Upload folder using huggingface_hub

34_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

34_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: 34_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. -->
+
+# 34_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

34_128_e3_3e-5/adapter_config.json

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

34_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c27256c083edfd63b9cc039c248351bb97851b6277430123bf6d74bc3c20a987
+size 791751704

34_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.436218182569296e+18,
+    "train_loss": 0.6181889377437435,
+    "train_runtime": 688.4097,
+    "train_samples": 10650,
+    "train_samples_per_second": 46.411,
+    "train_steps_per_second": 1.451
+}

34_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
+}

34_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
+  }
+}

34_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
+}

34_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.436218182569296e+18,
+    "train_loss": 0.6181889377437435,
+    "train_runtime": 688.4097,
+    "train_samples": 10650,
+    "train_samples_per_second": 46.411,
+    "train_steps_per_second": 1.451
+}

34_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1436 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 999,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015015015015015015,
+      "grad_norm": 1.1484143733978271,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.4078,
+      "step": 5
+    },
+    {
+      "epoch": 0.03003003003003003,
+      "grad_norm": 0.6892414093017578,
+      "learning_rate": 5.4e-06,
+      "loss": 1.4025,
+      "step": 10
+    },
+    {
+      "epoch": 0.04504504504504504,
+      "grad_norm": 0.5325756072998047,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 1.4203,
+      "step": 15
+    },
+    {
+      "epoch": 0.06006006006006006,
+      "grad_norm": 0.8819801807403564,
+      "learning_rate": 1.1400000000000001e-05,
+      "loss": 1.39,
+      "step": 20
+    },
+    {
+      "epoch": 0.07507507507507508,
+      "grad_norm": 0.5360053181648254,
+      "learning_rate": 1.44e-05,
+      "loss": 1.3497,
+      "step": 25
+    },
+    {
+      "epoch": 0.09009009009009009,
+      "grad_norm": 0.4859957695007324,
+      "learning_rate": 1.74e-05,
+      "loss": 1.3029,
+      "step": 30
+    },
+    {
+      "epoch": 0.10510510510510511,
+      "grad_norm": 0.5125545263290405,
+      "learning_rate": 2.04e-05,
+      "loss": 1.2705,
+      "step": 35
+    },
+    {
+      "epoch": 0.12012012012012012,
+      "grad_norm": 0.4615287780761719,
+      "learning_rate": 2.3400000000000003e-05,
+      "loss": 1.3094,
+      "step": 40
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.48541459441185,
+      "learning_rate": 2.64e-05,
+      "loss": 1.3004,
+      "step": 45
+    },
+    {
+      "epoch": 0.15015015015015015,
+      "grad_norm": 0.4013228118419647,
+      "learning_rate": 2.94e-05,
+      "loss": 1.1772,
+      "step": 50
+    },
+    {
+      "epoch": 0.16516516516516516,
+      "grad_norm": 0.5810917019844055,
+      "learning_rate": 2.9998684950135947e-05,
+      "loss": 1.2781,
+      "step": 55
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 0.45503100752830505,
+      "learning_rate": 2.9993342955245677e-05,
+      "loss": 1.26,
+      "step": 60
+    },
+    {
+      "epoch": 0.19519519519519518,
+      "grad_norm": 0.497655987739563,
+      "learning_rate": 2.998389328711426e-05,
+      "loss": 1.2291,
+      "step": 65
+    },
+    {
+      "epoch": 0.21021021021021022,
+      "grad_norm": 0.48465633392333984,
+      "learning_rate": 2.997033853463391e-05,
+      "loss": 1.1916,
+      "step": 70
+    },
+    {
+      "epoch": 0.22522522522522523,
+      "grad_norm": 0.5153307318687439,
+      "learning_rate": 2.995268241135232e-05,
+      "loss": 1.2513,
+      "step": 75
+    },
+    {
+      "epoch": 0.24024024024024024,
+      "grad_norm": 0.5280073285102844,
+      "learning_rate": 2.993092975445526e-05,
+      "loss": 1.2412,
+      "step": 80
+    },
+    {
+      "epoch": 0.2552552552552553,
+      "grad_norm": 0.5075555443763733,
+      "learning_rate": 2.9905086523441348e-05,
+      "loss": 1.2018,
+      "step": 85
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.5215229988098145,
+      "learning_rate": 2.987515979848935e-05,
+      "loss": 1.1528,
+      "step": 90
+    },
+    {
+      "epoch": 0.2852852852852853,
+      "grad_norm": 0.5198177695274353,
+      "learning_rate": 2.9841157778518462e-05,
+      "loss": 1.1286,
+      "step": 95
+    },
+    {
