Upload folder using huggingface_hub

31_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

31_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: 31_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. -->
+
+# 31_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

31_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": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "o_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

31_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49a084ed979d0e8ac6be18cc09eef089847a0821ef558303e9f243e7aca6a93b
+size 791751704

31_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2822802840284037e+18,
+    "train_loss": 0.5662356106465946,
+    "train_runtime": 642.1801,
+    "train_samples": 9861,
+    "train_samples_per_second": 46.067,
+    "train_steps_per_second": 1.444
+}

31_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
+}

31_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
+  }
+}

31_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
+}

31_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.2822802840284037e+18,
+    "train_loss": 0.5662356106465946,
+    "train_runtime": 642.1801,
+    "train_samples": 9861,
+    "train_samples_per_second": 46.067,
+    "train_steps_per_second": 1.444
+}

31_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1338 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 927,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01620745542949757,
+      "grad_norm": 1.2608121633529663,
+      "learning_rate": 2.553191489361702e-06,
+      "loss": 1.3583,
+      "step": 5
+    },
+    {
+      "epoch": 0.03241491085899514,
+      "grad_norm": 0.8590869903564453,
+      "learning_rate": 5.74468085106383e-06,
+      "loss": 1.3282,
+      "step": 10
+    },
+    {
+      "epoch": 0.04862236628849271,
+      "grad_norm": 0.9047601222991943,
+      "learning_rate": 8.936170212765958e-06,
+      "loss": 1.2847,
+      "step": 15
+    },
+    {
+      "epoch": 0.06482982171799027,
+      "grad_norm": 0.6455599665641785,
+      "learning_rate": 1.2127659574468084e-05,
+      "loss": 1.2918,
+      "step": 20
+    },
+    {
+      "epoch": 0.08103727714748785,
+      "grad_norm": 0.5892545580863953,
+      "learning_rate": 1.531914893617021e-05,
+      "loss": 1.2986,
+      "step": 25
+    },
+    {
+      "epoch": 0.09724473257698542,
+      "grad_norm": 0.6959712505340576,
+      "learning_rate": 1.8510638297872342e-05,
+      "loss": 1.2778,
+      "step": 30
+    },
+    {
+      "epoch": 0.11345218800648298,
+      "grad_norm": 0.49091899394989014,
+      "learning_rate": 2.170212765957447e-05,
+      "loss": 1.2691,
+      "step": 35
+    },
+    {
+      "epoch": 0.12965964343598055,
+      "grad_norm": 0.4507109224796295,
+      "learning_rate": 2.4893617021276595e-05,
+      "loss": 1.2281,
+      "step": 40
+    },
+    {
+      "epoch": 0.1458670988654781,
+      "grad_norm": 0.6016919016838074,
+      "learning_rate": 2.8085106382978723e-05,
+      "loss": 1.2404,
+      "step": 45
+    },
+    {
+      "epoch": 0.1620745542949757,
+      "grad_norm": 0.5189322233200073,
+      "learning_rate": 2.9999617656412492e-05,
+      "loss": 1.2311,
+      "step": 50
+    },
+    {
+      "epoch": 0.17828200972447325,
+      "grad_norm": 0.6017511487007141,
+      "learning_rate": 2.99953165148981e-05,
+      "loss": 1.1876,
+      "step": 55
+    },
+    {
+      "epoch": 0.19448946515397084,
+      "grad_norm": 0.47526559233665466,
+      "learning_rate": 2.9986237677350935e-05,
+      "loss": 1.1664,
+      "step": 60
+    },
+    {
+      "epoch": 0.2106969205834684,
+      "grad_norm": 0.5273451805114746,
+      "learning_rate": 2.997238403640259e-05,
+      "loss": 1.1455,
+      "step": 65
+    },
+    {
+      "epoch": 0.22690437601296595,
+      "grad_norm": 0.48251208662986755,
+      "learning_rate": 2.995376000599692e-05,
+      "loss": 1.1335,
+      "step": 70
+    },
+    {
+      "epoch": 0.24311183144246354,
+      "grad_norm": 0.6429893374443054,
+      "learning_rate": 2.9930371519983753e-05,
+      "loss": 1.1754,
+      "step": 75
+    },
+    {
+      "epoch": 0.2593192868719611,
+      "grad_norm": 0.5252504348754883,
+      "learning_rate": 2.9902226030228252e-05,
+      "loss": 1.0671,
+      "step": 80
+    },
+    {
+      "epoch": 0.2755267423014587,
+      "grad_norm": 0.570288360118866,
