Upload folder using huggingface_hub

11_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

11_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: 11_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. -->
+
+# 11_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

11_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": [
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

11_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9276eb24715257069fd5bd1e38663223d9f24a83f4848cb2d3b18868bc5516b9
+size 791751704

11_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.6551636736996803e+18,
+    "train_loss": 0.5368774858438913,
+    "train_runtime": 778.027,
+    "train_samples": 11340,
+    "train_samples_per_second": 43.726,
+    "train_steps_per_second": 1.369
+}

11_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
+}

11_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
+  }
+}

11_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
+}

11_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.6551636736996803e+18,
+    "train_loss": 0.5368774858438913,
+    "train_runtime": 778.027,
+    "train_samples": 11340,
+    "train_samples_per_second": 43.726,
+    "train_steps_per_second": 1.369
+}

11_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1065,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014104372355430184,
+      "grad_norm": 1.0637387037277222,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.3069,
+      "step": 5
+    },
+    {
+      "epoch": 0.028208744710860368,
+      "grad_norm": 0.8158851861953735,
+      "learning_rate": 4.9999999999999996e-06,
+      "loss": 1.2549,
+      "step": 10
+    },
+    {
+      "epoch": 0.04231311706629055,
+      "grad_norm": 0.6005497574806213,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 1.3247,
+      "step": 15
+    },
+    {
+      "epoch": 0.056417489421720736,
+      "grad_norm": 0.5396072268486023,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 1.1989,
+      "step": 20
+    },
+    {
+      "epoch": 0.07052186177715092,
+      "grad_norm": 0.490671843290329,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 1.1646,
+      "step": 25
+    },
+    {
+      "epoch": 0.0846262341325811,
+      "grad_norm": 0.5251336693763733,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 1.1628,
+      "step": 30
+    },
+    {
+      "epoch": 0.09873060648801128,
+      "grad_norm": 0.4558011293411255,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 1.14,
+      "step": 35
+    },
+    {
+      "epoch": 0.11283497884344147,
+      "grad_norm": 0.47032037377357483,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 1.1684,
+      "step": 40
+    },
+    {
+      "epoch": 0.12693935119887165,
+      "grad_norm": 0.4130344092845917,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 1.1429,
+      "step": 45
+    },
+    {
+      "epoch": 0.14104372355430184,
+      "grad_norm": 0.4210389256477356,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 1.128,
+      "step": 50
+    },
+    {
+      "epoch": 0.15514809590973203,
+      "grad_norm": 0.4607349634170532,
+      "learning_rate": 3e-05,
+      "loss": 1.0764,
+      "step": 55
+    },
+    {
+      "epoch": 0.1692524682651622,
+      "grad_norm": 0.5495645999908447,
+      "learning_rate": 2.999818953568259e-05,
+      "loss": 1.1115,
+      "step": 60
+    },
+    {
+      "epoch": 0.18335684062059238,
+      "grad_norm": 0.4598657488822937,
+      "learning_rate": 2.9992758579767835e-05,
+      "loss": 1.0923,
+      "step": 65
+    },
+    {
+      "epoch": 0.19746121297602257,
+      "grad_norm": 0.5236585140228271,
+      "learning_rate": 2.9983708443262656e-05,
+      "loss": 1.1037,
+      "step": 70
+    },
+    {
+      "epoch": 0.21156558533145275,
+      "grad_norm": 0.4360106289386749,
+      "learning_rate": 2.9971041310826943e-05,
+      "loss": 1.0932,
+      "step": 75
+    },
+    {
+      "epoch": 0.22566995768688294,
+      "grad_norm": 0.48803409934043884,
+      "learning_rate": 2.99547602402462e-05,
+      "loss": 1.0744,
+      "step": 80
+    },
+    {
+      "epoch": 0.2397743300423131,
+      "grad_norm": 0.5093035697937012,
+      "learning_rate": 2.993486916169341e-05,
+      "loss": 1.0131,
+      "step": 85
+    },
+    {
+      "epoch": 0.2538787023977433,
+      "grad_norm": 0.4685842990875244,
+      "learning_rate": 2.9911372876780297e-05,
+      "loss": 1.0318,
+      "step": 90
+    },
+    {
+      "epoch": 0.2679830747531735,
+      "grad_norm": 0.4982532858848572,
+      "learning_rate": 2.988427705739825e-05,
+      "loss": 1.0393,
+      "step": 95
+    },
+    {
+      "epoch": 0.2820874471086037,
+      "grad_norm": 0.5553637742996216,
+      "learning_rate": 2.985358824434916e-05,
+      "loss": 1.0019,
+      "step": 100
+    },
+    {
+      "epoch": 0.29619181946403383,
+      "grad_norm": 0.612057626247406,
+      "learning_rate": 2.9819313845766484e-05,
+      "loss": 0.961,
+      "step": 105
+    },