+      "epoch": 0.3003003003003003,
+      "grad_norm": 0.5829412937164307,
+      "learning_rate": 2.9803089778942062e-05,
+      "loss": 1.1929,
+      "step": 100
+    },
+    {
+      "epoch": 0.3153153153153153,
+      "grad_norm": 0.605205774307251,
+      "learning_rate": 2.976096622911561e-05,
+      "loss": 1.0895,
+      "step": 105
+    },
+    {
+      "epoch": 0.3303303303303303,
+      "grad_norm": 0.6692696809768677,
+      "learning_rate": 2.971479866947935e-05,
+      "loss": 1.085,
+      "step": 110
+    },
+    {
+      "epoch": 0.34534534534534533,
+      "grad_norm": 0.6942810416221619,
+      "learning_rate": 2.9664599748396622e-05,
+      "loss": 1.1369,
+      "step": 115
+    },
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 0.6146662831306458,
+      "learning_rate": 2.961038321868862e-05,
+      "loss": 1.1004,
+      "step": 120
+    },
+    {
+      "epoch": 0.37537537537537535,
+      "grad_norm": 0.6204975843429565,
+      "learning_rate": 2.9552163933866605e-05,
+      "loss": 1.1154,
+      "step": 125
+    },
+    {
+      "epoch": 0.39039039039039036,
+      "grad_norm": 0.6181800365447998,
+      "learning_rate": 2.948995784406251e-05,
+      "loss": 1.0623,
+      "step": 130
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.6573542952537537,
+      "learning_rate": 2.942378199165917e-05,
+      "loss": 1.0642,
+      "step": 135
+    },
+    {
+      "epoch": 0.42042042042042044,
+      "grad_norm": 0.6602272987365723,
+      "learning_rate": 2.935365450662126e-05,
+      "loss": 1.0251,
+      "step": 140
+    },
+    {
+      "epoch": 0.43543543543543545,
+      "grad_norm": 0.7046717405319214,
+      "learning_rate": 2.9279594601528295e-05,
+      "loss": 1.1018,
+      "step": 145
+    },
+    {
+      "epoch": 0.45045045045045046,
+      "grad_norm": 0.7052332758903503,
+      "learning_rate": 2.9201622566311028e-05,
+      "loss": 1.0514,
+      "step": 150
+    },
+    {
+      "epoch": 0.46546546546546547,
+      "grad_norm": 0.6828079223632812,
+      "learning_rate": 2.9119759762692708e-05,
+      "loss": 1.0436,
+      "step": 155
+    },
+    {
+      "epoch": 0.4804804804804805,
+      "grad_norm": 0.6680599451065063,
+      "learning_rate": 2.9034028618336647e-05,
+      "loss": 1.0623,
+      "step": 160
+    },
+    {
+      "epoch": 0.4954954954954955,
+      "grad_norm": 0.7614235877990723,
+      "learning_rate": 2.894445262070183e-05,
+      "loss": 0.9853,
+      "step": 165
+    },
+    {
+      "epoch": 0.5105105105105106,
+      "grad_norm": 0.7840650081634521,
+      "learning_rate": 2.8851056310608105e-05,
+      "loss": 1.0016,
+      "step": 170
+    },
+    {
+      "epoch": 0.5255255255255256,
+      "grad_norm": 0.7831375598907471,
+      "learning_rate": 2.875386527551286e-05,
+      "loss": 0.9423,
+      "step": 175
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.782213032245636,
+      "learning_rate": 2.8652906142500877e-05,
+      "loss": 0.9897,
+      "step": 180
+    },
+    {
+      "epoch": 0.5555555555555556,
+      "grad_norm": 0.7841219305992126,
+      "learning_rate": 2.854820657098943e-05,
+      "loss": 0.8911,
+      "step": 185
+    },
+    {
+      "epoch": 0.5705705705705706,
+      "grad_norm": 0.8948962688446045,
+      "learning_rate": 2.843979524515053e-05,
+      "loss": 0.9788,
+      "step": 190
+    },
+    {
+      "epoch": 0.5855855855855856,
+      "grad_norm": 0.9402740597724915,
+      "learning_rate": 2.8327701866052404e-05,
+      "loss": 0.9185,
+      "step": 195
+    },
+    {
+      "epoch": 0.6006006006006006,
+      "grad_norm": 0.8964099884033203,
+      "learning_rate": 2.8211957143522424e-05,
+      "loss": 0.8831,
+      "step": 200
+    },
+    {
+      "epoch": 0.6156156156156156,
+      "grad_norm": 0.8970125317573547,
+      "learning_rate": 2.809259278773363e-05,
+      "loss": 0.8455,
+      "step": 205
+    },
+    {
+      "epoch": 0.6306306306306306,
+      "grad_norm": 0.9058867692947388,
+      "learning_rate": 2.79696415005172e-05,
+      "loss": 0.9014,
+      "step": 210
+    },
+    {
+      "epoch": 0.6456456456456456,
+      "grad_norm": 1.1062525510787964,
+      "learning_rate": 2.784313696640327e-05,
+      "loss": 0.847,
+      "step": 215
+    },
+    {
+      "epoch": 0.6606606606606606,
+      "grad_norm": 0.9456507563591003,
+      "learning_rate": 2.771311384339247e-05,
+      "loss": 0.8587,
+      "step": 220
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 1.0028166770935059,
+      "learning_rate": 2.7579607753460813e-05,
+      "loss": 0.8766,
+      "step": 225
+    },
+    {
+      "epoch": 0.6906906906906907,