+      "learning_rate": 2.9869332504236687e-05,
+      "loss": 1.1081,
+      "step": 85
+    },
+    {
+      "epoch": 0.2917341977309562,
+      "grad_norm": 0.5421008467674255,
+      "learning_rate": 2.9831701422299244e-05,
+      "loss": 1.1029,
+      "step": 90
+    },
+    {
+      "epoch": 0.3079416531604538,
+      "grad_norm": 0.7204851508140564,
+      "learning_rate": 2.97893447741509e-05,
+      "loss": 1.1121,
+      "step": 95
+    },
+    {
+      "epoch": 0.3241491085899514,
+      "grad_norm": 0.643638551235199,
+      "learning_rate": 2.9742276055151334e-05,
+      "loss": 1.0857,
+      "step": 100
+    },
+    {
+      "epoch": 0.34035656401944897,
+      "grad_norm": 0.5737510919570923,
+      "learning_rate": 2.969051026198513e-05,
+      "loss": 1.0256,
+      "step": 105
+    },
+    {
+      "epoch": 0.3565640194489465,
+      "grad_norm": 0.7252358794212341,
+      "learning_rate": 2.9634063887883652e-05,
+      "loss": 1.0764,
+      "step": 110
+    },
+    {
+      "epoch": 0.3727714748784441,
+      "grad_norm": 0.6471376419067383,
+      "learning_rate": 2.9572954917370086e-05,
+      "loss": 1.0189,
+      "step": 115
+    },
+    {
+      "epoch": 0.3889789303079417,
+      "grad_norm": 0.8101359009742737,
+      "learning_rate": 2.950720282052936e-05,
+      "loss": 0.9578,
+      "step": 120
+    },
+    {
+      "epoch": 0.4051863857374392,
+      "grad_norm": 0.7164385318756104,
+      "learning_rate": 2.9436828546804707e-05,
+      "loss": 1.0043,
+      "step": 125
+    },
+    {
+      "epoch": 0.4213938411669368,
+      "grad_norm": 0.7544165253639221,
+      "learning_rate": 2.9361854518322945e-05,
+      "loss": 1.0499,
+      "step": 130
+    },
+    {
+      "epoch": 0.4376012965964344,
+      "grad_norm": 0.7659139037132263,
+      "learning_rate": 2.9282304622750468e-05,
+      "loss": 0.956,
+      "step": 135
+    },
+    {
+      "epoch": 0.4538087520259319,
+      "grad_norm": 0.697608470916748,
+      "learning_rate": 2.919820420568235e-05,
+      "loss": 0.9869,
+      "step": 140
+    },
+    {
+      "epoch": 0.4700162074554295,
+      "grad_norm": 0.7487397789955139,
+      "learning_rate": 2.910958006256693e-05,
+      "loss": 0.9049,
+      "step": 145
+    },
+    {
+      "epoch": 0.4862236628849271,
+      "grad_norm": 0.7782930731773376,
+      "learning_rate": 2.9016460430168447e-05,
+      "loss": 0.9487,
+      "step": 150
+    },
+    {
+      "epoch": 0.5024311183144247,
+      "grad_norm": 0.8702194094657898,
+      "learning_rate": 2.8918874977570422e-05,
+      "loss": 0.8916,
+      "step": 155
+    },
+    {
+      "epoch": 0.5186385737439222,
+      "grad_norm": 0.8503997921943665,
+      "learning_rate": 2.8816854796722754e-05,
+      "loss": 0.8707,
+      "step": 160
+    },
+    {
+      "epoch": 0.5348460291734197,
+      "grad_norm": 0.8497751355171204,
+      "learning_rate": 2.8710432392535413e-05,
+      "loss": 0.8659,
+      "step": 165
+    },
+    {
+      "epoch": 0.5510534846029174,
+      "grad_norm": 0.7617987394332886,
+      "learning_rate": 2.8599641672521973e-05,
+      "loss": 0.9452,
+      "step": 170
+    },
+    {
+      "epoch": 0.5672609400324149,
+      "grad_norm": 0.7082445621490479,
+      "learning_rate": 2.8484517935996257e-05,
+      "loss": 0.8795,
+      "step": 175
+    },
+    {
+      "epoch": 0.5834683954619124,
+      "grad_norm": 0.8376393914222717,
+      "learning_rate": 2.8365097862825516e-05,
+      "loss": 0.8895,
+      "step": 180
+    },
+    {
+      "epoch": 0.5996758508914101,
+      "grad_norm": 0.8631802201271057,
+      "learning_rate": 2.8241419501743797e-05,
+      "loss": 0.898,
+      "step": 185
+    },
+    {
+      "epoch": 0.6158833063209076,
+      "grad_norm": 0.9005579352378845,
+      "learning_rate": 2.8113522258229088e-05,
+      "loss": 0.8882,
+      "step": 190
+    },
+    {
+      "epoch": 0.6320907617504052,
+      "grad_norm": 0.9785137176513672,
+      "learning_rate": 2.798144688194829e-05,
+      "loss": 0.8547,
+      "step": 195
+    },
+    {
+      "epoch": 0.6482982171799028,
+      "grad_norm": 0.8441904187202454,
+      "learning_rate": 2.7845235453773837e-05,
+      "loss": 0.8251,
+      "step": 200
+    },
+    {
+      "epoch": 0.6645056726094003,
+      "grad_norm": 0.8505977988243103,
+      "learning_rate": 2.7704931372376183e-05,
+      "loss": 0.7619,
+      "step": 205
