      "grad_norm": 1.0216686725616455,
+      "learning_rate": 1.824590638606947e-05,
+      "loss": 0.5304,
+      "step": 450
+    },
+    {
+      "epoch": 1.3957055214723926,
+      "grad_norm": 1.1520646810531616,
+      "learning_rate": 1.7997836629967962e-05,
+      "loss": 0.4555,
+      "step": 455
+    },
+    {
+      "epoch": 1.4110429447852761,
+      "grad_norm": 1.0427292585372925,
+      "learning_rate": 1.7748909824297204e-05,
+      "loss": 0.4865,
+      "step": 460
+    },
+    {
+      "epoch": 1.4263803680981595,
+      "grad_norm": 1.133017897605896,
+      "learning_rate": 1.7499197134580174e-05,
+      "loss": 0.4863,
+      "step": 465
+    },
+    {
+      "epoch": 1.441717791411043,
+      "grad_norm": 1.153871774673462,
+      "learning_rate": 1.7248769951015734e-05,
+      "loss": 0.4925,
+      "step": 470
+    },
+    {
+      "epoch": 1.4570552147239264,
+      "grad_norm": 1.1278655529022217,
+      "learning_rate": 1.6997699868068918e-05,
+      "loss": 0.4752,
+      "step": 475
+    },
+    {
+      "epoch": 1.4723926380368098,
+      "grad_norm": 1.183666706085205,
+      "learning_rate": 1.674605866400286e-05,
+      "loss": 0.47,
+      "step": 480
+    },
+    {
+      "epoch": 1.4877300613496933,
+      "grad_norm": 1.1284968852996826,
+      "learning_rate": 1.6493918280358135e-05,
+      "loss": 0.4844,
+      "step": 485
+    },
+    {
+      "epoch": 1.5030674846625767,
+      "grad_norm": 1.1074920892715454,
+      "learning_rate": 1.6241350801385434e-05,
+      "loss": 0.4511,
+      "step": 490
+    },
+    {
+      "epoch": 1.51840490797546,
+      "grad_norm": 1.194481372833252,
+      "learning_rate": 1.5988428433437477e-05,
+      "loss": 0.486,
+      "step": 495
+    },
+    {
+      "epoch": 1.5337423312883436,
+      "grad_norm": 1.1266710758209229,
+      "learning_rate": 1.573522348432594e-05,
+      "loss": 0.4731,
+      "step": 500
+    },
+    {
+      "epoch": 1.5490797546012272,
+      "grad_norm": 1.157607078552246,
+      "learning_rate": 1.5481808342649455e-05,
+      "loss": 0.4472,
+      "step": 505
+    },
+    {
+      "epoch": 1.5644171779141103,
+      "grad_norm": 0.9894949197769165,
+      "learning_rate": 1.522825545709847e-05,
+      "loss": 0.4269,
+      "step": 510
+    },
+    {
+      "epoch": 1.5797546012269938,
+      "grad_norm": 1.1299246549606323,
+      "learning_rate": 1.497463731574294e-05,
+      "loss": 0.431,
+      "step": 515
+    },
+    {
+      "epoch": 1.5950920245398774,
+      "grad_norm": 1.2490668296813965,
+      "learning_rate": 1.4721026425308758e-05,
+      "loss": 0.4632,
+      "step": 520
+    },
+    {
+      "epoch": 1.6104294478527608,
+      "grad_norm": 1.1780003309249878,
+      "learning_rate": 1.446749529044886e-05,
+      "loss": 0.4291,
+      "step": 525
+    },
+    {
+      "epoch": 1.6257668711656441,
+      "grad_norm": 1.257867455482483,
+      "learning_rate": 1.4214116393014902e-05,
+      "loss": 0.4417,
+      "step": 530
+    },
+    {
+      "epoch": 1.6411042944785277,
+      "grad_norm": 1.0419623851776123,
+      "learning_rate": 1.3960962171335487e-05,
+      "loss": 0.4001,
+      "step": 535
+    },
+    {
+      "epoch": 1.656441717791411,