+      "grad_norm": 0.854725182056427,
+      "learning_rate": 2.7442655272800463e-05,
+      "loss": 0.913,
+      "step": 230
+    },
+    {
+      "epoch": 0.7057057057057057,
+      "grad_norm": 0.8915291428565979,
+      "learning_rate": 2.7302293921799097e-05,
+      "loss": 0.9235,
+      "step": 235
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.9481147527694702,
+      "learning_rate": 2.715856215476055e-05,
+      "loss": 0.8392,
+      "step": 240
+    },
+    {
+      "epoch": 0.7357357357357357,
+      "grad_norm": 0.8800114393234253,
+      "learning_rate": 2.7011499349369643e-05,
+      "loss": 0.8768,
+      "step": 245
+    },
+    {
+      "epoch": 0.7507507507507507,
+      "grad_norm": 0.9145507216453552,
+      "learning_rate": 2.686114579590403e-05,
+      "loss": 0.8378,
+      "step": 250
+    },
+    {
+      "epoch": 0.7657657657657657,
+      "grad_norm": 1.0099443197250366,
+      "learning_rate": 2.670754268619598e-05,
+      "loss": 0.853,
+      "step": 255
+    },
+    {
+      "epoch": 0.7807807807807807,
+      "grad_norm": 0.9794849753379822,
+      "learning_rate": 2.655073210234722e-05,
+      "loss": 0.8288,
+      "step": 260
+    },
+    {
+      "epoch": 0.7957957957957958,
+      "grad_norm": 0.9411181211471558,
+      "learning_rate": 2.6390757005199858e-05,
+      "loss": 0.7824,
+      "step": 265
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.9992733001708984,
+      "learning_rate": 2.6227661222566516e-05,
+      "loss": 0.8103,
+      "step": 270
+    },
+    {
+      "epoch": 0.8258258258258259,
+      "grad_norm": 0.975662112236023,
+      "learning_rate": 2.6061489437223026e-05,
+      "loss": 0.8058,
+      "step": 275
+    },
+    {
+      "epoch": 0.8408408408408409,
+      "grad_norm": 1.0072816610336304,
+      "learning_rate": 2.58922871746668e-05,
+      "loss": 0.7837,
+      "step": 280
+    },
+    {
+      "epoch": 0.8558558558558559,
+      "grad_norm": 0.966558039188385,
+      "learning_rate": 2.5720100790644417e-05,
+      "loss": 0.7745,
+      "step": 285
+    },
+    {
+      "epoch": 0.8708708708708709,
+      "grad_norm": 1.1010689735412598,
+      "learning_rate": 2.554497745845166e-05,
+      "loss": 0.7394,
+      "step": 290
+    },
+    {
+      "epoch": 0.8858858858858859,
+      "grad_norm": 1.0176725387573242,
+      "learning_rate": 2.536696515600965e-05,
+      "loss": 0.7764,
+      "step": 295
+    },
+    {
+      "epoch": 0.9009009009009009,
+      "grad_norm": 1.0427451133728027,
+      "learning_rate": 2.518611265272048e-05,
+      "loss": 0.7098,
+      "step": 300
+    },
+    {
+      "epoch": 0.9159159159159159,
+      "grad_norm": 1.1417382955551147,
+      "learning_rate": 2.5002469496106044e-05,
+      "loss": 0.7165,
+      "step": 305
+    },
+    {
+      "epoch": 0.9309309309309309,
+      "grad_norm": 1.088168740272522,
+      "learning_rate": 2.4816085998233678e-05,
+      "loss": 0.7403,
+      "step": 310
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 1.066701889038086,
+      "learning_rate": 2.462701322193234e-05,
+      "loss": 0.7415,
+      "step": 315
+    },
+    {
+      "epoch": 0.960960960960961,
+      "grad_norm": 1.2539544105529785,
+      "learning_rate": 2.4435302966803103e-05,
+      "loss": 0.7658,
+      "step": 320
+    },
+    {
+      "epoch": 0.975975975975976,
+      "grad_norm": 1.1172897815704346,
+      "learning_rate": 2.4241007755027798e-05,
+      "loss": 0.7404,
+      "step": 325
+    },
+    {
+      "epoch": 0.990990990990991,
+      "grad_norm": 0.981971800327301,
+      "learning_rate": 2.4044180816979718e-05,
+      "loss": 0.6921,
+      "step": 330
+    },
+    {
+      "epoch": 1.006006006006006,
+      "grad_norm": 1.0711027383804321,
+      "learning_rate": 2.384487607664026e-05,
+      "loss": 0.6788,
+      "step": 335
+    },
+    {
+      "epoch": 1.021021021021021,
+      "grad_norm": 1.1622968912124634,
+      "learning_rate": 2.3643148136825554e-05,
+      "loss": 0.6253,
+      "step": 340
+    },
+    {
+      "epoch": 1.0360360360360361,
+      "grad_norm": 1.0621509552001953,
+      "learning_rate": 2.343905226422715e-05,
+      "loss": 0.654,
+      "step": 345
+    },
+    {
+      "epoch": 1.0510510510510511,
+      "grad_norm": 1.0353513956069946,
+      "learning_rate": 2.323264437427079e-05,
+      "loss": 0.5955,
+      "step": 350
+    },
+    {
+      "epoch": 1.0660660660660661,
+      "grad_norm": 1.0856592655181885,
+      "learning_rate": 2.3023981015797432e-05,
+      "loss": 0.604,
+      "step": 355
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 1.090743899345398,