+    },
+    {
+      "epoch": 0.6807131280388979,
+      "grad_norm": 0.857123851776123,
+      "learning_rate": 2.756057934039649e-05,
+      "loss": 0.7795,
+      "step": 210
+    },
+    {
+      "epoch": 0.6969205834683955,
+      "grad_norm": 0.9974377751350403,
+      "learning_rate": 2.741222535020376e-05,
+      "loss": 0.7796,
+      "step": 215
+    },
+    {
+      "epoch": 0.713128038897893,
+      "grad_norm": 1.0163153409957886,
+      "learning_rate": 2.7259916669241104e-05,
+      "loss": 0.7878,
+      "step": 220
+    },
+    {
+      "epoch": 0.7293354943273906,
+      "grad_norm": 0.9492141604423523,
+      "learning_rate": 2.7103701824965756e-05,
+      "loss": 0.7938,
+      "step": 225
+    },
+    {
+      "epoch": 0.7455429497568882,
+      "grad_norm": 0.9435144066810608,
+      "learning_rate": 2.6943630589387598e-05,
+      "loss": 0.7918,
+      "step": 230
+    },
+    {
+      "epoch": 0.7617504051863857,
+      "grad_norm": 0.9193881750106812,
+      "learning_rate": 2.6779753963211172e-05,
+      "loss": 0.7876,
+      "step": 235
+    },
+    {
+      "epoch": 0.7779578606158833,
+      "grad_norm": 1.0289579629898071,
+      "learning_rate": 2.661212415958624e-05,
+      "loss": 0.7667,
+      "step": 240
+    },
+    {
+      "epoch": 0.7941653160453809,
+      "grad_norm": 0.8978919982910156,
+      "learning_rate": 2.6440794587471972e-05,
+      "loss": 0.7579,
+      "step": 245
+    },
+    {
+      "epoch": 0.8103727714748784,
+      "grad_norm": 0.9762867093086243,
+      "learning_rate": 2.6265819834620246e-05,
+      "loss": 0.7636,
+      "step": 250
+    },
+    {
+      "epoch": 0.826580226904376,
+      "grad_norm": 1.1456222534179688,
+      "learning_rate": 2.6087255650183243e-05,
+      "loss": 0.7309,
+      "step": 255
+    },
+    {
+      "epoch": 0.8427876823338736,
+      "grad_norm": 1.1659109592437744,
+      "learning_rate": 2.5905158926951108e-05,
+      "loss": 0.7486,
+      "step": 260
+    },
+    {
+      "epoch": 0.8589951377633711,
+      "grad_norm": 0.9701941013336182,
+      "learning_rate": 2.571958768322517e-05,
+      "loss": 0.7199,
+      "step": 265
+    },
+    {
+      "epoch": 0.8752025931928687,
+      "grad_norm": 0.9915440678596497,
+      "learning_rate": 2.5530601044332605e-05,
+      "loss": 0.7194,
+      "step": 270
+    },
+    {
+      "epoch": 0.8914100486223663,
+      "grad_norm": 0.988502562046051,
+      "learning_rate": 2.5338259223788343e-05,
+      "loss": 0.7336,
+      "step": 275
+    },
+    {
+      "epoch": 0.9076175040518638,
+      "grad_norm": 0.9917594790458679,
+      "learning_rate": 2.514262350411029e-05,
+      "loss": 0.6968,
+      "step": 280
+    },
+    {
+      "epoch": 0.9238249594813615,
+      "grad_norm": 1.0882996320724487,
+      "learning_rate": 2.4943756217293976e-05,
+      "loss": 0.6915,
+      "step": 285
+    },
+    {
+      "epoch": 0.940032414910859,
+      "grad_norm": 1.1328370571136475,
+      "learning_rate": 2.4741720724952754e-05,
+      "loss": 0.6391,
+      "step": 290
+    },
+    {
+      "epoch": 0.9562398703403565,
+      "grad_norm": 1.0500516891479492,
+      "learning_rate": 2.4536581398130032e-05,
+      "loss": 0.6852,
+      "step": 295
+    },
+    {
+      "epoch": 0.9724473257698542,
+      "grad_norm": 1.0785151720046997,
+      "learning_rate": 2.4328403596789833e-05,
+      "loss": 0.6592,
+      "step": 300
+    },
+    {
+      "epoch": 0.9886547811993517,
+      "grad_norm": 1.1277464628219604,
+      "learning_rate": 2.4117253648992292e-05,
+      "loss": 0.6382,
+      "step": 305
+    },
+    {
+      "epoch": 1.0032414910858996,
+      "grad_norm": 1.054197072982788,
+      "learning_rate": 2.3903198829760712e-05,
+      "loss": 0.6585,
+      "step": 310
+    },
+    {
+      "epoch": 1.019448946515397,
+      "grad_norm": 1.1577117443084717,
+      "learning_rate": 2.3686307339646883e-05,
+      "loss": 0.6093,
+      "step": 315
+    },
+    {
+      "epoch": 1.0356564019448946,
+      "grad_norm": 1.1010081768035889,
+      "learning_rate": 2.3466648283001542e-05,
+      "loss": 0.6015,
+      "step": 320
+    },
+    {
+      "epoch": 1.0518638573743921,
+      "grad_norm": 1.0694541931152344,
+      "learning_rate": 2.3244291645956852e-05,
+      "loss": 0.5543,
+      "step": 325
+    },
+    {
+      "epoch": 1.0680713128038897,
+      "grad_norm": 1.0830672979354858,