+    {
+      "epoch": 0.31029619181946405,
+      "grad_norm": 0.5543063879013062,
+      "learning_rate": 2.978146213532697e-05,
+      "loss": 0.9992,
+      "step": 110
+    },
+    {
+      "epoch": 0.3244005641748942,
+      "grad_norm": 0.521835446357727,
+      "learning_rate": 2.9740042250253443e-05,
+      "loss": 1.006,
+      "step": 115
+    },
+    {
+      "epoch": 0.3385049365303244,
+      "grad_norm": 0.5960680842399597,
+      "learning_rate": 2.969506418910909e-05,
+      "loss": 0.9591,
+      "step": 120
+    },
+    {
+      "epoch": 0.3526093088857546,
+      "grad_norm": 0.5530820488929749,
+      "learning_rate": 2.9646538809383876e-05,
+      "loss": 0.9707,
+      "step": 125
+    },
+    {
+      "epoch": 0.36671368124118475,
+      "grad_norm": 0.6507030725479126,
+      "learning_rate": 2.959447782487361e-05,
+      "loss": 0.9596,
+      "step": 130
+    },
+    {
+      "epoch": 0.38081805359661497,
+      "grad_norm": 0.5503715872764587,
+      "learning_rate": 2.9538893802852254e-05,
+      "loss": 0.9001,
+      "step": 135
+    },
+    {
+      "epoch": 0.39492242595204513,
+      "grad_norm": 0.6081051826477051,
+      "learning_rate": 2.947980016103828e-05,
+      "loss": 0.9459,
+      "step": 140
+    },
+    {
+      "epoch": 0.4090267983074753,
+      "grad_norm": 0.5859440565109253,
+      "learning_rate": 2.9417211164355668e-05,
+      "loss": 0.973,
+      "step": 145
+    },
+    {
+      "epoch": 0.4231311706629055,
+      "grad_norm": 0.7161879539489746,
+      "learning_rate": 2.9351141921490436e-05,
+      "loss": 0.9505,
+      "step": 150
+    },
+    {
+      "epoch": 0.43723554301833567,
+      "grad_norm": 0.6699029803276062,
+      "learning_rate": 2.9281608381243485e-05,
+      "loss": 0.8382,
+      "step": 155
+    },
+    {
+      "epoch": 0.4513399153737659,
+      "grad_norm": 0.7366487979888916,
+      "learning_rate": 2.92086273286806e-05,
+      "loss": 0.8906,
+      "step": 160
+    },
+    {
+      "epoch": 0.46544428772919605,
+      "grad_norm": 0.7281913757324219,
+      "learning_rate": 2.9132216381080664e-05,
+      "loss": 0.85,
+      "step": 165
+    },
+    {
+      "epoch": 0.4795486600846262,
+      "grad_norm": 0.7109456062316895,
+      "learning_rate": 2.9052393983682876e-05,
+      "loss": 0.8731,
+      "step": 170
+    },
+    {
+      "epoch": 0.4936530324400564,
+      "grad_norm": 0.6839827299118042,
+      "learning_rate": 2.8969179405234202e-05,
+      "loss": 0.8767,
+      "step": 175
+    },
+    {
+      "epoch": 0.5077574047954866,
+      "grad_norm": 0.7410655617713928,
+      "learning_rate": 2.888259273333798e-05,
+      "loss": 0.9017,
+      "step": 180
+    },
+    {
+      "epoch": 0.5218617771509168,
+      "grad_norm": 0.7175915837287903,
+      "learning_rate": 2.8792654869604844e-05,
+      "loss": 0.8676,
+      "step": 185
+    },
+    {
+      "epoch": 0.535966149506347,
+      "grad_norm": 0.8601197004318237,
+      "learning_rate": 2.8699387524607206e-05,
+      "loss": 0.8909,
+      "step": 190
+    },
+    {
+      "epoch": 0.5500705218617772,
+      "grad_norm": 0.9511786699295044,
+      "learning_rate": 2.8602813212638415e-05,
+      "loss": 0.8254,
+      "step": 195
+    },
+    {
+      "epoch": 0.5641748942172073,
+      "grad_norm": 0.6891305446624756,
+      "learning_rate": 2.8502955246277904e-05,
+      "loss": 0.8098,
+      "step": 200
+    },
+    {
+      "epoch": 0.5782792665726375,
+      "grad_norm": 0.8119242191314697,
+      "learning_rate": 2.839983773076367e-05,
+      "loss": 0.8738,
+      "step": 205
+    },
+    {
+      "epoch": 0.5923836389280677,
+      "grad_norm": 0.7489730715751648,
+      "learning_rate": 2.8293485558173352e-05,
+      "loss": 0.8235,
+      "step": 210
+    },
+    {
+      "epoch": 0.6064880112834978,
+      "grad_norm": 0.837908923625946,
+      "learning_rate": 2.8183924401415424e-05,
+      "loss": 0.7688,
+      "step": 215
+    },
+    {
+      "epoch": 0.6205923836389281,
+      "grad_norm": 0.8816768527030945,
+      "learning_rate": 2.8071180708031874e-05,
+      "loss": 0.8027,
+      "step": 220
+    },
+    {
+      "epoch": 0.6346967559943583,
+      "grad_norm": 0.7762036323547363,
+      "learning_rate": 2.7955281693813884e-05,
+      "loss": 0.7851,
+      "step": 225
+    },
+    {
+      "epoch": 0.6488011283497884,
+      "grad_norm": 0.8296380043029785,
+      "learning_rate": 2.7836255336232076e-05,
+      "loss": 0.8324,
+      "step": 230
+    },
+    {
+      "epoch": 0.6629055007052186,
+      "grad_norm": 1.1211967468261719,
+      "learning_rate": 2.771413036768288e-05,
+      "loss": 0.7473,
+      "step": 235
+    },
+    {
+      "epoch": 0.6770098730606487,
+      "grad_norm": 0.8396211862564087,
+      "learning_rate": 2.7588936268552675e-05,
+      "loss": 0.7569,
+      "step": 240
+    },
+    {
+      "epoch": 0.691114245416079,
+      "grad_norm": 0.7665356397628784,
+      "learning_rate": 2.7460703260101352e-05,