+      "grad_norm": 1.1442716121673584,
+      "learning_rate": 1.3708104999506819e-05,
+      "loss": 0.4708,
+      "step": 540
+    },
+    {
+      "epoch": 1.6717791411042944,
+      "grad_norm": 1.2492327690124512,
+      "learning_rate": 1.3455617166701712e-05,
+      "loss": 0.4616,
+      "step": 545
+    },
+    {
+      "epoch": 1.687116564417178,
+      "grad_norm": 1.1348553895950317,
+      "learning_rate": 1.320357085650287e-05,
+      "loss": 0.4147,
+      "step": 550
+    },
+    {
+      "epoch": 1.7024539877300615,
+      "grad_norm": 1.2993242740631104,
+      "learning_rate": 1.29520381262664e-05,
+      "loss": 0.4012,
+      "step": 555
+    },
+    {
+      "epoch": 1.7177914110429446,
+      "grad_norm": 1.278564691543579,
+      "learning_rate": 1.2701090886521366e-05,
+      "loss": 0.437,
+      "step": 560
+    },
+    {
+      "epoch": 1.7331288343558282,
+      "grad_norm": 1.0541185140609741,
+      "learning_rate": 1.2450800880411339e-05,
+      "loss": 0.3997,
+      "step": 565
+    },
+    {
+      "epoch": 1.7484662576687118,
+      "grad_norm": 1.1179388761520386,
+      "learning_rate": 1.2201239663183771e-05,
+      "loss": 0.3816,
+      "step": 570
+    },
+    {
+      "epoch": 1.7638036809815951,
+      "grad_norm": 1.2214819192886353,
+      "learning_rate": 1.1952478581733159e-05,
+      "loss": 0.4286,
+      "step": 575
+    },
+    {
+      "epoch": 1.7791411042944785,
+      "grad_norm": 1.20120370388031,
+      "learning_rate": 1.1704588754203695e-05,
+      "loss": 0.4101,
+      "step": 580
+    },
+    {
+      "epoch": 1.794478527607362,
+      "grad_norm": 1.140474557876587,
+      "learning_rate": 1.1457641049657336e-05,
+      "loss": 0.4007,
+      "step": 585
+    },
+    {
+      "epoch": 1.8098159509202454,
+      "grad_norm": 1.0792462825775146,
+      "learning_rate": 1.1211706067813135e-05,
+      "loss": 0.4321,
+      "step": 590
+    },
+    {
+      "epoch": 1.8251533742331287,
+      "grad_norm": 1.357324242591858,
+      "learning_rate": 1.096685411886349e-05,
+      "loss": 0.4078,
+      "step": 595
+    },
+    {
+      "epoch": 1.8404907975460123,
+      "grad_norm": 1.175324559211731,
+      "learning_rate": 1.0723155203373247e-05,
+      "loss": 0.4092,
+      "step": 600
+    },
+    {
+      "epoch": 1.8558282208588959,
+      "grad_norm": 1.4264357089996338,
+      "learning_rate": 1.0480678992267235e-05,
+      "loss": 0.409,
+      "step": 605
+    },
+    {
+      "epoch": 1.871165644171779,
+      "grad_norm": 1.2610962390899658,
+      "learning_rate": 1.0239494806912149e-05,
+      "loss": 0.4052,
+      "step": 610
+    },
+    {
+      "epoch": 1.8865030674846626,
+      "grad_norm": 1.133188009262085,
+      "learning_rate": 9.999671599298262e-06,
+      "loss": 0.4083,
+      "step": 615
+    },
+    {
+      "epoch": 1.9018404907975461,
+      "grad_norm": 1.1806271076202393,
+      "learning_rate": 9.761277932326818e-06,
+      "loss": 0.4028,
+      "step": 620
+    },
+    {
+      "epoch": 1.9171779141104295,
+      "grad_norm": 1.1987602710723877,
+      "learning_rate": 9.524381960208598e-06,
+      "loss": 0.3965,
+      "step": 625
+    },
+    {
+      "epoch": 1.9325153374233128,
+      "grad_norm": 1.2796728610992432,