+      "learning_rate": 2.301930827412796e-05,
+      "loss": 0.5628,
+      "step": 330
+    },
+    {
+      "epoch": 1.0842787682333874,
+      "grad_norm": 1.3060392141342163,
+      "learning_rate": 2.279176985004066e-05,
+      "loss": 0.5275,
+      "step": 335
+    },
+    {
+      "epoch": 1.100486223662885,
+      "grad_norm": 1.045863151550293,
+      "learning_rate": 2.2561748870292478e-05,
+      "loss": 0.5537,
+      "step": 340
+    },
+    {
+      "epoch": 1.1166936790923825,
+      "grad_norm": 1.0819013118743896,
+      "learning_rate": 2.2329318622454327e-05,
+      "loss": 0.5711,
+      "step": 345
+    },
+    {
+      "epoch": 1.13290113452188,
+      "grad_norm": 1.1481125354766846,
+      "learning_rate": 2.2094553161720153e-05,
+      "loss": 0.5357,
+      "step": 350
+    },
+    {
+      "epoch": 1.1491085899513775,
+      "grad_norm": 1.190308690071106,
+      "learning_rate": 2.1857527287312067e-05,
+      "loss": 0.5331,
+      "step": 355
+    },
+    {
+      "epoch": 1.1653160453808753,
+      "grad_norm": 1.2032331228256226,
+      "learning_rate": 2.161831651864832e-05,
+      "loss": 0.5442,
+      "step": 360
+    },
+    {
+      "epoch": 1.1815235008103728,
+      "grad_norm": 1.1635992527008057,
+      "learning_rate": 2.1376997071281902e-05,
+      "loss": 0.557,
+      "step": 365
+    },
+    {
+      "epoch": 1.1977309562398704,
+      "grad_norm": 1.2854974269866943,
+      "learning_rate": 2.1133645832617304e-05,
+      "loss": 0.5783,
+      "step": 370
+    },
+    {
+      "epoch": 1.213938411669368,
+      "grad_norm": 1.222918152809143,
+      "learning_rate": 2.0888340337413217e-05,
+      "loss": 0.4875,
+      "step": 375
+    },
+    {
+      "epoch": 1.2301458670988654,
+      "grad_norm": 1.2602648735046387,
+      "learning_rate": 2.0641158743078996e-05,
+      "loss": 0.5379,
+      "step": 380
+    },
+    {
+      "epoch": 1.246353322528363,
+      "grad_norm": 1.3083213567733765,
+      "learning_rate": 2.039217980477273e-05,
+      "loss": 0.5613,
+      "step": 385
+    },
+    {
+      "epoch": 1.2625607779578605,
+      "grad_norm": 1.1991331577301025,
+      "learning_rate": 2.014148285030884e-05,
+      "loss": 0.4901,
+      "step": 390
+    },
+    {
+      "epoch": 1.2787682333873582,
+      "grad_norm": 1.2222563028335571,
+      "learning_rate": 1.9889147754883265e-05,
+      "loss": 0.5288,
+      "step": 395
+    },
+    {
+      "epoch": 1.2949756888168558,
+      "grad_norm": 1.297658085823059,
+      "learning_rate": 1.963525491562421e-05,
+      "loss": 0.4812,
+      "step": 400
+    },
+    {
+      "epoch": 1.3111831442463533,
+      "grad_norm": 1.170430302619934,
+      "learning_rate": 1.9379885225976623e-05,
+      "loss": 0.492,
+      "step": 405
+    },
+    {
+      "epoch": 1.3273905996758508,
+      "grad_norm": 1.1340793371200562,
+      "learning_rate": 1.9123120049928507e-05,
+      "loss": 0.4788,
+      "step": 410
+    },
+    {
+      "epoch": 1.3435980551053484,
+      "grad_norm": 1.12411367893219,
+      "learning_rate": 1.8865041196087357e-05,
+      "loss": 0.5189,
+      "step": 415
+    },
+    {
+      "epoch": 1.359805510534846,
+      "grad_norm": 1.1650874614715576,
+      "learning_rate": 1.8605730891614886e-05,
+      "loss": 0.5101,
+      "step": 420
+    },
+    {
+      "epoch": 1.3760129659643436,
+      "grad_norm": 1.2535614967346191,
+      "learning_rate": 1.8345271756028452e-05,
+      "loss": 0.5172,
+      "step": 425
+    },
+    {
+      "epoch": 1.3922204213938412,
+      "grad_norm": 1.2112749814987183,
+      "learning_rate": 1.808374677487741e-05,
+      "loss": 0.5385,
+      "step": 430
+    },
+    {
+      "epoch": 1.4084278768233387,
+      "grad_norm": 1.2398228645324707,
+      "learning_rate": 1.7821239273302886e-05,
+      "loss": 0.4951,
+      "step": 435
+    },
+    {
+      "epoch": 1.4246353322528362,
+      "grad_norm": 1.1920042037963867,
+      "learning_rate": 1.755783288948936e-05,
+      "loss": 0.5153,
+      "step": 440
+    },
+    {
+      "epoch": 1.440842787682334,
+      "grad_norm": 1.2706419229507446,
+      "learning_rate": 1.7293611548016453e-05,
+      "loss": 0.4718,
+      "step": 445
+    },
+    {
+      "epoch": 1.4570502431118315,
+      "grad_norm": 1.3067541122436523,
+      "learning_rate": 1.7028659433119533e-05,
+      "loss": 0.4412,
+      "step": 450