+      "loss": 0.7236,
+      "step": 245
+    },
+    {
+      "epoch": 0.7052186177715092,
+      "grad_norm": 0.8343570232391357,
+      "learning_rate": 2.732946229716707e-05,
+      "loss": 0.8298,
+      "step": 250
+    },
+    {
+      "epoch": 0.7193229901269393,
+      "grad_norm": 0.7757318615913391,
+      "learning_rate": 2.7195245060693875e-05,
+      "loss": 0.7601,
+      "step": 255
+    },
+    {
+      "epoch": 0.7334273624823695,
+      "grad_norm": 0.9279292225837708,
+      "learning_rate": 2.7058083950084078e-05,
+      "loss": 0.756,
+      "step": 260
+    },
+    {
+      "epoch": 0.7475317348377997,
+      "grad_norm": 0.8167361617088318,
+      "learning_rate": 2.6918012075377226e-05,
+      "loss": 0.7282,
+      "step": 265
+    },
+    {
+      "epoch": 0.7616361071932299,
+      "grad_norm": 0.9970722198486328,
+      "learning_rate": 2.6775063249257455e-05,
+      "loss": 0.7269,
+      "step": 270
+    },
+    {
+      "epoch": 0.7757404795486601,
+      "grad_norm": 0.9086365103721619,
+      "learning_rate": 2.6629271978891274e-05,
+      "loss": 0.6997,
+      "step": 275
+    },
+    {
+      "epoch": 0.7898448519040903,
+      "grad_norm": 0.9044206738471985,
+      "learning_rate": 2.6480673457597737e-05,
+      "loss": 0.7432,
+      "step": 280
+    },
+    {
+      "epoch": 0.8039492242595204,
+      "grad_norm": 0.9141209125518799,
+      "learning_rate": 2.6329303556352887e-05,
+      "loss": 0.6848,
+      "step": 285
+    },
+    {
+      "epoch": 0.8180535966149506,
+      "grad_norm": 1.0687633752822876,
+      "learning_rate": 2.617519881513072e-05,
+      "loss": 0.6867,
+      "step": 290
+    },
+    {
+      "epoch": 0.8321579689703809,
+      "grad_norm": 0.883161187171936,
+      "learning_rate": 2.601839643408259e-05,
+      "loss": 0.7145,
+      "step": 295
+    },
+    {
+      "epoch": 0.846262341325811,
+      "grad_norm": 0.8746663331985474,
+      "learning_rate": 2.585893426455726e-05,
+      "loss": 0.6872,
+      "step": 300
+    },
+    {
+      "epoch": 0.8603667136812412,
+      "grad_norm": 0.8704200387001038,
+      "learning_rate": 2.569685079996379e-05,
+      "loss": 0.721,
+      "step": 305
+    },
+    {
+      "epoch": 0.8744710860366713,
+      "grad_norm": 0.8843702673912048,
+      "learning_rate": 2.553218516647939e-05,
+      "loss": 0.6911,
+      "step": 310
+    },
+    {
+      "epoch": 0.8885754583921015,
+      "grad_norm": 0.9311623573303223,
+      "learning_rate": 2.5364977113604556e-05,
+      "loss": 0.6773,
+      "step": 315
+    },
+    {
+      "epoch": 0.9026798307475318,
+      "grad_norm": 1.0709477663040161,
+      "learning_rate": 2.5195267004567726e-05,
+      "loss": 0.6897,
+      "step": 320
+    },
+    {
+      "epoch": 0.9167842031029619,
+      "grad_norm": 0.9492301344871521,
+      "learning_rate": 2.5023095806581802e-05,
+      "loss": 0.6388,
+      "step": 325
+    },
+    {
+      "epoch": 0.9308885754583921,
+      "grad_norm": 0.9412577748298645,
+      "learning_rate": 2.4848505080954837e-05,
+      "loss": 0.6361,
+      "step": 330
+    },
+    {
+      "epoch": 0.9449929478138223,
+      "grad_norm": 1.0852649211883545,
+      "learning_rate": 2.4671536973057353e-05,
+      "loss": 0.6297,
+      "step": 335
+    },
+    {
+      "epoch": 0.9590973201692524,
+      "grad_norm": 0.9144278168678284,
+      "learning_rate": 2.4492234202148643e-05,
+      "loss": 0.6433,
+      "step": 340
+    },
+    {
+      "epoch": 0.9732016925246827,
+      "grad_norm": 1.0399242639541626,
+      "learning_rate": 2.431064005106453e-05,
+      "loss": 0.6612,
+      "step": 345
+    },
+    {
+      "epoch": 0.9873060648801129,
+      "grad_norm": 1.1090110540390015,
+      "learning_rate": 2.4126798355769127e-05,
+      "loss": 0.6673,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.2217705249786377,
+      "learning_rate": 2.394075349477302e-05,
+      "loss": 0.6451,
+      "step": 355
+    },
+    {
+      "epoch": 1.0141043723554302,
+      "grad_norm": 0.9779360294342041,
+      "learning_rate": 2.3752550378420504e-05,
+      "loss": 0.5504,
+      "step": 360
+    },
+    {
+      "epoch": 1.0282087447108603,
+      "grad_norm": 1.057576060295105,
+      "learning_rate": 2.356223443804846e-05,
+      "loss": 0.5537,
+      "step": 365
+    },
+    {
+      "epoch": 1.0423131170662905,
+      "grad_norm": 0.9656654000282288,
+      "learning_rate": 2.3369851615019436e-05,
+      "loss": 0.5313,
+      "step": 370
+    },
+    {
+      "epoch": 1.0564174894217206,
+      "grad_norm": 0.9629194140434265,
+      "learning_rate": 2.3175448349631612e-05,
+      "loss": 0.513,
+      "step": 375
+    },
+    {
+      "epoch": 1.0705218617771508,
+      "grad_norm": 0.9746912717819214,
+      "learning_rate": 2.297907156990834e-05,
+      "loss": 0.5261,
+      "step": 380
+    },
+    {
+      "epoch": 1.0846262341325812,
+      "grad_norm": 1.168735384941101,
+      "learning_rate": 2.278076868026995e-05,