+      "learning_rate": 2.2813119355570793e-05,
+      "loss": 0.6169,
+      "step": 360
+    },
+    {
+      "epoch": 1.0960960960960962,
+      "grad_norm": 1.0367685556411743,
+      "learning_rate": 2.260011716261555e-05,
+      "loss": 0.6323,
+      "step": 365
+    },
+    {
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.149460792541504,
+      "learning_rate": 2.2385032792390602e-05,
+      "loss": 0.5658,
+      "step": 370
+    },
+    {
+      "epoch": 1.1261261261261262,
+      "grad_norm": 1.2203172445297241,
+      "learning_rate": 2.216792517080157e-05,
+      "loss": 0.579,
+      "step": 375
+    },
+    {
+      "epoch": 1.1411411411411412,
+      "grad_norm": 1.3246182203292847,
+      "learning_rate": 2.1948853778057134e-05,
+      "loss": 0.5894,
+      "step": 380
+    },
+    {
+      "epoch": 1.1561561561561562,
+      "grad_norm": 1.381394863128662,
+      "learning_rate": 2.172787863237341e-05,
+      "loss": 0.6076,
+      "step": 385
+    },
+    {
+      "epoch": 1.1711711711711712,
+      "grad_norm": 1.3174819946289062,
+      "learning_rate": 2.150506027353099e-05,
+      "loss": 0.5601,
+      "step": 390
+    },
+    {
+      "epoch": 1.1861861861861862,
+      "grad_norm": 1.1005864143371582,
+      "learning_rate": 2.128045974628908e-05,
+      "loss": 0.5917,
+      "step": 395
+    },
+    {
+      "epoch": 1.2012012012012012,
+      "grad_norm": 1.0645122528076172,
+      "learning_rate": 2.1054138583661252e-05,
+      "loss": 0.6081,
+      "step": 400
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 1.3405433893203735,
+      "learning_rate": 2.0826158790057502e-05,
+      "loss": 0.5679,
+      "step": 405
+    },
+    {
+      "epoch": 1.2312312312312312,
+      "grad_norm": 1.2713614702224731,
+      "learning_rate": 2.0596582824297075e-05,
+      "loss": 0.5596,
+      "step": 410
+    },
+    {
+      "epoch": 1.2462462462462462,
+      "grad_norm": 1.1423583030700684,
+      "learning_rate": 2.0365473582496887e-05,
+      "loss": 0.588,
+      "step": 415
+    },
+    {
+      "epoch": 1.2612612612612613,
+      "grad_norm": 1.141084909439087,
+      "learning_rate": 2.0132894380840062e-05,
+      "loss": 0.547,
+      "step": 420
+    },
+    {
+      "epoch": 1.2762762762762763,
+      "grad_norm": 1.1362380981445312,
+      "learning_rate": 1.9898908938229456e-05,
+      "loss": 0.5738,
+      "step": 425
+    },
+    {
+      "epoch": 1.2912912912912913,
+      "grad_norm": 1.1193246841430664,
+      "learning_rate": 1.966358135883078e-05,
+      "loss": 0.5221,
+      "step": 430
+    },
+    {
+      "epoch": 1.3063063063063063,
+      "grad_norm": 1.1693378686904907,
+      "learning_rate": 1.9426976114510228e-05,
+      "loss": 0.5801,
+      "step": 435
+    },
+    {
+      "epoch": 1.3213213213213213,
+      "grad_norm": 1.1746633052825928,
+      "learning_rate": 1.918915802717134e-05,
+      "loss": 0.5532,
+      "step": 440
+    },
+    {
+      "epoch": 1.3363363363363363,
+      "grad_norm": 1.2581690549850464,
+      "learning_rate": 1.8950192250995983e-05,
+      "loss": 0.5322,
+      "step": 445
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 1.378767490386963,
+      "learning_rate": 1.8710144254594268e-05,
+      "loss": 0.517,
+      "step": 450
+    },
+    {
+      "epoch": 1.3663663663663663,
+      "grad_norm": 1.3416332006454468,
+      "learning_rate": 1.8469079803068375e-05,
+      "loss": 0.5847,
+      "step": 455
+    },
+    {
+      "epoch": 1.3813813813813813,
+      "grad_norm": 1.3204106092453003,
+      "learning_rate": 1.822706493999511e-05,
+      "loss": 0.5586,
+      "step": 460
+    },
+    {
+      "epoch": 1.3963963963963963,
+      "grad_norm": 1.3145545721054077,
+      "learning_rate": 1.798416596933216e-05,
+      "loss": 0.5416,
+      "step": 465
+    },
+    {
+      "epoch": 1.4114114114114114,
+      "grad_norm": 1.3292595148086548,
+      "learning_rate": 1.7740449437253052e-05,
+      "loss": 0.541,
+      "step": 470
+    },
+    {
+      "epoch": 1.4264264264264264,
+      "grad_norm": 1.2827143669128418,
+      "learning_rate": 1.749598211391574e-05,
+      "loss": 0.5017,
+      "step": 475
+    },
+    {
+      "epoch": 1.4414414414414414,
+      "grad_norm": 1.2557770013809204,
+      "learning_rate": 1.725083097516979e-05,
+      "loss": 0.5669,
+      "step": 480
+    },
+    {
+      "epoch": 1.4564564564564564,
+      "grad_norm": 1.2120285034179688,
+      "learning_rate": 1.7005063184207284e-05,
+      "loss": 0.5202,
+      "step": 485
+    },
+    {
+      "epoch": 1.4714714714714714,
+      "grad_norm": 1.2216753959655762,