+    },
+    {
+      "epoch": 1.473257698541329,
+      "grad_norm": 1.2596648931503296,
+      "learning_rate": 1.6763060961867568e-05,
+      "loss": 0.468,
+      "step": 455
+    },
+    {
+      "epoch": 1.4894651539708266,
+      "grad_norm": 1.2401411533355713,
+      "learning_rate": 1.649690075726674e-05,
+      "loss": 0.4822,
+      "step": 460
+    },
+    {
+      "epoch": 1.505672609400324,
+      "grad_norm": 1.4504960775375366,
+      "learning_rate": 1.623026362129856e-05,
+      "loss": 0.4034,
+      "step": 465
+    },
+    {
+      "epoch": 1.5218800648298219,
+      "grad_norm": 1.1868679523468018,
+      "learning_rate": 1.5963234507900826e-05,
+      "loss": 0.4302,
+      "step": 470
+    },
+    {
+      "epoch": 1.5380875202593192,
+      "grad_norm": 1.3226382732391357,
+      "learning_rate": 1.5695898495900295e-05,
+      "loss": 0.4641,
+      "step": 475
+    },
+    {
+      "epoch": 1.554294975688817,
+      "grad_norm": 1.2887495756149292,
+      "learning_rate": 1.5428340761905444e-05,
+      "loss": 0.4247,
+      "step": 480
+    },
+    {
+      "epoch": 1.5705024311183144,
+      "grad_norm": 1.3862051963806152,
+      "learning_rate": 1.5160646553168181e-05,
+      "loss": 0.4512,
+      "step": 485
+    },
+    {
+      "epoch": 1.586709886547812,
+      "grad_norm": 1.267487645149231,
+      "learning_rate": 1.4892901160422958e-05,
+      "loss": 0.4766,
+      "step": 490
+    },
+    {
+      "epoch": 1.6029173419773097,
+      "grad_norm": 1.2538328170776367,
+      "learning_rate": 1.4625189890712122e-05,
+      "loss": 0.4546,
+      "step": 495
+    },
+    {
+      "epoch": 1.619124797406807,
+      "grad_norm": 1.098090410232544,
+      "learning_rate": 1.4357598040205965e-05,
+      "loss": 0.3877,
+      "step": 500
+    },
+    {
+      "epoch": 1.6353322528363048,
+      "grad_norm": 1.1650983095169067,
+      "learning_rate": 1.409021086702634e-05,
+      "loss": 0.4895,
+      "step": 505
+    },
+    {
+      "epoch": 1.6515397082658023,
+      "grad_norm": 1.2536464929580688,
+      "learning_rate": 1.3823113564082329e-05,
+      "loss": 0.4098,
+      "step": 510
+    },
+    {
+      "epoch": 1.6677471636952999,
+      "grad_norm": 1.3373360633850098,
+      "learning_rate": 1.3556391231926716e-05,
+      "loss": 0.3807,
+      "step": 515
+    },
+    {
+      "epoch": 1.6839546191247974,
+      "grad_norm": 1.3934822082519531,
+      "learning_rate": 1.3290128851641892e-05,
+      "loss": 0.427,
+      "step": 520
+    },
+    {
+      "epoch": 1.700162074554295,
+      "grad_norm": 1.4924999475479126,
+      "learning_rate": 1.3024411257763808e-05,
+      "loss": 0.4081,
+      "step": 525
+    },
+    {
+      "epoch": 1.7163695299837927,
+      "grad_norm": 1.3756160736083984,
+      "learning_rate": 1.2759323111252624e-05,
+      "loss": 0.3941,
+      "step": 530
+    },
+    {
+      "epoch": 1.73257698541329,
+      "grad_norm": 1.1852853298187256,
+      "learning_rate": 1.2494948872518675e-05,
+      "loss": 0.3849,
+      "step": 535
+    },
+    {
+      "epoch": 1.7487844408427877,
+      "grad_norm": 1.408382773399353,
+      "learning_rate": 1.223137277451232e-05,
+      "loss": 0.434,
+      "step": 540
+    },
+    {
+      "epoch": 1.7649918962722853,
+      "grad_norm": 1.2881886959075928,
+      "learning_rate": 1.1968678795886258e-05,
+      "loss": 0.4408,
+      "step": 545
+    },
+    {
+      "epoch": 1.7811993517017828,
+      "grad_norm": 1.400038719177246,
+      "learning_rate": 1.1706950634238887e-05,
+      "loss": 0.3718,
+      "step": 550
+    },
+    {
+      "epoch": 1.7974068071312805,
+      "grad_norm": 1.3220003843307495,
+      "learning_rate": 1.1446271679447194e-05,
+      "loss": 0.3764,
+      "step": 555
+    },
+    {
+      "epoch": 1.8136142625607778,
+      "grad_norm": 1.2493178844451904,
+      "learning_rate": 1.11867249870977e-05,
+      "loss": 0.3972,
+      "step": 560
+    },
+    {
+      "epoch": 1.8298217179902756,
+      "grad_norm": 1.4055944681167603,
+      "learning_rate": 1.0928393252023887e-05,
+      "loss": 0.3832,
+      "step": 565
+    },
+    {
+      "epoch": 1.8460291734197731,
+      "grad_norm": 1.1597641706466675,
+      "learning_rate": 1.0671358781958624e-05,
+      "loss": 0.3963,
+      "step": 570
+    },
+    {
+      "epoch": 1.8622366288492707,
+      "grad_norm": 1.2812806367874146,