+      "loss": 0.5427,
+      "step": 385
+    },
+    {
+      "epoch": 1.0987306064880114,
+      "grad_norm": 1.0234464406967163,
+      "learning_rate": 2.2580587550090545e-05,
+      "loss": 0.536,
+      "step": 390
+    },
+    {
+      "epoch": 1.1128349788434415,
+      "grad_norm": 1.0218459367752075,
+      "learning_rate": 2.237857650214255e-05,
+      "loss": 0.4849,
+      "step": 395
+    },
+    {
+      "epoch": 1.1269393511988717,
+      "grad_norm": 0.9948587417602539,
+      "learning_rate": 2.217478430093183e-05,
+      "loss": 0.5444,
+      "step": 400
+    },
+    {
+      "epoch": 1.1410437235543018,
+      "grad_norm": 1.0465857982635498,
+      "learning_rate": 2.1969260140926184e-05,
+      "loss": 0.5036,
+      "step": 405
+    },
+    {
+      "epoch": 1.155148095909732,
+      "grad_norm": 1.0164107084274292,
+      "learning_rate": 2.1762053634680027e-05,
+      "loss": 0.5309,
+      "step": 410
+    },
+    {
+      "epoch": 1.1692524682651622,
+      "grad_norm": 1.1416183710098267,
+      "learning_rate": 2.155321480085813e-05,
+      "loss": 0.4755,
+      "step": 415
+    },
+    {
+      "epoch": 1.1833568406205923,
+      "grad_norm": 0.9101325869560242,
+      "learning_rate": 2.13427940521614e-05,
+      "loss": 0.488,
+      "step": 420
+    },
+    {
+      "epoch": 1.1974612129760225,
+      "grad_norm": 1.10642409324646,
+      "learning_rate": 2.1130842183157454e-05,
+      "loss": 0.4858,
+      "step": 425
+    },
+    {
+      "epoch": 1.2115655853314529,
+      "grad_norm": 1.0681025981903076,
+      "learning_rate": 2.0917410358019073e-05,
+      "loss": 0.4921,
+      "step": 430
+    },
+    {
+      "epoch": 1.225669957686883,
+      "grad_norm": 1.1171808242797852,
+      "learning_rate": 2.07025500981734e-05,
+      "loss": 0.5029,
+      "step": 435
+    },
+    {
+      "epoch": 1.2397743300423132,
+      "grad_norm": 1.2518407106399536,
+      "learning_rate": 2.0486313269864934e-05,
+      "loss": 0.4947,
+      "step": 440
+    },
+    {
+      "epoch": 1.2538787023977433,
+      "grad_norm": 0.9475494027137756,
+      "learning_rate": 2.0268752071635233e-05,
+      "loss": 0.4939,
+      "step": 445
+    },
+    {
+      "epoch": 1.2679830747531735,
+      "grad_norm": 1.1768218278884888,
+      "learning_rate": 2.004991902172248e-05,
+      "loss": 0.5105,
+      "step": 450
+    },
+    {
+      "epoch": 1.2820874471086037,
+      "grad_norm": 1.079684853553772,
+      "learning_rate": 1.9829866945383767e-05,
+      "loss": 0.5013,
+      "step": 455
+    },
+    {
+      "epoch": 1.2961918194640338,
+      "grad_norm": 1.0443543195724487,
+      "learning_rate": 1.9608648962143395e-05,
+      "loss": 0.4948,
+      "step": 460
+    },
+    {
+      "epoch": 1.310296191819464,
+      "grad_norm": 1.0285274982452393,
+      "learning_rate": 1.938631847297004e-05,
+      "loss": 0.4711,
+      "step": 465
+    },
+    {
+      "epoch": 1.3244005641748942,
+      "grad_norm": 0.9570646286010742,
+      "learning_rate": 1.9162929147385995e-05,
+      "loss": 0.4554,
+      "step": 470
+    },
+    {
+      "epoch": 1.3385049365303243,
+      "grad_norm": 1.0006874799728394,
+      "learning_rate": 1.893853491051165e-05,
+      "loss": 0.4825,
+      "step": 475
+    },
+    {
+      "epoch": 1.3526093088857545,
+      "grad_norm": 1.1493821144104004,
+      "learning_rate": 1.8713189930048196e-05,
+      "loss": 0.4631,
+      "step": 480
+    },
+    {
+      "epoch": 1.3667136812411846,
+      "grad_norm": 1.1185847520828247,
+      "learning_rate": 1.84869486032018e-05,
+      "loss": 0.4803,
+      "step": 485
+    },
+    {
+      "epoch": 1.380818053596615,
+      "grad_norm": 1.0214569568634033,
+      "learning_rate": 1.825986554355236e-05,
+      "loss": 0.4732,
+      "step": 490
+    },
+    {
+      "epoch": 1.3949224259520452,
+      "grad_norm": 1.028522253036499,
+      "learning_rate": 1.8031995567870108e-05,
+      "loss": 0.479,
+      "step": 495
+    },
+    {
+      "epoch": 1.4090267983074753,
+      "grad_norm": 1.0258777141571045,
+      "learning_rate": 1.7803393682883028e-05,
+      "loss": 0.4857,
+      "step": 500
+    },
+    {
+      "epoch": 1.4231311706629055,
+      "grad_norm": 1.1711688041687012,
+      "learning_rate": 1.757411507199855e-05,
+      "loss": 0.477,
+      "step": 505
+    },
+    {
+      "epoch": 1.4372355430183357,
+      "grad_norm": 1.1011371612548828,
+      "learning_rate": 1.7344215081982503e-05,
+      "loss": 0.4523,
+      "step": 510
+    },
+    {
+      "epoch": 1.4513399153737658,
+      "grad_norm": 1.2413910627365112,
+      "learning_rate": 1.7113749209598685e-05,
+      "loss": 0.4327,
+      "step": 515
+    },
+    {
+      "epoch": 1.465444287729196,
+      "grad_norm": 1.0976892709732056,
+      "learning_rate": 1.6882773088212213e-05,
+      "loss": 0.4144,
+      "step": 520
+    },
+    {
+      "epoch": 1.4795486600846262,
+      "grad_norm": 1.229501485824585,
