Upload folder using huggingface_hub

49_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

49_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: 49_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. -->
+
+# 49_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

49_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": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

49_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f910e7be805689b2c6f2230cd5a3e6205c095cf470e72c352b51a44d960b5c7
+size 791751704

49_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.8582176454431212e+18,
+    "train_loss": 0.5394563638152684,
+    "train_runtime": 871.0297,
+    "train_samples": 12438,
+    "train_samples_per_second": 42.839,
+    "train_steps_per_second": 1.34
+}

49_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
+}

49_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
+  }
+}

49_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
+}

49_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.8582176454431212e+18,
+    "train_loss": 0.5394563638152684,
+    "train_runtime": 871.0297,
+    "train_samples": 12438,
+    "train_samples_per_second": 42.839,
+    "train_steps_per_second": 1.34
+}

49_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1674 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1167,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012853470437017995,
+      "grad_norm": 0.9604760408401489,
+      "learning_rate": 2.033898305084746e-06,
+      "loss": 1.273,
+      "step": 5
+    },
+    {
+      "epoch": 0.02570694087403599,
+      "grad_norm": 0.7636861801147461,
+      "learning_rate": 4.576271186440678e-06,
+      "loss": 1.3104,
+      "step": 10
+    },
+    {
+      "epoch": 0.038560411311053984,
+      "grad_norm": 0.8130346536636353,
+      "learning_rate": 7.1186440677966106e-06,
+      "loss": 1.2719,
+      "step": 15
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.5278398990631104,
+      "learning_rate": 9.661016949152542e-06,
+      "loss": 1.2795,
+      "step": 20
+    },
+    {
+      "epoch": 0.06426735218508997,
+      "grad_norm": 0.5267850160598755,
+      "learning_rate": 1.2203389830508475e-05,
+      "loss": 1.2154,
+      "step": 25
+    },
+    {
+      "epoch": 0.07712082262210797,
+      "grad_norm": 0.46455225348472595,
+      "learning_rate": 1.4745762711864408e-05,
+      "loss": 1.1493,
+      "step": 30
+    },
+    {
+      "epoch": 0.08997429305912596,
+      "grad_norm": 0.41945594549179077,
+      "learning_rate": 1.728813559322034e-05,
+      "loss": 1.1774,
+      "step": 35
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 0.62894606590271,
+      "learning_rate": 1.983050847457627e-05,
+      "loss": 1.1306,
+      "step": 40
+    },
+    {
+      "epoch": 0.11568123393316196,
+      "grad_norm": 0.41832807660102844,
+      "learning_rate": 2.2372881355932205e-05,
+      "loss": 1.1525,
+      "step": 45
+    },
+    {
+      "epoch": 0.12853470437017994,
+      "grad_norm": 0.4818113446235657,
+      "learning_rate": 2.4915254237288138e-05,
+      "loss": 1.1368,
+      "step": 50
+    },
+    {
+      "epoch": 0.14138817480719795,
+      "grad_norm": 0.4366658329963684,
+      "learning_rate": 2.7457627118644068e-05,
+      "loss": 1.131,
+      "step": 55
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.4142184555530548,
+      "learning_rate": 3e-05,
+      "loss": 1.1335,
+      "step": 60
+    },
+    {
+      "epoch": 0.16709511568123395,
+      "grad_norm": 0.4652119278907776,
+      "learning_rate": 2.9998492649592036e-05,
+      "loss": 1.1501,
+      "step": 65
+    },
+    {