+      "learning_rate": 1.041570347130984e-05,
+      "loss": 0.3829,
+      "step": 575
+    },
+    {
+      "epoch": 1.8784440842787682,
+      "grad_norm": 1.271889567375183,
+      "learning_rate": 1.0161508775067994e-05,
+      "loss": 0.4195,
+      "step": 580
+    },
+    {
+      "epoch": 1.8946515397082657,
+      "grad_norm": 1.4789602756500244,
+      "learning_rate": 9.908855682853442e-06,
+      "loss": 0.3408,
+      "step": 585
+    },
+    {
+      "epoch": 1.9108589951377635,
+      "grad_norm": 1.3204796314239502,
+      "learning_rate": 9.65782469311216e-06,
+      "loss": 0.3652,
+      "step": 590
+    },
+    {
+      "epoch": 1.9270664505672608,
+      "grad_norm": 1.1117668151855469,
+      "learning_rate": 9.408495787467918e-06,
+      "loss": 0.4064,
+      "step": 595
+    },
+    {
+      "epoch": 1.9432739059967585,
+      "grad_norm": 1.317980408668518,
+      "learning_rate": 9.16094840523913e-06,
+      "loss": 0.3637,
+      "step": 600
+    },
+    {
+      "epoch": 1.959481361426256,
+      "grad_norm": 1.2342796325683594,
+      "learning_rate": 8.915261418128491e-06,
+      "loss": 0.3763,
+      "step": 605
+    },
+    {
+      "epoch": 1.9756888168557536,
+      "grad_norm": 1.2812680006027222,
+      "learning_rate": 8.671513105093462e-06,
+      "loss": 0.3602,
+      "step": 610
+    },
+    {
+      "epoch": 1.9918962722852513,
+      "grad_norm": 1.6511602401733398,
+      "learning_rate": 8.429781127405627e-06,
+      "loss": 0.3484,
+      "step": 615
+    },
+    {
+      "epoch": 2.006482982171799,
+      "grad_norm": 1.2281585931777954,
+      "learning_rate": 8.190142503906798e-06,
+      "loss": 0.3691,
+      "step": 620
+    },
+    {
+      "epoch": 2.0226904376012964,
+      "grad_norm": 1.4553028345108032,
+      "learning_rate": 7.952673586469894e-06,
+      "loss": 0.3327,
+      "step": 625
+    },
+    {
+      "epoch": 2.038897893030794,
+      "grad_norm": 1.2474943399429321,
+      "learning_rate": 7.717450035672237e-06,
+      "loss": 0.2909,
+      "step": 630
+    },
+    {
+      "epoch": 2.055105348460292,
+      "grad_norm": 1.3365769386291504,
+      "learning_rate": 7.484546796689177e-06,
+      "loss": 0.2966,
+      "step": 635
+    },
+    {
+      "epoch": 2.0713128038897892,
+      "grad_norm": 1.216200590133667,
+      "learning_rate": 7.254038075415573e-06,
+      "loss": 0.278,
+      "step": 640
+    },
+    {
+      "epoch": 2.087520259319287,
+      "grad_norm": 1.16641104221344,
+      "learning_rate": 7.025997314822913e-06,
+      "loss": 0.2723,
+      "step": 645
+    },
+    {
+      "epoch": 2.1037277147487843,
+      "grad_norm": 1.3077505826950073,
+      "learning_rate": 6.800497171559433e-06,
+      "loss": 0.2876,
+      "step": 650
+    },
+    {
+      "epoch": 2.119935170178282,
+      "grad_norm": 1.3633626699447632,
+      "learning_rate": 6.577609492800798e-06,
+      "loss": 0.3271,
+      "step": 655
+    },
+    {
+      "epoch": 2.1361426256077793,
+      "grad_norm": 1.3778159618377686,
+      "learning_rate": 6.357405293358708e-06,
+      "loss": 0.2982,
+      "step": 660
+    },
+    {
+      "epoch": 2.152350081037277,
+      "grad_norm": 1.328687310218811,
+      "learning_rate": 6.139954733054656e-06,
+      "loss": 0.3158,
+      "step": 665
+    },
+    {
+      "epoch": 2.168557536466775,
+      "grad_norm": 1.342050552368164,
+      "learning_rate": 5.925327094366163e-06,
+      "loss": 0.2897,
+      "step": 670
+    },
+    {
+      "epoch": 2.184764991896272,
+      "grad_norm": 1.3360869884490967,
+      "learning_rate": 5.713590760352489e-06,
+      "loss": 0.3044,
+      "step": 675
+    },
+    {
+      "epoch": 2.20097244732577,
+      "grad_norm": 1.5091679096221924,
+      "learning_rate": 5.504813192866946e-06,
+      "loss": 0.2552,
+      "step": 680
+    },
+    {
+      "epoch": 2.217179902755267,
+      "grad_norm": 1.3954471349716187,
+      "learning_rate": 5.299060911062685e-06,
+      "loss": 0.2868,
+      "step": 685
+    },
+    {
+      "epoch": 2.233387358184765,
+      "grad_norm": 1.2861418724060059,
+      "learning_rate": 5.096399470198883e-06,
+      "loss": 0.3283,
+      "step": 690
+    },
+    {
+      "epoch": 2.2495948136142627,
+      "grad_norm": 1.3335310220718384,
+      "learning_rate": 4.8968934407539885e-06,
+      "loss": 0.2807,
+      "step": 695
+    },
+    {