+      "learning_rate": 1.6758746073162303e-05,
+      "loss": 0.5216,
+      "step": 490
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 1.2441867589950562,
+      "learning_rate": 1.651194712466425e-05,
+      "loss": 0.4892,
+      "step": 495
+    },
+    {
+      "epoch": 1.5015015015015014,
+      "grad_norm": 1.2296313047409058,
+      "learning_rate": 1.626473395334981e-05,
+      "loss": 0.5244,
+      "step": 500
+    },
+    {
+      "epoch": 1.5165165165165164,
+      "grad_norm": 1.413462519645691,
+      "learning_rate": 1.6017174287338833e-05,
+      "loss": 0.5157,
+      "step": 505
+    },
+    {
+      "epoch": 1.5315315315315314,
+      "grad_norm": 1.2754665613174438,
+      "learning_rate": 1.5769335949679097e-05,
+      "loss": 0.5245,
+      "step": 510
+    },
+    {
+      "epoch": 1.5465465465465464,
+      "grad_norm": 1.099385380744934,
+      "learning_rate": 1.5521286839765078e-05,
+      "loss": 0.5156,
+      "step": 515
+    },
+    {
+      "epoch": 1.5615615615615615,
+      "grad_norm": 1.2021174430847168,
+      "learning_rate": 1.527309491473577e-05,
+      "loss": 0.4909,
+      "step": 520
+    },
+    {
+      "epoch": 1.5765765765765765,
+      "grad_norm": 1.195141077041626,
+      "learning_rate": 1.5024828170856737e-05,
+      "loss": 0.5513,
+      "step": 525
+    },
+    {
+      "epoch": 1.5915915915915915,
+      "grad_norm": 1.0667812824249268,
+      "learning_rate": 1.4776554624891373e-05,
+      "loss": 0.5261,
+      "step": 530
+    },
+    {
+      "epoch": 1.6066066066066065,
+      "grad_norm": 1.5521669387817383,
+      "learning_rate": 1.4528342295466647e-05,
+      "loss": 0.4718,
+      "step": 535
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 1.3704042434692383,
+      "learning_rate": 1.4280259184438216e-05,
+      "loss": 0.4967,
+      "step": 540
+    },
+    {
+      "epoch": 1.6366366366366365,
+      "grad_norm": 1.3184561729431152,
+      "learning_rate": 1.4032373258260257e-05,
+      "loss": 0.4634,
+      "step": 545
+    },
+    {
+      "epoch": 1.6516516516516515,
+      "grad_norm": 1.2044627666473389,
+      "learning_rate": 1.378475242936489e-05,
+      "loss": 0.4878,
+      "step": 550
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.220750331878662,
+      "learning_rate": 1.3537464537556487e-05,
+      "loss": 0.5096,
+      "step": 555
+    },
+    {
+      "epoch": 1.6816816816816815,
+      "grad_norm": 1.1133580207824707,
+      "learning_rate": 1.3290577331425796e-05,
+      "loss": 0.4481,
+      "step": 560
+    },
+    {
+      "epoch": 1.6966966966966965,
+      "grad_norm": 1.167839527130127,
+      "learning_rate": 1.3044158449789148e-05,
+      "loss": 0.4439,
+      "step": 565
+    },
+    {
+      "epoch": 1.7117117117117115,
+      "grad_norm": 1.2148222923278809,
+      "learning_rate": 1.2798275403157663e-05,
+      "loss": 0.4517,
+      "step": 570
+    },
+    {
+      "epoch": 1.7267267267267268,
+      "grad_norm": 1.3124196529388428,
+      "learning_rate": 1.2552995555241616e-05,
+      "loss": 0.4705,
+      "step": 575
+    },
+    {
+      "epoch": 1.7417417417417418,
+      "grad_norm": 1.202958345413208,
+      "learning_rate": 1.2308386104495086e-05,
+      "loss": 0.418,
+      "step": 580
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 1.5169272422790527,
+      "learning_rate": 1.206451406570578e-05,
+      "loss": 0.4718,
+      "step": 585
+    },
+    {
+      "epoch": 1.7717717717717718,
+      "grad_norm": 1.2230910062789917,
+      "learning_rate": 1.1821446251635282e-05,
+      "loss": 0.4669,
+      "step": 590
+    },
+    {
+      "epoch": 1.7867867867867868,
+      "grad_norm": 1.345558524131775,
+      "learning_rate": 1.157924925471454e-05,
+      "loss": 0.4965,
+      "step": 595
+    },
+    {
+      "epoch": 1.8018018018018018,
+      "grad_norm": 1.2992432117462158,
+      "learning_rate": 1.1337989428799825e-05,
+      "loss": 0.4798,
+      "step": 600
+    },
+    {
+      "epoch": 1.8168168168168168,
+      "grad_norm": 1.3273664712905884,
+      "learning_rate": 1.1097732870993966e-05,
+      "loss": 0.4688,
+      "step": 605
+    },
+    {
+      "epoch": 1.8318318318318318,
+      "grad_norm": 1.3090227842330933,
+      "learning_rate": 1.0858545403537966e-05,
+      "loss": 0.4327,
+      "step": 610
+    },
+    {
+      "epoch": 1.8468468468468469,
+      "grad_norm": 1.4429737329483032,
+      "learning_rate": 1.0620492555777935e-05,
+      "loss": 0.4798,
+      "step": 615
+    },
+    {
+      "epoch": 1.8618618618618619,
+      "grad_norm": 1.3790085315704346,
+      "learning_rate": 1.0383639546212201e-05,