+      "learning_rate": 1.6651342474359876e-05,
+      "loss": 0.4022,
+      "step": 525
+    },
+    {
+      "epoch": 1.4936530324400565,
+      "grad_norm": 0.9871422648429871,
+      "learning_rate": 1.6419513234290787e-05,
+      "loss": 0.4781,
+      "step": 530
+    },
+    {
+      "epoch": 1.5077574047954867,
+      "grad_norm": 1.2000219821929932,
+      "learning_rate": 1.618734133048052e-05,
+      "loss": 0.4432,
+      "step": 535
+    },
+    {
+      "epoch": 1.5218617771509169,
+      "grad_norm": 1.192143440246582,
+      "learning_rate": 1.5954882808122076e-05,
+      "loss": 0.4347,
+      "step": 540
+    },
+    {
+      "epoch": 1.535966149506347,
+      "grad_norm": 1.10850191116333,
+      "learning_rate": 1.572219378159677e-05,
+      "loss": 0.4575,
+      "step": 545
+    },
+    {
+      "epoch": 1.5500705218617772,
+      "grad_norm": 1.1962031126022339,
+      "learning_rate": 1.5489330420928554e-05,
+      "loss": 0.4297,
+      "step": 550
+    },
+    {
+      "epoch": 1.5641748942172073,
+      "grad_norm": 1.1044001579284668,
+      "learning_rate": 1.52563489382248e-05,
+      "loss": 0.4132,
+      "step": 555
+    },
+    {
+      "epoch": 1.5782792665726375,
+      "grad_norm": 1.1754919290542603,
+      "learning_rate": 1.502330557410699e-05,
+      "loss": 0.4108,
+      "step": 560
+    },
+    {
+      "epoch": 1.5923836389280677,
+      "grad_norm": 1.2200361490249634,
+      "learning_rate": 1.4790256584134467e-05,
+      "loss": 0.4378,
+      "step": 565
+    },
+    {
+      "epoch": 1.6064880112834978,
+      "grad_norm": 1.1088594198226929,
+      "learning_rate": 1.4557258225224645e-05,
+      "loss": 0.4256,
+      "step": 570
+    },
+    {
+      "epoch": 1.620592383638928,
+      "grad_norm": 1.0826644897460938,
+      "learning_rate": 1.4324366742072829e-05,
+      "loss": 0.4417,
+      "step": 575
+    },
+    {
+      "epoch": 1.6346967559943582,
+      "grad_norm": 1.2812403440475464,
+      "learning_rate": 1.4091638353575025e-05,
+      "loss": 0.3782,
+      "step": 580
+    },
+    {
+      "epoch": 1.6488011283497883,
+      "grad_norm": 1.1855332851409912,
+      "learning_rate": 1.3859129239256979e-05,
+      "loss": 0.4267,
+      "step": 585
+    },
+    {
+      "epoch": 1.6629055007052185,
+      "grad_norm": 1.1016427278518677,
+      "learning_rate": 1.3626895525712684e-05,
+      "loss": 0.4646,
+      "step": 590
+    },
+    {
+      "epoch": 1.6770098730606486,
+      "grad_norm": 0.9694410562515259,
+      "learning_rate": 1.339499327305569e-05,
+      "loss": 0.4382,
+      "step": 595
+    },
+    {
+      "epoch": 1.691114245416079,
+      "grad_norm": 1.075080156326294,
+      "learning_rate": 1.3163478461386473e-05,
+      "loss": 0.4266,
+      "step": 600
+    },
+    {
+      "epoch": 1.7052186177715092,
+      "grad_norm": 1.114485502243042,
+      "learning_rate": 1.2932406977279098e-05,
+      "loss": 0.3908,
+      "step": 605
+    },
+    {
+      "epoch": 1.7193229901269393,
+      "grad_norm": 1.386763095855713,
+      "learning_rate": 1.2701834600290465e-05,
+      "loss": 0.3927,
+      "step": 610
+    },
+    {
+      "epoch": 1.7334273624823695,
+      "grad_norm": 1.2929261922836304,
+      "learning_rate": 1.2471816989495388e-05,
+      "loss": 0.4185,
+      "step": 615
+    },
+    {
+      "epoch": 1.7475317348377997,
+      "grad_norm": 1.1296864748001099,
+      "learning_rate": 1.224240967005076e-05,
+      "loss": 0.3696,
+      "step": 620
+    },
+    {
+      "epoch": 1.76163610719323,
+      "grad_norm": 1.12260901927948,
+      "learning_rate": 1.2013668019792059e-05,
+      "loss": 0.3917,
+      "step": 625
+    },
+    {
+      "epoch": 1.7757404795486602,
+      "grad_norm": 1.0319411754608154,
+      "learning_rate": 1.178564725586537e-05,
+      "loss": 0.3933,
+      "step": 630
+    },
+    {
+      "epoch": 1.7898448519040904,
+      "grad_norm": 1.118044376373291,
+      "learning_rate": 1.155840242139826e-05,
+      "loss": 0.3672,
+      "step": 635
+    },
+    {
+      "epoch": 1.8039492242595205,
+      "grad_norm": 1.1741349697113037,
+      "learning_rate": 1.1331988372212604e-05,
+      "loss": 0.4185,
+      "step": 640
+    },
+    {
+      "epoch": 1.8180535966149507,
+      "grad_norm": 1.1323720216751099,
+      "learning_rate": 1.1106459763582677e-05,
+      "loss": 0.4182,
+      "step": 645
+    },
+    {
+      "epoch": 1.8321579689703809,
+      "grad_norm": 1.1298606395721436,
+      "learning_rate": 1.0881871037041609e-05,
+      "loss": 0.4054,
+      "step": 650
+    },
+    {
+      "epoch": 1.846262341325811,
+      "grad_norm": 1.0114415884017944,
+      "learning_rate": 1.0658276407239462e-05,
+      "loss": 0.3591,
+      "step": 655
+    },
+    {
+      "epoch": 1.8603667136812412,
+      "grad_norm": 1.1224391460418701,
+      "learning_rate": 1.0435729848856076e-05,
+      "loss": 0.3733,
+      "step": 660
+    },
+    {
+      "epoch": 1.8744710860366713,