+      "epoch": 2.26580226904376,
+      "grad_norm": 1.175858736038208,
+      "learning_rate": 4.700606387852796e-06,
+      "loss": 0.2695,
+      "step": 700
+    },
+    {
+      "epoch": 2.282009724473258,
+      "grad_norm": 1.2836474180221558,
+      "learning_rate": 4.507600851013758e-06,
+      "loss": 0.284,
+      "step": 705
+    },
+    {
+      "epoch": 2.298217179902755,
+      "grad_norm": 1.2776073217391968,
+      "learning_rate": 4.317938324223125e-06,
+      "loss": 0.287,
+      "step": 710
+    },
+    {
+      "epoch": 2.314424635332253,
+      "grad_norm": 1.3337186574935913,
+      "learning_rate": 4.131679236342198e-06,
+      "loss": 0.2907,
+      "step": 715
+    },
+    {
+      "epoch": 2.3306320907617506,
+      "grad_norm": 1.1861037015914917,
+      "learning_rate": 3.948882931853924e-06,
+      "loss": 0.2697,
+      "step": 720
+    },
+    {
+      "epoch": 2.346839546191248,
+      "grad_norm": 1.4212161302566528,
+      "learning_rate": 3.769607651955015e-06,
+      "loss": 0.2722,
+      "step": 725
+    },
+    {
+      "epoch": 2.3630470016207457,
+      "grad_norm": 1.3712878227233887,
+      "learning_rate": 3.5939105159995363e-06,
+      "loss": 0.3016,
+      "step": 730
+    },
+    {
+      "epoch": 2.379254457050243,
+      "grad_norm": 1.208249807357788,
+      "learning_rate": 3.4218475033000102e-06,
+      "loss": 0.3004,
+      "step": 735
+    },
+    {
+      "epoch": 2.3954619124797407,
+      "grad_norm": 1.204421877861023,
+      "learning_rate": 3.2534734352916683e-06,
+      "loss": 0.3131,
+      "step": 740
+    },
+    {
+      "epoch": 2.411669367909238,
+      "grad_norm": 1.1377441883087158,
+      "learning_rate": 3.0888419580656784e-06,
+      "loss": 0.2993,
+      "step": 745
+    },
+    {
+      "epoch": 2.427876823338736,
+      "grad_norm": 1.6020410060882568,
+      "learning_rate": 2.9280055252768e-06,
+      "loss": 0.2896,
+      "step": 750
+    },
+    {
+      "epoch": 2.4440842787682335,
+      "grad_norm": 1.356314778327942,
+      "learning_rate": 2.7710153814310187e-06,
+      "loss": 0.281,
+      "step": 755
+    },
+    {
+      "epoch": 2.460291734197731,
+      "grad_norm": 1.3577505350112915,
+      "learning_rate": 2.61792154555839e-06,
+      "loss": 0.2701,
+      "step": 760
+    },
+    {
+      "epoch": 2.4764991896272286,
+      "grad_norm": 1.146355390548706,
+      "learning_rate": 2.4687727952763497e-06,
+      "loss": 0.3054,
+      "step": 765
+    },
+    {
+      "epoch": 2.492706645056726,
+      "grad_norm": 1.246884822845459,
+      "learning_rate": 2.3236166512485563e-06,
+      "loss": 0.2978,
+      "step": 770
+    },
+    {
+      "epoch": 2.5089141004862237,
+      "grad_norm": 1.2138808965682983,
+      "learning_rate": 2.1824993620441997e-06,
+      "loss": 0.279,
+      "step": 775
+    },
+    {
+      "epoch": 2.525121555915721,
+      "grad_norm": 1.2127461433410645,
+      "learning_rate": 2.0454658894026447e-06,
+      "loss": 0.2565,
+      "step": 780
+    },
+    {
+      "epoch": 2.5413290113452187,
+      "grad_norm": 1.321583867073059,
+      "learning_rate": 1.9125598939080424e-06,
+      "loss": 0.272,
+      "step": 785
+    },
+    {
+      "epoch": 2.5575364667747165,
+      "grad_norm": 1.2404441833496094,
+      "learning_rate": 1.783823721078532e-06,
+      "loss": 0.2947,
+      "step": 790
+    },
+    {
+      "epoch": 2.5737439222042138,
+      "grad_norm": 1.3019307851791382,
+      "learning_rate": 1.659298387874408e-06,
+      "loss": 0.3128,
+      "step": 795
+    },
+    {
+      "epoch": 2.5899513776337115,
+      "grad_norm": 1.2681828737258911,
+      "learning_rate": 1.5390235696296268e-06,
+      "loss": 0.2688,
+      "step": 800
+    },
+    {
+      "epoch": 2.6061588330632093,
+      "grad_norm": 1.3946645259857178,
+      "learning_rate": 1.423037587410722e-06,
+      "loss": 0.29,
+      "step": 805
+    },
+    {
+      "epoch": 2.6223662884927066,
+      "grad_norm": 1.2748512029647827,
+      "learning_rate": 1.3113773958072606e-06,
+      "loss": 0.249,
+      "step": 810
+    },
+    {
+      "epoch": 2.6385737439222043,
+      "grad_norm": 1.1915643215179443,
+      "learning_rate": 1.2040785711576192e-06,
+      "loss": 0.2561,
+      "step": 815
+    },
+    {
+      "epoch": 2.6547811993517016,
+      "grad_norm": 1.3371423482894897,
+      "learning_rate": 1.1011753002139285e-06,