+      "epoch": 0.17994858611825193,
+      "grad_norm": 0.47485363483428955,
+      "learning_rate": 2.9993970901315514e-05,
+      "loss": 1.0901,
+      "step": 70
+    },
+    {
+      "epoch": 0.1928020565552699,
+      "grad_norm": 0.4693622887134552,
+      "learning_rate": 2.9986435663951645e-05,
+      "loss": 1.0861,
+      "step": 75
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.6187178492546082,
+      "learning_rate": 2.997588845193284e-05,
+      "loss": 1.0876,
+      "step": 80
+    },
+    {
+      "epoch": 0.2185089974293059,
+      "grad_norm": 0.8080940842628479,
+      "learning_rate": 2.9962331385038356e-05,
+      "loss": 1.0768,
+      "step": 85
+    },
+    {
+      "epoch": 0.23136246786632392,
+      "grad_norm": 0.5959859490394592,
+      "learning_rate": 2.9945767187968226e-05,
+      "loss": 1.0474,
+      "step": 90
+    },
+    {
+      "epoch": 0.2442159383033419,
+      "grad_norm": 0.5025818347930908,
+      "learning_rate": 2.9926199189795684e-05,
+      "loss": 1.0082,
+      "step": 95
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.5009885430335999,
+      "learning_rate": 2.990363132329806e-05,
+      "loss": 1.0472,
+      "step": 100
+    },
+    {
+      "epoch": 0.2699228791773779,
+      "grad_norm": 0.5792273283004761,
+      "learning_rate": 2.9878068124166394e-05,
+      "loss": 1.0235,
+      "step": 105
+    },
+    {
+      "epoch": 0.2827763496143959,
+      "grad_norm": 0.5140129923820496,
+      "learning_rate": 2.9849514730093843e-05,
+      "loss": 1.0819,
+      "step": 110
+    },
+    {
+      "epoch": 0.29562982005141386,
+      "grad_norm": 0.5050700306892395,
+      "learning_rate": 2.9817976879743092e-05,
+      "loss": 1.0596,
+      "step": 115
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.5441417098045349,
+      "learning_rate": 2.9783460911593024e-05,
+      "loss": 0.9743,
+      "step": 120
+    },
+    {
+      "epoch": 0.3213367609254499,
+      "grad_norm": 0.5327843427658081,
+      "learning_rate": 2.97459737626648e-05,
+      "loss": 0.9851,
+      "step": 125
+    },
+    {
+      "epoch": 0.3341902313624679,
+      "grad_norm": 0.6015195846557617,
+      "learning_rate": 2.970552296712764e-05,
+      "loss": 0.9801,
+      "step": 130
+    },
+    {
+      "epoch": 0.34704370179948585,
+      "grad_norm": 0.6730561852455139,
+      "learning_rate": 2.966211665478464e-05,
+      "loss": 0.9669,
+      "step": 135
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.582878053188324,
+      "learning_rate": 2.961576354943881e-05,
+      "loss": 0.9148,
+      "step": 140
+    },
+    {
+      "epoch": 0.37275064267352187,
+      "grad_norm": 0.6537643671035767,
+      "learning_rate": 2.9566472967139796e-05,
+      "loss": 0.9628,
+      "step": 145
+    },
+    {
+      "epoch": 0.3856041131105398,
+      "grad_norm": 0.5790269374847412,
+      "learning_rate": 2.9514254814311492e-05,
+      "loss": 0.9042,
+      "step": 150
+    },
+    {
+      "epoch": 0.39845758354755784,
+      "grad_norm": 0.7693259119987488,
+      "learning_rate": 2.9459119585761107e-05,
+      "loss": 0.8871,
+      "step": 155
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.6483209133148193,
+      "learning_rate": 2.9401078362569866e-05,
+      "loss": 0.9224,
+      "step": 160
+    },
+    {
+      "epoch": 0.4241645244215938,
+      "grad_norm": 0.6751565933227539,
+      "learning_rate": 2.9340142809865967e-05,
+      "loss": 0.9185,
+      "step": 165
+    },
+    {
+      "epoch": 0.4370179948586118,
+      "grad_norm": 0.6384418606758118,
+      "learning_rate": 2.9276325174480108e-05,
+      "loss": 0.8835,
+      "step": 170
+    },