+      "loss": 0.4657,
+      "step": 620
+    },
+    {
+      "epoch": 1.8768768768768769,
+      "grad_norm": 1.22480309009552,
+      "learning_rate": 1.0148051264623685e-05,
+      "loss": 0.3955,
+      "step": 625
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 1.1307729482650757,
+      "learning_rate": 9.913792254302247e-06,
+      "loss": 0.434,
+      "step": 630
+    },
+    {
+      "epoch": 1.906906906906907,
+      "grad_norm": 1.239790678024292,
+      "learning_rate": 9.680926694361966e-06,
+      "loss": 0.4035,
+      "step": 635
+    },
+    {
+      "epoch": 1.921921921921922,
+      "grad_norm": 1.3346116542816162,
+      "learning_rate": 9.449518382158268e-06,
+      "loss": 0.4644,
+      "step": 640
+    },
+    {
+      "epoch": 1.936936936936937,
+      "grad_norm": 1.3505034446716309,
+      "learning_rate": 9.219630715809539e-06,
+      "loss": 0.4206,
+      "step": 645
+    },
+    {
+      "epoch": 1.951951951951952,
+      "grad_norm": 1.283050775527954,
+      "learning_rate": 8.991326676828208e-06,
+      "loss": 0.4157,
+      "step": 650
+    },
+    {
+      "epoch": 1.966966966966967,
+      "grad_norm": 1.2651106119155884,
+      "learning_rate": 8.76466881286588e-06,
+      "loss": 0.4181,
+      "step": 655
+    },
+    {
+      "epoch": 1.981981981981982,
+      "grad_norm": 1.3032163381576538,
+      "learning_rate": 8.539719220577426e-06,
+      "loss": 0.392,
+      "step": 660
+    },
+    {
+      "epoch": 1.996996996996997,
+      "grad_norm": 1.4221028089523315,
+      "learning_rate": 8.316539528608548e-06,
+      "loss": 0.4458,
+      "step": 665
+    },
+    {
+      "epoch": 2.012012012012012,
+      "grad_norm": 1.3767088651657104,
+      "learning_rate": 8.095190880711595e-06,
+      "loss": 0.3574,
+      "step": 670
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 1.3390811681747437,
+      "learning_rate": 7.875733918994251e-06,
+      "loss": 0.3285,
+      "step": 675
+    },
+    {
+      "epoch": 2.042042042042042,
+      "grad_norm": 1.2981222867965698,
+      "learning_rate": 7.658228767305602e-06,
+      "loss": 0.3435,
+      "step": 680
+    },
+    {
+      "epoch": 2.057057057057057,
+      "grad_norm": 1.383222222328186,
+      "learning_rate": 7.442735014764237e-06,
+      "loss": 0.3033,
+      "step": 685
+    },
+    {
+      "epoch": 2.0720720720720722,
+      "grad_norm": 1.26736319065094,
+      "learning_rate": 7.229311699432833e-06,
+      "loss": 0.3622,
+      "step": 690
+    },
+    {
+      "epoch": 2.0870870870870872,
+      "grad_norm": 1.2942931652069092,
+      "learning_rate": 7.018017292143665e-06,
+      "loss": 0.3619,
+      "step": 695
+    },
+    {
+      "epoch": 2.1021021021021022,
+      "grad_norm": 1.2717978954315186,
+      "learning_rate": 6.8089096804796135e-06,
+      "loss": 0.3593,
+      "step": 700
+    },
+    {
+      "epoch": 2.1171171171171173,
+      "grad_norm": 1.3928852081298828,
+      "learning_rate": 6.602046152914866e-06,
+      "loss": 0.3528,
+      "step": 705
+    },
+    {
+      "epoch": 2.1321321321321323,
+      "grad_norm": 1.2075221538543701,
+      "learning_rate": 6.397483383119827e-06,
+      "loss": 0.3308,
+      "step": 710
+    },
+    {
+      "epoch": 2.1471471471471473,
+      "grad_norm": 1.3162615299224854,
+      "learning_rate": 6.19527741443439e-06,
+      "loss": 0.3547,
+      "step": 715
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 1.269258975982666,
+      "learning_rate": 5.995483644513992e-06,
+      "loss": 0.4106,
+      "step": 720
+    },
+    {
+      "epoch": 2.1771771771771773,
+      "grad_norm": 1.2482011318206787,
+      "learning_rate": 5.798156810152491e-06,
+      "loss": 0.3618,
+      "step": 725
+    },
+    {
+      "epoch": 2.1921921921921923,
+      "grad_norm": 1.2571535110473633,
+      "learning_rate": 5.603350972286093e-06,
+      "loss": 0.3535,
+      "step": 730
+    },
+    {
+      "epoch": 2.2072072072072073,
+      "grad_norm": 1.5052522420883179,
+      "learning_rate": 5.411119501182525e-06,
+      "loss": 0.367,
+      "step": 735
+    },
+    {
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.2361116409301758,
+      "learning_rate": 5.2215150618193115e-06,
+      "loss": 0.3222,
+      "step": 740
+    },
+    {
+      "epoch": 2.2372372372372373,
+      "grad_norm": 1.1828457117080688,
+      "learning_rate": 5.034589599455392e-06,
+      "loss": 0.3099,
+      "step": 745
+    },
+    {
+      "epoch": 2.2522522522522523,
+      "grad_norm": 1.35744309425354,
+      "learning_rate": 4.850394325399809e-06,
+      "loss": 0.3155,