+      "learning_rate": 9.289051408979382e-06,
+      "loss": 0.3501,
+      "step": 630
+    },
+    {
+      "epoch": 1.9478527607361964,
+      "grad_norm": 1.212151288986206,
+      "learning_rate": 9.055353557137789e-06,
+      "loss": 0.3578,
+      "step": 635
+    },
+    {
+      "epoch": 1.9631901840490797,
+      "grad_norm": 1.1031944751739502,
+      "learning_rate": 8.82335521641107e-06,
+      "loss": 0.4611,
+      "step": 640
+    },
+    {
+      "epoch": 1.978527607361963,
+      "grad_norm": 1.1507176160812378,
+      "learning_rate": 8.593122712654337e-06,
+      "loss": 0.3971,
+      "step": 645
+    },
+    {
+      "epoch": 1.9938650306748467,
+      "grad_norm": 1.3288483619689941,
+      "learning_rate": 8.364721866888716e-06,
+      "loss": 0.3795,
+      "step": 650
+    },
+    {
+      "epoch": 2.0092024539877302,
+      "grad_norm": 1.1326398849487305,
+      "learning_rate": 8.138217976483847e-06,
+      "loss": 0.3444,
+      "step": 655
+    },
+    {
+      "epoch": 2.0245398773006134,
+      "grad_norm": 1.2195041179656982,
+      "learning_rate": 7.913675796489983e-06,
+      "loss": 0.3054,
+      "step": 660
+    },
+    {
+      "epoch": 2.039877300613497,
+      "grad_norm": 1.240760087966919,
+      "learning_rate": 7.691159521125304e-06,
+      "loss": 0.3669,
+      "step": 665
+    },
+    {
+      "epoch": 2.0552147239263805,
+      "grad_norm": 1.090166449546814,
+      "learning_rate": 7.470732765423413e-06,
+      "loss": 0.3017,
+      "step": 670
+    },
+    {
+      "epoch": 2.0705521472392636,
+      "grad_norm": 1.2588560581207275,
+      "learning_rate": 7.252458547046486e-06,
+      "loss": 0.2871,
+      "step": 675
+    },
+    {
+      "epoch": 2.085889570552147,
+      "grad_norm": 1.1772913932800293,
+      "learning_rate": 7.0363992682692095e-06,
+      "loss": 0.2965,
+      "step": 680
+    },
+    {
+      "epoch": 2.1012269938650308,
+      "grad_norm": 1.2672231197357178,
+      "learning_rate": 6.822616698138619e-06,
+      "loss": 0.3516,
+      "step": 685
+    },
+    {
+      "epoch": 2.116564417177914,
+      "grad_norm": 1.194394826889038,
+      "learning_rate": 6.611171954814998e-06,
+      "loss": 0.3016,
+      "step": 690
+    },
+    {
+      "epoch": 2.1319018404907975,
+      "grad_norm": 1.2427701950073242,
+      "learning_rate": 6.402125488098835e-06,
+      "loss": 0.3077,
+      "step": 695
+    },
+    {
+      "epoch": 2.147239263803681,
+      "grad_norm": 1.3371913433074951,
+      "learning_rate": 6.195537062148877e-06,
+      "loss": 0.3189,
+      "step": 700
+    },
+    {
+      "epoch": 2.1625766871165646,
+      "grad_norm": 1.1829326152801514,
+      "learning_rate": 5.9914657383961854e-06,
+      "loss": 0.2919,
+      "step": 705
+    },
+    {
+      "epoch": 2.1779141104294477,
+      "grad_norm": 1.1718101501464844,
+      "learning_rate": 5.789969858659134e-06,
+      "loss": 0.3108,
+      "step": 710
+    },
+    {
+      "epoch": 2.1932515337423313,
+      "grad_norm": 1.3176288604736328,
+      "learning_rate": 5.591107028464035e-06,
+      "loss": 0.2868,
+      "step": 715
+    },
+    {
+      "epoch": 2.208588957055215,
+      "grad_norm": 1.2966890335083008,