+    {
+      "epoch": 0.4498714652956298,
+      "grad_norm": 1.143051266670227,
+      "learning_rate": 2.9209638282484122e-05,
+      "loss": 0.9271,
+      "step": 175
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.6958455443382263,
+      "learning_rate": 2.9140095536613182e-05,
+      "loss": 0.8937,
+      "step": 180
+    },
+    {
+      "epoch": 0.4755784061696658,
+      "grad_norm": 0.7605907320976257,
+      "learning_rate": 2.9067710913572146e-05,
+      "loss": 0.8564,
+      "step": 185
+    },
+    {
+      "epoch": 0.4884318766066838,
+      "grad_norm": 0.715293288230896,
+      "learning_rate": 2.8992498961226482e-05,
+      "loss": 0.8638,
+      "step": 190
+    },
+    {
+      "epoch": 0.5012853470437018,
+      "grad_norm": 0.788199245929718,
+      "learning_rate": 2.8914474795678462e-05,
+      "loss": 0.8409,
+      "step": 195
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.7671679258346558,
+      "learning_rate": 2.8833654098229132e-05,
+      "loss": 0.9372,
+      "step": 200
+    },
+    {
+      "epoch": 0.5269922879177378,
+      "grad_norm": 0.8497247695922852,
+      "learning_rate": 2.8750053112226654e-05,
+      "loss": 0.8105,
+      "step": 205
+    },
+    {
+      "epoch": 0.5398457583547558,
+      "grad_norm": 0.807873010635376,
+      "learning_rate": 2.8663688639801748e-05,
+      "loss": 0.848,
+      "step": 210
+    },
+    {
+      "epoch": 0.5526992287917738,
+      "grad_norm": 0.7143222689628601,
+      "learning_rate": 2.8574578038490772e-05,
+      "loss": 0.8283,
+      "step": 215
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.7607510089874268,
+      "learning_rate": 2.8482739217747228e-05,
+      "loss": 0.8444,
+      "step": 220
+    },
+    {
+      "epoch": 0.5784061696658098,
+      "grad_norm": 0.7231160998344421,
+      "learning_rate": 2.838819063534231e-05,
+      "loss": 0.8572,
+      "step": 225
+    },
+    {
+      "epoch": 0.5912596401028277,
+      "grad_norm": 0.7305110096931458,
+      "learning_rate": 2.8290951293655244e-05,
+      "loss": 0.8119,
+      "step": 230
+    },
+    {
+      "epoch": 0.6041131105398457,
+      "grad_norm": 0.803169846534729,
+      "learning_rate": 2.819104073585422e-05,
+      "loss": 0.8202,
+      "step": 235
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.7558185458183289,
+      "learning_rate": 2.808847904196857e-05,
+      "loss": 0.7891,
+      "step": 240
+    },
+    {
+      "epoch": 0.6298200514138818,
+      "grad_norm": 0.91909259557724,
+      "learning_rate": 2.798328682485312e-05,
+      "loss": 0.7905,
+      "step": 245
+    },
+    {
+      "epoch": 0.6426735218508998,
+      "grad_norm": 0.8484181761741638,
+      "learning_rate": 2.7875485226045385e-05,
+      "loss": 0.8101,
+      "step": 250
+    },
+    {
+      "epoch": 0.6555269922879178,
+      "grad_norm": 0.8669614791870117,
+      "learning_rate": 2.7765095911516548e-05,
+      "loss": 0.7814,
+      "step": 255
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.8128072619438171,
+      "learning_rate": 2.765214106731706e-05,
+      "loss": 0.7744,
+      "step": 260
+    },
+    {
+      "epoch": 0.6812339331619537,
+      "grad_norm": 0.800499677658081,
+      "learning_rate": 2.7536643395117645e-05,
+      "loss": 0.7885,
+      "step": 265
+    },
+    {
+      "epoch": 0.6940874035989717,
+      "grad_norm": 0.8798700571060181,
+      "learning_rate": 2.7418626107646747e-05,
+      "loss": 0.7366,
+      "step": 270
+    },
+    {
+      "epoch": 0.7069408740359897,
+      "grad_norm": 0.7950812578201294,
+      "learning_rate": 2.729811292402522e-05,
+      "loss": 0.813,
+      "step": 275