+      "step": 750
+    },
+    {
+      "epoch": 2.2672672672672673,
+      "grad_norm": 1.571617841720581,
+      "learning_rate": 4.668979702981568e-06,
+      "loss": 0.3668,
+      "step": 755
+    },
+    {
+      "epoch": 2.2822822822822824,
+      "grad_norm": 1.4292407035827637,
+      "learning_rate": 4.490395433724365e-06,
+      "loss": 0.3346,
+      "step": 760
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 1.4717832803726196,
+      "learning_rate": 4.314690443730014e-06,
+      "loss": 0.3474,
+      "step": 765
+    },
+    {
+      "epoch": 2.3123123123123124,
+      "grad_norm": 1.3873339891433716,
+      "learning_rate": 4.141912870274372e-06,
+      "loss": 0.3386,
+      "step": 770
+    },
+    {
+      "epoch": 2.3273273273273274,
+      "grad_norm": 1.247406244277954,
+      "learning_rate": 3.972110048619306e-06,
+      "loss": 0.3356,
+      "step": 775
+    },
+    {
+      "epoch": 2.3423423423423424,
+      "grad_norm": 1.3082075119018555,
+      "learning_rate": 3.805328499044449e-06,
+      "loss": 0.2945,
+      "step": 780
+    },
+    {
+      "epoch": 2.3573573573573574,
+      "grad_norm": 1.1410104036331177,
+      "learning_rate": 3.641613914102168e-06,
+      "loss": 0.3169,
+      "step": 785
+    },
+    {
+      "epoch": 2.3723723723723724,
+      "grad_norm": 1.461309790611267,
+      "learning_rate": 3.4810111460993733e-06,
+      "loss": 0.3336,
+      "step": 790
+    },
+    {
+      "epoch": 2.3873873873873874,
+      "grad_norm": 1.247636318206787,
+      "learning_rate": 3.3235641948094736e-06,
+      "loss": 0.3093,
+      "step": 795
+    },
+    {
+      "epoch": 2.4024024024024024,
+      "grad_norm": 1.3898581266403198,
+      "learning_rate": 3.1693161954178963e-06,
+      "loss": 0.329,
+      "step": 800
+    },
+    {
+      "epoch": 2.4174174174174174,
+      "grad_norm": 1.3026165962219238,
+      "learning_rate": 3.01830940670453e-06,
+      "loss": 0.3348,
+      "step": 805
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 1.4054383039474487,
+      "learning_rate": 2.870585199466199e-06,
+      "loss": 0.3092,
+      "step": 810
+    },
+    {
+      "epoch": 2.4474474474474475,
+      "grad_norm": 1.4873379468917847,
+      "learning_rate": 2.7261840451824787e-06,
+      "loss": 0.3401,
+      "step": 815
+    },
+    {
+      "epoch": 2.4624624624624625,
+      "grad_norm": 1.1497246026992798,
+      "learning_rate": 2.5851455049278568e-06,
+      "loss": 0.3246,
+      "step": 820
+    },
+    {
+      "epoch": 2.4774774774774775,
+      "grad_norm": 1.2546913623809814,
+      "learning_rate": 2.447508218533321e-06,
+      "loss": 0.3299,
+      "step": 825
+    },
+    {
+      "epoch": 2.4924924924924925,
+      "grad_norm": 1.1396286487579346,
+      "learning_rate": 2.3133098940003545e-06,
+      "loss": 0.3244,
+      "step": 830
+    },
+    {
+      "epoch": 2.5075075075075075,
+      "grad_norm": 1.480946660041809,
+      "learning_rate": 2.1825872971701855e-06,
+      "loss": 0.3566,
+      "step": 835
+    },
+    {
+      "epoch": 2.5225225225225225,
+      "grad_norm": 1.2736468315124512,
+      "learning_rate": 2.0553762416512095e-06,
+      "loss": 0.3,
+      "step": 840
+    },
+    {
+      "epoch": 2.5375375375375375,
+      "grad_norm": 1.244612216949463,
+      "learning_rate": 1.9317115790072267e-06,
+      "loss": 0.3551,
+      "step": 845
+    },
+    {
+      "epoch": 2.5525525525525525,
+      "grad_norm": 1.502899169921875,
+      "learning_rate": 1.8116271892093167e-06,
+      "loss": 0.3379,
+      "step": 850
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 1.1430363655090332,
+      "learning_rate": 1.695155971353844e-06,
+      "loss": 0.2762,
+      "step": 855
+    },
+    {
+      "epoch": 2.5825825825825826,
+      "grad_norm": 1.282637357711792,
+      "learning_rate": 1.582329834649197e-06,
+      "loss": 0.318,
+      "step": 860
+    },
+    {
+      "epoch": 2.5975975975975976,
+      "grad_norm": 1.0939358472824097,
+      "learning_rate": 1.4731796896737682e-06,
+      "loss": 0.3304,
+      "step": 865
+    },
+    {
+      "epoch": 2.6126126126126126,
+      "grad_norm": 1.370607852935791,
+      "learning_rate": 1.367735439907456e-06,
+      "loss": 0.3132,
+      "step": 870
+    },
+    {
+      "epoch": 2.6276276276276276,
+      "grad_norm": 1.2452490329742432,
+      "learning_rate": 1.2660259735391417e-06,
+      "loss": 0.3115,
+      "step": 875
+    },
+    {
+      "epoch": 2.6426426426426426,
+      "grad_norm": 1.39225172996521,
+      "learning_rate": 1.1680791555522824e-06,
+      "loss": 0.3733,
+      "step": 880
+    },
+    {