+      "grad_norm": 1.0747662782669067,
+      "learning_rate": 1.0214285083571852e-05,
+      "loss": 0.3492,
+      "step": 665
+    },
+    {
+      "epoch": 1.8885754583921015,
+      "grad_norm": 1.0635310411453247,
+      "learning_rate": 9.993995567099557e-06,
+      "loss": 0.4061,
+      "step": 670
+    },
+    {
+      "epoch": 1.9026798307475317,
+      "grad_norm": 1.1589092016220093,
+      "learning_rate": 9.774914476280406e-06,
+      "loss": 0.4135,
+      "step": 675
+    },
+    {
+      "epoch": 1.9167842031029618,
+      "grad_norm": 1.0753183364868164,
+      "learning_rate": 9.5570946962474e-06,
+      "loss": 0.3453,
+      "step": 680
+    },
+    {
+      "epoch": 1.930888575458392,
+      "grad_norm": 1.2297141551971436,
+      "learning_rate": 9.340588807659128e-06,
+      "loss": 0.3324,
+      "step": 685
+    },
+    {
+      "epoch": 1.9449929478138221,
+      "grad_norm": 1.1735154390335083,
+      "learning_rate": 9.125449074007022e-06,
+      "loss": 0.3842,
+      "step": 690
+    },
+    {
+      "epoch": 1.9590973201692523,
+      "grad_norm": 1.0675801038742065,
+      "learning_rate": 8.911727428999228e-06,
+      "loss": 0.3502,
+      "step": 695
+    },
+    {
+      "epoch": 1.9732016925246827,
+      "grad_norm": 1.1319217681884766,
+      "learning_rate": 8.699475464024022e-06,
+      "loss": 0.3665,
+      "step": 700
+    },
+    {
+      "epoch": 1.9873060648801129,
+      "grad_norm": 1.0797913074493408,
+      "learning_rate": 8.488744415695935e-06,
+      "loss": 0.3492,
+      "step": 705
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5745668411254883,
+      "learning_rate": 8.279585153487432e-06,
+      "loss": 0.3524,
+      "step": 710
+    },
+    {
+      "epoch": 2.01410437235543,
+      "grad_norm": 1.1583154201507568,
+      "learning_rate": 8.072048167449306e-06,
+      "loss": 0.3004,
+      "step": 715
+    },
+    {
+      "epoch": 2.0282087447108603,
+      "grad_norm": 1.0896048545837402,
+      "learning_rate": 7.866183556022589e-06,
+      "loss": 0.3038,
+      "step": 720
+    },
+    {
+      "epoch": 2.0423131170662905,
+      "grad_norm": 1.1953916549682617,
+      "learning_rate": 7.66204101394504e-06,
+      "loss": 0.2683,
+      "step": 725
+    },
+    {
+      "epoch": 2.0564174894217206,
+      "grad_norm": 1.1226842403411865,
+      "learning_rate": 7.459669820255068e-06,
+      "loss": 0.2816,
+      "step": 730
+    },
+    {
+      "epoch": 2.070521861777151,
+      "grad_norm": 1.1742262840270996,
+      "learning_rate": 7.259118826396023e-06,
+      "loss": 0.2981,
+      "step": 735
+    },
+    {
+      "epoch": 2.084626234132581,
+      "grad_norm": 1.1152386665344238,
+      "learning_rate": 7.060436444423655e-06,
+      "loss": 0.3146,
+      "step": 740
+    },
+    {
+      "epoch": 2.098730606488011,
+      "grad_norm": 1.127606749534607,
+      "learning_rate": 6.863670635319715e-06,
+      "loss": 0.2814,
+      "step": 745
+    },
+    {
+      "epoch": 2.1128349788434413,
+      "grad_norm": 1.1797164678573608,
+      "learning_rate": 6.668868897414361e-06,
+      "loss": 0.2995,
+      "step": 750
+    },
+    {
+      "epoch": 2.1269393511988715,
+      "grad_norm": 1.1157251596450806,
+      "learning_rate": 6.476078254920332e-06,
+      "loss": 0.3234,
+      "step": 755
+    },
+    {
+      "epoch": 2.1410437235543016,
+      "grad_norm": 1.2317026853561401,
+      "learning_rate": 6.285345246581483e-06,
+      "loss": 0.2731,
+      "step": 760
+    },
+    {
+      "epoch": 2.155148095909732,
+      "grad_norm": 1.138250708580017,
+      "learning_rate": 6.096715914438581e-06,
+      "loss": 0.2951,
+      "step": 765
+    },
+    {
+      "epoch": 2.1692524682651624,
+      "grad_norm": 1.1442720890045166,
+      "learning_rate": 5.9102357927149636e-06,
+      "loss": 0.2752,
+      "step": 770
+    },
+    {
+      "epoch": 2.1833568406205925,
+      "grad_norm": 1.0629494190216064,
+      "learning_rate": 5.725949896824805e-06,
+      "loss": 0.2754,
+      "step": 775
+    },
+    {
+      "epoch": 2.1974612129760227,
+      "grad_norm": 1.4599025249481201,
+      "learning_rate": 5.543902712506608e-06,
+      "loss": 0.2692,
+      "step": 780
+    },
+    {
+      "epoch": 2.211565585331453,
+      "grad_norm": 1.312333345413208,
+      "learning_rate": 5.364138185084537e-06,
+      "loss": 0.2667,
+      "step": 785
+    },
+    {
+      "epoch": 2.225669957686883,
+      "grad_norm": 1.1906170845031738,
+      "learning_rate": 5.186699708860253e-06,
+      "loss": 0.2938,
+      "step": 790
+    },
+    {
+      "epoch": 2.239774330042313,
+      "grad_norm": 1.2544625997543335,
+      "learning_rate": 5.011630116637714e-06,
+      "loss": 0.2709,
+      "step": 795
+    },
+    {
+      "epoch": 2.2538787023977433,
+      "grad_norm": 1.1292496919631958,
+      "learning_rate": 4.838971669383567e-06,
+      "loss": 0.2547,
+      "step": 800
+    },
+    {
+      "epoch": 2.2679830747531735,
+      "grad_norm": 1.0335288047790527,