+      "learning_rate": 5.3949341005764045e-06,
+      "loss": 0.2952,
+      "step": 720
+    },
+    {
+      "epoch": 2.223926380368098,
+      "grad_norm": 1.3806135654449463,
+      "learning_rate": 5.20150715874733e-06,
+      "loss": 0.2908,
+      "step": 725
+    },
+    {
+      "epoch": 2.2392638036809815,
+      "grad_norm": 1.1960639953613281,
+      "learning_rate": 5.0108815016797264e-06,
+      "loss": 0.2975,
+      "step": 730
+    },
+    {
+      "epoch": 2.254601226993865,
+      "grad_norm": 1.2420316934585571,
+      "learning_rate": 4.823111627219005e-06,
+      "loss": 0.3089,
+      "step": 735
+    },
+    {
+      "epoch": 2.2699386503067487,
+      "grad_norm": 1.2030253410339355,
+      "learning_rate": 4.638251216772771e-06,
+      "loss": 0.3181,
+      "step": 740
+    },
+    {
+      "epoch": 2.285276073619632,
+      "grad_norm": 1.3142906427383423,
+      "learning_rate": 4.456353119963834e-06,
+      "loss": 0.3313,
+      "step": 745
+    },
+    {
+      "epoch": 2.3006134969325154,
+      "grad_norm": 1.2937871217727661,
+      "learning_rate": 4.277469339521078e-06,
+      "loss": 0.2948,
+      "step": 750
+    },
+    {
+      "epoch": 2.315950920245399,
+      "grad_norm": 1.3126288652420044,
+      "learning_rate": 4.101651016412442e-06,
+      "loss": 0.3103,
+      "step": 755
+    },
+    {
+      "epoch": 2.331288343558282,
+      "grad_norm": 1.1288119554519653,
+      "learning_rate": 3.9289484152242526e-06,
+      "loss": 0.2648,
+      "step": 760
+    },
+    {
+      "epoch": 2.3466257668711656,
+      "grad_norm": 1.1804512739181519,
+      "learning_rate": 3.7594109097911208e-06,
+      "loss": 0.3286,
+      "step": 765
+    },
+    {
+      "epoch": 2.361963190184049,
+      "grad_norm": 1.1652648448944092,
+      "learning_rate": 3.5930869690804914e-06,
+      "loss": 0.2772,
+      "step": 770
+    },
+    {
+      "epoch": 2.3773006134969323,
+      "grad_norm": 1.175654649734497,
+      "learning_rate": 3.430024143335861e-06,
+      "loss": 0.2843,
+      "step": 775
+    },
+    {
+      "epoch": 2.392638036809816,
+      "grad_norm": 1.4218146800994873,
+      "learning_rate": 3.2702690504826894e-06,
+      "loss": 0.3156,
+      "step": 780
+    },
+    {
+      "epoch": 2.4079754601226995,
+      "grad_norm": 1.2394732236862183,
+      "learning_rate": 3.113867362800843e-06,
+      "loss": 0.2932,
+      "step": 785
+    },
+    {
+      "epoch": 2.4233128834355826,
+      "grad_norm": 1.165306568145752,
+      "learning_rate": 2.9608637938673327e-06,
+      "loss": 0.279,
+      "step": 790
+    },
+    {
+      "epoch": 2.438650306748466,
+      "grad_norm": 1.4578087329864502,
+      "learning_rate": 2.8113020857732165e-06,
+      "loss": 0.2863,
+      "step": 795
+    },
+    {
+      "epoch": 2.4539877300613497,
+      "grad_norm": 1.0880450010299683,
+      "learning_rate": 2.6652249966181997e-06,
+      "loss": 0.3053,
+      "step": 800
+    },
+    {
+      "epoch": 2.4693251533742333,
+      "grad_norm": 1.248149037361145,
+      "learning_rate": 2.52267428828653e-06,
+      "loss": 0.2773,
+      "step": 805
+    },
+    {
+      "epoch": 2.4846625766871164,
+      "grad_norm": 1.11225426197052,
+      "learning_rate": 2.383690714507722e-06,