+      "loss": 0.3168,
+      "step": 820
+    },
+    {
+      "epoch": 2.6709886547811994,
+      "grad_norm": 1.2416796684265137,
+      "learning_rate": 1.0027003692497482e-06,
+      "loss": 0.2604,
+      "step": 825
+    },
+    {
+      "epoch": 2.6871961102106967,
+      "grad_norm": 1.0988385677337646,
+      "learning_rate": 9.086851536139423e-07,
+      "loss": 0.2639,
+      "step": 830
+    },
+    {
+      "epoch": 2.7034035656401945,
+      "grad_norm": 1.2113264799118042,
+      "learning_rate": 8.191596077341057e-07,
+      "loss": 0.2896,
+      "step": 835
+    },
+    {
+      "epoch": 2.719611021069692,
+      "grad_norm": 1.2403887510299683,
+      "learning_rate": 7.341522555726971e-07,
+      "loss": 0.3118,
+      "step": 840
+    },
+    {
+      "epoch": 2.7358184764991895,
+      "grad_norm": 1.1255820989608765,
+      "learning_rate": 6.536901815389567e-07,
+      "loss": 0.2958,
+      "step": 845
+    },
+    {
+      "epoch": 2.7520259319286873,
+      "grad_norm": 1.3676382303237915,
+      "learning_rate": 5.77799021859473e-07,
+      "loss": 0.2645,
+      "step": 850
+    },
+    {
+      "epoch": 2.768233387358185,
+      "grad_norm": 1.2115435600280762,
+      "learning_rate": 5.065029564101542e-07,
+      "loss": 0.2926,
+      "step": 855
+    },
+    {
+      "epoch": 2.7844408427876823,
+      "grad_norm": 1.1631747484207153,
+      "learning_rate": 4.398247010122125e-07,
+      "loss": 0.2846,
+      "step": 860
+    },
+    {
+      "epoch": 2.8006482982171796,
+      "grad_norm": 1.309217095375061,
+      "learning_rate": 3.7778550019463396e-07,
+      "loss": 0.2639,
+      "step": 865
+    },
+    {
+      "epoch": 2.8168557536466774,
+      "grad_norm": 1.1608315706253052,
+      "learning_rate": 3.204051204253877e-07,
+      "loss": 0.2494,
+      "step": 870
+    },
+    {
+      "epoch": 2.833063209076175,
+      "grad_norm": 1.3217846155166626,
+      "learning_rate": 2.6770184381359363e-07,
+      "loss": 0.2643,
+      "step": 875
+    },
+    {
+      "epoch": 2.8492706645056725,
+      "grad_norm": 1.3208414316177368,
+      "learning_rate": 2.1969246228460526e-07,
+      "loss": 0.278,
+      "step": 880
+    },
+    {
+      "epoch": 2.86547811993517,
+      "grad_norm": 1.2435957193374634,
+      "learning_rate": 1.763922722298944e-07,
+      "loss": 0.2405,
+      "step": 885
+    },
+    {
+      "epoch": 2.881685575364668,
+      "grad_norm": 1.2140178680419922,
+      "learning_rate": 1.3781506963343125e-07,
+      "loss": 0.2518,
+      "step": 890
+    },
+    {
+      "epoch": 2.8978930307941653,
+      "grad_norm": 1.3278192281723022,
+      "learning_rate": 1.0397314567610561e-07,
+      "loss": 0.2922,
+      "step": 895
+    },
+    {
+      "epoch": 2.914100486223663,
+      "grad_norm": 1.1252845525741577,
+      "learning_rate": 7.487728281960593e-08,
+      "loss": 0.2589,
+      "step": 900
+    },
+    {
+      "epoch": 2.9303079416531603,
+      "grad_norm": 1.1713452339172363,
+      "learning_rate": 5.0536751370992564e-08,
+      "loss": 0.2883,
+      "step": 905
+    },
+    {
+      "epoch": 2.946515397082658,
+      "grad_norm": 1.311859369277954,
+      "learning_rate": 3.095930652905699e-08,
+      "loss": 0.2789,
+      "step": 910
+    },
+    {
+      "epoch": 2.9627228525121554,
+      "grad_norm": 1.4269510507583618,
+      "learning_rate": 1.615118591342335e-08,
+      "loss": 0.2545,
+      "step": 915
+    },
+    {
+      "epoch": 2.978930307941653,
+      "grad_norm": 1.2540826797485352,
+      "learning_rate": 6.117107577161551e-09,
+      "loss": 0.2729,
+      "step": 920
+    },
+    {
+      "epoch": 2.995137763371151,
+      "grad_norm": 1.3862510919570923,
+      "learning_rate": 8.602685035563607e-10,
+      "loss": 0.2469,
+      "step": 925
+    },
+    {
+      "epoch": 3.0,
+      "step": 927,
+      "total_flos": 1.2822802840284037e+18,
+      "train_loss": 0.5662356106465946,
+      "train_runtime": 642.1801,
+      "train_samples_per_second": 46.067,
+      "train_steps_per_second": 1.444
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 927,
+  "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": 1.2822802840284037e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

31_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:521b91b59d2a915be1f4915b7502646d59fb4e3d57bfb4cd8e9f2b8311a2aa98
+size 8145