+      "epoch": 2.6576576576576576,
+      "grad_norm": 1.2224600315093994,
+      "learning_rate": 1.0739218200908317e-06,
+      "loss": 0.3154,
+      "step": 885
+    },
+    {
+      "epoch": 2.6726726726726726,
+      "grad_norm": 1.4974796772003174,
+      "learning_rate": 9.835797631076055e-07,
+      "loss": 0.2844,
+      "step": 890
+    },
+    {
+      "epoch": 2.6876876876876876,
+      "grad_norm": 1.409374713897705,
+      "learning_rate": 8.970777352970322e-07,
+      "loss": 0.3037,
+      "step": 895
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 1.2999298572540283,
+      "learning_rate": 8.14439435314312e-07,
+      "loss": 0.3085,
+      "step": 900
+    },
+    {
+      "epoch": 2.7177177177177176,
+      "grad_norm": 1.228987693786621,
+      "learning_rate": 7.356875032827643e-07,
+      "loss": 0.3166,
+      "step": 905
+    },
+    {
+      "epoch": 2.7327327327327327,
+      "grad_norm": 1.3100334405899048,
+      "learning_rate": 6.608435145912062e-07,
+      "loss": 0.3036,
+      "step": 910
+    },
+    {
+      "epoch": 2.7477477477477477,
+      "grad_norm": 1.41297447681427,
+      "learning_rate": 5.899279739830126e-07,
+      "loss": 0.2832,
+      "step": 915
+    },
+    {
+      "epoch": 2.7627627627627627,
+      "grad_norm": 1.4600352048873901,
+      "learning_rate": 5.229603099385016e-07,
+      "loss": 0.3116,
+      "step": 920
+    },
+    {
+      "epoch": 2.7777777777777777,
+      "grad_norm": 1.304701805114746,
+      "learning_rate": 4.5995886935219e-07,
+      "loss": 0.3074,
+      "step": 925
+    },
+    {
+      "epoch": 2.7927927927927927,
+      "grad_norm": 1.1860195398330688,
+      "learning_rate": 4.009409125063479e-07,
+      "loss": 0.331,
+      "step": 930
+    },
+    {
+      "epoch": 2.8078078078078077,
+      "grad_norm": 1.3436297178268433,
+      "learning_rate": 3.4592260834227453e-07,
+      "loss": 0.3369,
+      "step": 935
+    },
+    {
+      "epoch": 2.8228228228228227,
+      "grad_norm": 1.3938167095184326,
+      "learning_rate": 2.9491903003054154e-07,
+      "loss": 0.3209,
+      "step": 940
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 1.2662007808685303,
+      "learning_rate": 2.479441508414515e-07,
+      "loss": 0.3125,
+      "step": 945
+    },
+    {
+      "epoch": 2.8528528528528527,
+      "grad_norm": 1.2462223768234253,
+      "learning_rate": 2.0501084031682493e-07,
+      "loss": 0.2904,
+      "step": 950
+    },
+    {
+      "epoch": 2.8678678678678677,
+      "grad_norm": 1.3806508779525757,
+      "learning_rate": 1.661308607441875e-07,
+      "loss": 0.3029,
+      "step": 955
+    },
+    {
+      "epoch": 2.8828828828828827,
+      "grad_norm": 1.2454555034637451,
+      "learning_rate": 1.3131486393429427e-07,
+      "loss": 0.3107,
+      "step": 960
+    },
+    {
+      "epoch": 2.8978978978978978,
+      "grad_norm": 1.1660720109939575,
+      "learning_rate": 1.0057238830288417e-07,
+      "loss": 0.289,
+      "step": 965
+    },
+    {
+      "epoch": 2.9129129129129128,
+      "grad_norm": 1.3258354663848877,
+      "learning_rate": 7.391185625748364e-08,
+      "loss": 0.3103,
+      "step": 970
+    },
+    {
+      "epoch": 2.9279279279279278,
+      "grad_norm": 1.3270028829574585,
+      "learning_rate": 5.134057188993901e-08,
+      "loss": 0.3137,
+      "step": 975
+    },
+    {
+      "epoch": 2.942942942942943,
+      "grad_norm": 1.1255927085876465,
+      "learning_rate": 3.2864718975350597e-08,
+      "loss": 0.285,
+      "step": 980
+    },
+    {
+      "epoch": 2.957957957957958,
+      "grad_norm": 1.2705459594726562,
+      "learning_rate": 1.848935927792117e-08,
+      "loss": 0.3244,
+      "step": 985
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 1.3995997905731201,
+      "learning_rate": 8.218431164198625e-09,
+      "loss": 0.2825,
+      "step": 990
+    },
+    {
+      "epoch": 2.987987987987988,
+      "grad_norm": 1.2223838567733765,
+      "learning_rate": 2.054748524099037e-09,
+      "loss": 0.3181,
+      "step": 995
+    },
+    {
+      "epoch": 3.0,
+      "step": 999,
+      "total_flos": 1.436218182569296e+18,
+      "train_loss": 0.6181889377437435,
+      "train_runtime": 688.4097,
+      "train_samples_per_second": 46.411,
+      "train_steps_per_second": 1.451
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 999,
+  "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": 1.436218182569296e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

34_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a4e6415a415835e1721ac15bca4897a22bfffa0ca49a3c0b6aaa1043029005e
+size 8145