+      "loss": 0.297,
+      "step": 810
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.144210934638977,
+      "learning_rate": 2.2483140092055233e-06,
+      "loss": 0.284,
+      "step": 815
+    },
+    {
+      "epoch": 2.5153374233128836,
+      "grad_norm": 1.362216591835022,
+      "learning_rate": 2.116582875138382e-06,
+      "loss": 0.2914,
+      "step": 820
+    },
+    {
+      "epoch": 2.530674846625767,
+      "grad_norm": 1.4110219478607178,
+      "learning_rate": 1.9885349728347555e-06,
+      "loss": 0.339,
+      "step": 825
+    },
+    {
+      "epoch": 2.5460122699386503,
+      "grad_norm": 1.2461217641830444,
+      "learning_rate": 1.8642069098263603e-06,
+      "loss": 0.2775,
+      "step": 830
+    },
+    {
+      "epoch": 2.561349693251534,
+      "grad_norm": 1.2816096544265747,
+      "learning_rate": 1.7436342301824687e-06,
+      "loss": 0.3125,
+      "step": 835
+    },
+    {
+      "epoch": 2.5766871165644174,
+      "grad_norm": 1.1968787908554077,
+      "learning_rate": 1.6268514043482425e-06,
+      "loss": 0.2742,
+      "step": 840
+    },
+    {
+      "epoch": 2.5920245398773005,
+      "grad_norm": 1.2479854822158813,
+      "learning_rate": 1.513891819289993e-06,
+      "loss": 0.2918,
+      "step": 845
+    },
+    {
+      "epoch": 2.607361963190184,
+      "grad_norm": 1.1733531951904297,
+      "learning_rate": 1.4047877689502092e-06,
+      "loss": 0.2543,
+      "step": 850
+    },
+    {
+      "epoch": 2.6226993865030677,
+      "grad_norm": 1.1784672737121582,
+      "learning_rate": 1.2995704450150565e-06,
+      "loss": 0.2948,
+      "step": 855
+    },
+    {
+      "epoch": 2.638036809815951,
+      "grad_norm": 1.200485348701477,
+      "learning_rate": 1.1982699279970223e-06,
+      "loss": 0.257,
+      "step": 860
+    },
+    {
+      "epoch": 2.6533742331288344,
+      "grad_norm": 1.071563959121704,
+      "learning_rate": 1.1009151786351884e-06,
+      "loss": 0.2979,
+      "step": 865
+    },
+    {
+      "epoch": 2.668711656441718,
+      "grad_norm": 1.348412275314331,
+      "learning_rate": 1.0075340296156894e-06,
+      "loss": 0.2841,
+      "step": 870
+    },
+    {
+      "epoch": 2.684049079754601,
+      "grad_norm": 1.358690857887268,
+      "learning_rate": 9.181531776146412e-07,
+      "loss": 0.3097,
+      "step": 875
+    },
+    {
+      "epoch": 2.6993865030674846,
+      "grad_norm": 1.1868973970413208,
+      "learning_rate": 8.327981756658332e-07,
+      "loss": 0.2827,
+      "step": 880
+    },
+    {
+      "epoch": 2.714723926380368,
+      "grad_norm": 1.2396225929260254,
+      "learning_rate": 7.514934258553969e-07,
+      "loss": 0.2842,
+      "step": 885
+    },
+    {
+      "epoch": 2.7300613496932513,
+      "grad_norm": 1.1880395412445068,
+      "learning_rate": 6.742621723455072e-07,
+      "loss": 0.2994,
+      "step": 890
+    },
+    {
+      "epoch": 2.745398773006135,
+      "grad_norm": 1.0822758674621582,
+      "learning_rate": 6.01126494729125e-07,
+      "loss": 0.2556,
+      "step": 895
+    },
+    {
+      "epoch": 2.7607361963190185,
+      "grad_norm": 1.2059530019760132,
+      "learning_rate": 5.321073017176775e-07,
+      "loss": 0.2836,
+      "step": 900