+      "learning_rate": 4.668766046025522e-06,
+      "loss": 0.2839,
+      "step": 805
+    },
+    {
+      "epoch": 2.2820874471086037,
+      "grad_norm": 1.2633644342422485,
+      "learning_rate": 4.501054333391275e-06,
+      "loss": 0.2833,
+      "step": 810
+    },
+    {
+      "epoch": 2.296191819464034,
+      "grad_norm": 1.4309486150741577,
+      "learning_rate": 4.335877016290326e-06,
+      "loss": 0.2572,
+      "step": 815
+    },
+    {
+      "epoch": 2.310296191819464,
+      "grad_norm": 1.140089511871338,
+      "learning_rate": 4.173273967741184e-06,
+      "loss": 0.282,
+      "step": 820
+    },
+    {
+      "epoch": 2.324400564174894,
+      "grad_norm": 1.0295286178588867,
+      "learning_rate": 4.013284439346143e-06,
+      "loss": 0.2748,
+      "step": 825
+    },
+    {
+      "epoch": 2.3385049365303243,
+      "grad_norm": 1.161552906036377,
+      "learning_rate": 3.855947051816179e-06,
+      "loss": 0.2915,
+      "step": 830
+    },
+    {
+      "epoch": 2.3526093088857545,
+      "grad_norm": 1.19903564453125,
+      "learning_rate": 3.7012997856480797e-06,
+      "loss": 0.247,
+      "step": 835
+    },
+    {
+      "epoch": 2.3667136812411846,
+      "grad_norm": 1.076019525527954,
+      "learning_rate": 3.5493799719561415e-06,
+      "loss": 0.2695,
+      "step": 840
+    },
+    {
+      "epoch": 2.380818053596615,
+      "grad_norm": 1.0606794357299805,
+      "learning_rate": 3.4002242834606023e-06,
+      "loss": 0.2932,
+      "step": 845
+    },
+    {
+      "epoch": 2.394922425952045,
+      "grad_norm": 1.0199371576309204,
+      "learning_rate": 3.2538687256350297e-06,
+      "loss": 0.2951,
+      "step": 850
+    },
+    {
+      "epoch": 2.409026798307475,
+      "grad_norm": 1.2532767057418823,
+      "learning_rate": 3.1103486280147624e-06,
+      "loss": 0.242,
+      "step": 855
+    },
+    {
+      "epoch": 2.4231311706629057,
+      "grad_norm": 1.1056053638458252,
+      "learning_rate": 2.969698635668553e-06,
+      "loss": 0.3052,
+      "step": 860
+    },
+    {
+      "epoch": 2.4372355430183354,
+      "grad_norm": 1.1143027544021606,
+      "learning_rate": 2.8319527008353863e-06,
+      "loss": 0.2853,
+      "step": 865
+    },
+    {
+      "epoch": 2.451339915373766,
+      "grad_norm": 1.3031234741210938,
+      "learning_rate": 2.697144074728577e-06,
+      "loss": 0.2887,
+      "step": 870
+    },
+    {
+      "epoch": 2.465444287729196,
+      "grad_norm": 1.3708378076553345,
+      "learning_rate": 2.5653052995090927e-06,
+      "loss": 0.2947,
+      "step": 875
+    },
+    {
+      "epoch": 2.4795486600846264,
+      "grad_norm": 1.1034775972366333,
+      "learning_rate": 2.4364682004300193e-06,
+      "loss": 0.2862,
+      "step": 880
+    },
+    {
+      "epoch": 2.4936530324400565,
+      "grad_norm": 1.668222427368164,
+      "learning_rate": 2.3106638781541174e-06,
+      "loss": 0.2849,
+      "step": 885
+    },
+    {
+      "epoch": 2.5077574047954867,
+      "grad_norm": 1.1864745616912842,
+      "learning_rate": 2.1879227012462443e-06,
+      "loss": 0.2725,
+      "step": 890
+    },
+    {
+      "epoch": 2.521861777150917,
+      "grad_norm": 1.040053367614746,
+      "learning_rate": 2.068274298842537e-06,
+      "loss": 0.2839,
+      "step": 895
+    },
+    {
+      "epoch": 2.535966149506347,
+      "grad_norm": 1.3880667686462402,
+      "learning_rate": 1.951747553498094e-06,
+      "loss": 0.2555,
+      "step": 900
+    },
+    {
+      "epoch": 2.550070521861777,
+      "grad_norm": 1.166029691696167,
+      "learning_rate": 1.838370594214845e-06,
+      "loss": 0.2883,
+      "step": 905
+    },
+    {
+      "epoch": 2.5641748942172073,
+      "grad_norm": 1.0345028638839722,
+      "learning_rate": 1.7281707896513476e-06,
+      "loss": 0.241,
+      "step": 910
+    },
+    {
+      "epoch": 2.5782792665726375,
+      "grad_norm": 1.1178319454193115,
+      "learning_rate": 1.6211747415161283e-06,
+      "loss": 0.2871,
+      "step": 915
+    },
+    {
+      "epoch": 2.5923836389280677,
+      "grad_norm": 1.3234437704086304,
+      "learning_rate": 1.5174082781461507e-06,
+      "loss": 0.2572,
+      "step": 920
+    },
+    {
+      "epoch": 2.606488011283498,
+      "grad_norm": 1.1979159116744995,
+      "learning_rate": 1.4168964482719916e-06,
+      "loss": 0.2797,
+      "step": 925
+    },
+    {
+      "epoch": 2.620592383638928,
+      "grad_norm": 1.1470959186553955,
+      "learning_rate": 1.3196635149711712e-06,
+      "loss": 0.2661,
+      "step": 930
+    },
+    {
+      "epoch": 2.634696755994358,
+      "grad_norm": 1.194756031036377,
+      "learning_rate": 1.225732949811194e-06,
+      "loss": 0.2499,
+      "step": 935
+    },
+    {
+      "epoch": 2.6488011283497883,
+      "grad_norm": 1.0186817646026611,
+      "learning_rate": 1.1351274271835948e-06,
+      "loss": 0.2836,
+      "step": 940
+    },
+    {
+      "epoch": 2.6629055007052185,