+    },
+    {
+      "epoch": 2.7760736196319016,
+      "grad_norm": 1.1232023239135742,
+      "learning_rate": 4.67224325163475e-07,
+      "loss": 0.2975,
+      "step": 905
+    },
+    {
+      "epoch": 2.791411042944785,
+      "grad_norm": 1.1995302438735962,
+      "learning_rate": 4.064961144185936e-07,
+      "loss": 0.2943,
+      "step": 910
+    },
+    {
+      "epoch": 2.8067484662576687,
+      "grad_norm": 1.1762601137161255,
+      "learning_rate": 3.499400310318035e-07,
+      "loss": 0.3385,
+      "step": 915
+    },
+    {
+      "epoch": 2.8220858895705523,
+      "grad_norm": 1.2636016607284546,
+      "learning_rate": 2.9757224378509305e-07,
+      "loss": 0.2657,
+      "step": 920
+    },
+    {
+      "epoch": 2.837423312883436,
+      "grad_norm": 1.172234058380127,
+      "learning_rate": 2.4940772407118286e-07,
+      "loss": 0.2943,
+      "step": 925
+    },
+    {
+      "epoch": 2.852760736196319,
+      "grad_norm": 1.1352618932724,
+      "learning_rate": 2.0546024161336773e-07,
+      "loss": 0.2752,
+      "step": 930
+    },
+    {
+      "epoch": 2.8680981595092025,
+      "grad_norm": 1.2794803380966187,
+      "learning_rate": 1.65742360528896e-07,
+      "loss": 0.3107,
+      "step": 935
+    },
+    {
+      "epoch": 2.883435582822086,
+      "grad_norm": 1.0951546430587769,
+      "learning_rate": 1.302654357370209e-07,
+      "loss": 0.2868,
+      "step": 940
+    },
+    {
+      "epoch": 2.8987730061349692,
+      "grad_norm": 1.2274115085601807,
+      "learning_rate": 9.903960971275883e-08,
+      "loss": 0.2569,
+      "step": 945
+    },
+    {
+      "epoch": 2.914110429447853,
+      "grad_norm": 1.1298874616622925,
+      "learning_rate": 7.207380958724918e-08,
+      "loss": 0.244,
+      "step": 950
+    },
+    {
+      "epoch": 2.9294478527607364,
+      "grad_norm": 1.103461503982544,
+      "learning_rate": 4.93757445955989e-08,
+      "loss": 0.2523,
+      "step": 955
+    },
+    {
+      "epoch": 2.9447852760736195,
+      "grad_norm": 1.1655006408691406,
+      "learning_rate": 3.095190387288227e-08,
+      "loss": 0.2497,
+      "step": 960
+    },
+    {
+      "epoch": 2.960122699386503,
+      "grad_norm": 1.27084219455719,
+      "learning_rate": 1.6807554598968212e-08,
+      "loss": 0.2777,
+      "step": 965
+    },
+    {
+      "epoch": 2.9754601226993866,
+      "grad_norm": 1.0959105491638184,
+      "learning_rate": 6.946740492698167e-09,
+      "loss": 0.2494,
+      "step": 970
+    },
+    {
+      "epoch": 2.9907975460122698,
+      "grad_norm": 1.117619276046753,
+      "learning_rate": 1.3722806558158495e-09,
+      "loss": 0.2814,
+      "step": 975
+    },
+    {
+      "epoch": 3.0,
+      "step": 978,
+      "total_flos": 1.4334566195296993e+18,
+      "train_loss": 0.5625010207752509,
+      "train_runtime": 674.2109,
+      "train_samples_per_second": 46.388,
+      "train_steps_per_second": 1.451
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 978,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4334566195296993e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

51_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8be1bad19fb5d96e31a495f0d87e20250028359375bfa31c2592a6dbad7e0c
+size 8145