+      "grad_norm": 1.125927448272705,
+      "learning_rate": 1.0478688188304609e-06,
+      "loss": 0.266,
+      "step": 945
+    },
+    {
+      "epoch": 2.6770098730606486,
+      "grad_norm": 1.1773096323013306,
+      "learning_rate": 9.63978188564706e-07,
+      "loss": 0.2785,
+      "step": 950
+    },
+    {
+      "epoch": 2.6911142454160792,
+      "grad_norm": 1.183424472808838,
+      "learning_rate": 8.834757871853461e-07,
+      "loss": 0.2703,
+      "step": 955
+    },
+    {
+      "epoch": 2.705218617771509,
+      "grad_norm": 1.1363831758499146,
+      "learning_rate": 8.063810475890732e-07,
+      "loss": 0.2485,
+      "step": 960
+    },
+    {
+      "epoch": 2.7193229901269396,
+      "grad_norm": 1.0881335735321045,
+      "learning_rate": 7.327125800792306e-07,
+      "loss": 0.2701,
+      "step": 965
+    },
+    {
+      "epoch": 2.7334273624823693,
+      "grad_norm": 1.0611447095870972,
+      "learning_rate": 6.624881678733852e-07,
+      "loss": 0.2947,
+      "step": 970
+    },
+    {
+      "epoch": 2.7475317348378,
+      "grad_norm": 1.1491048336029053,
+      "learning_rate": 5.957247628105428e-07,
+      "loss": 0.2426,
+      "step": 975
+    },
+    {
+      "epoch": 2.76163610719323,
+      "grad_norm": 1.1622920036315918,
+      "learning_rate": 5.324384812590416e-07,
+      "loss": 0.2494,
+      "step": 980
+    },
+    {
+      "epoch": 2.77574047954866,
+      "grad_norm": 1.0566214323043823,
+      "learning_rate": 4.726446002261542e-07,
+      "loss": 0.2737,
+      "step": 985
+    },
+    {
+      "epoch": 2.7898448519040904,
+      "grad_norm": 1.2265506982803345,
+      "learning_rate": 4.163575536702807e-07,
+      "loss": 0.2797,
+      "step": 990
+    },
+    {
+      "epoch": 2.8039492242595205,
+      "grad_norm": 1.0316542387008667,
+      "learning_rate": 3.6359092901666614e-07,
+      "loss": 0.2495,
+      "step": 995
+    },
+    {
+      "epoch": 2.8180535966149507,
+      "grad_norm": 1.2222540378570557,
+      "learning_rate": 3.1435746387745543e-07,
+      "loss": 0.2359,
+      "step": 1000
+    },
+    {
+      "epoch": 2.832157968970381,
+      "grad_norm": 1.1253416538238525,
+      "learning_rate": 2.686690429768918e-07,
+      "loss": 0.2479,
+      "step": 1005
+    },
+    {
+      "epoch": 2.846262341325811,
+      "grad_norm": 1.1156409978866577,
+      "learning_rate": 2.2653669528241271e-07,
+      "loss": 0.2747,
+      "step": 1010
+    },
+    {
+      "epoch": 2.860366713681241,
+      "grad_norm": 1.0888277292251587,
+      "learning_rate": 1.8797059134230188e-07,
+      "loss": 0.233,
+      "step": 1015
+    },
+    {
+      "epoch": 2.8744710860366713,
+      "grad_norm": 1.0753988027572632,
+      "learning_rate": 1.5298004083056093e-07,
+      "loss": 0.2948,
+      "step": 1020
+    },
+    {
+      "epoch": 2.8885754583921015,
+      "grad_norm": 1.0877095460891724,
+      "learning_rate": 1.2157349029961406e-07,
+      "loss": 0.2551,
+      "step": 1025
+    },
+    {
+      "epoch": 2.9026798307475317,
+      "grad_norm": 1.1085031032562256,
+      "learning_rate": 9.375852114133221e-08,
+      "loss": 0.2616,
+      "step": 1030
+    },
+    {
+      "epoch": 2.916784203102962,
+      "grad_norm": 1.057011604309082,
+      "learning_rate": 6.954184775693873e-08,
+      "loss": 0.2584,
+      "step": 1035
+    },
+    {
+      "epoch": 2.930888575458392,
+      "grad_norm": 1.0307466983795166,
+      "learning_rate": 4.8929315936174224e-08,
+      "loss": 0.2821,
+      "step": 1040
+    },
+    {
+      "epoch": 2.944992947813822,
+      "grad_norm": 1.2166166305541992,
+      "learning_rate": 3.1925901446148707e-08,
+      "loss": 0.2627,
+      "step": 1045
+    },
+    {
+      "epoch": 2.9590973201692523,
+      "grad_norm": 1.146585464477539,
+      "learning_rate": 1.8535708830225707e-08,
+      "loss": 0.2403,
+      "step": 1050
+    },
+    {
+      "epoch": 2.9732016925246825,
+      "grad_norm": 1.1046348810195923,
+      "learning_rate": 8.761970417198173e-09,
+      "loss": 0.2769,
+      "step": 1055
+    },
+    {
+      "epoch": 2.987306064880113,
+      "grad_norm": 1.154034972190857,
+      "learning_rate": 2.607045541015984e-09,
+      "loss": 0.2889,
+      "step": 1060
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.6319630146026611,
+      "learning_rate": 7.24199712615059e-11,
+      "loss": 0.255,
+      "step": 1065
+    },
+    {
+      "epoch": 3.0,
+      "step": 1065,
+      "total_flos": 1.6551636736996803e+18,
+      "train_loss": 0.5368774858438913,
+      "train_runtime": 778.027,
+      "train_samples_per_second": 43.726,
+      "train_steps_per_second": 1.369
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1065,
+  "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": 1.6551636736996803e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

11_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd5c051fdd72aa5c635c7800cbd0e8d3c8e195ee6fd228ac3c8b21eb0a3a566
+size 8145