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.8756250739097595,
+      "learning_rate": 2.7175128064999272e-05,
+      "loss": 0.7826,
+      "step": 280
+    },
+    {
+      "epoch": 0.7326478149100257,
+      "grad_norm": 0.9733713865280151,
+      "learning_rate": 2.704969624807254e-05,
+      "loss": 0.7632,
+      "step": 285
+    },
+    {
+      "epoch": 0.7455012853470437,
+      "grad_norm": 0.8784929513931274,
+      "learning_rate": 2.6921842682538436e-05,
+      "loss": 0.7314,
+      "step": 290
+    },
+    {
+      "epoch": 0.7583547557840618,
+      "grad_norm": 0.8444457650184631,
+      "learning_rate": 2.6791593064413498e-05,
+      "loss": 0.7321,
+      "step": 295
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.9540085196495056,
+      "learning_rate": 2.6658973571273077e-05,
+      "loss": 0.7795,
+      "step": 300
+    },
+    {
+      "epoch": 0.7840616966580977,
+      "grad_norm": 1.0279449224472046,
+      "learning_rate": 2.65240108569901e-05,
+      "loss": 0.7133,
+      "step": 305
+    },
+    {
+      "epoch": 0.7969151670951157,
+      "grad_norm": 0.8875748515129089,
+      "learning_rate": 2.6386732046378242e-05,
+      "loss": 0.7217,
+      "step": 310
+    },
+    {
+      "epoch": 0.8097686375321337,
+      "grad_norm": 0.9406142830848694,
+      "learning_rate": 2.6247164729740317e-05,
+      "loss": 0.6852,
+      "step": 315
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.8615289926528931,
+      "learning_rate": 2.6105336957323214e-05,
+      "loss": 0.7132,
+      "step": 320
+    },
+    {
+      "epoch": 0.8354755784061697,
+      "grad_norm": 0.9051153063774109,
+      "learning_rate": 2.5961277233680356e-05,
+      "loss": 0.7187,
+      "step": 325
+    },
+    {
+      "epoch": 0.8483290488431876,
+      "grad_norm": 0.926743745803833,
+      "learning_rate": 2.5815014511942828e-05,
+      "loss": 0.6838,
+      "step": 330
+    },
+    {
+      "epoch": 0.8611825192802056,
+      "grad_norm": 0.912087619304657,
+      "learning_rate": 2.566657818800041e-05,
+      "loss": 0.6964,
+      "step": 335
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 1.197026252746582,
+      "learning_rate": 2.5515998094593555e-05,
+      "loss": 0.6518,
+      "step": 340
+    },
+    {
+      "epoch": 0.8868894601542416,
+      "grad_norm": 0.8640385866165161,
+      "learning_rate": 2.5363304495317633e-05,
+      "loss": 0.6303,
+      "step": 345
+    },
+    {
+      "epoch": 0.8997429305912596,
+      "grad_norm": 0.9316200613975525,
+      "learning_rate": 2.5208528078540524e-05,
+      "loss": 0.6307,
+      "step": 350
+    },
+    {
+      "epoch": 0.9125964010282777,
+      "grad_norm": 0.9494955539703369,
+      "learning_rate": 2.50516999512349e-05,
+      "loss": 0.6274,
+      "step": 355
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.8832476139068604,
+      "learning_rate": 2.4892851632726306e-05,
+      "loss": 0.6386,
+      "step": 360
+    },
+    {
+      "epoch": 0.9383033419023136,
+      "grad_norm": 1.0047895908355713,
+      "learning_rate": 2.4732015048358447e-05,
+      "loss": 0.6535,
+      "step": 365
+    },
+    {
+      "epoch": 0.9511568123393316,
+      "grad_norm": 0.9000934958457947,
+      "learning_rate": 2.4569222523076796e-05,
+      "loss": 0.6528,
+      "step": 370
+    },
+    {
+      "epoch": 0.9640102827763496,
+      "grad_norm": 0.9459851980209351,
+      "learning_rate": 2.440450677493194e-05,
+      "loss": 0.6359,
+      "step": 375
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.9937883019447327,
+      "learning_rate": 2.4237900908503894e-05,
+      "loss": 0.6132,
+      "step": 380
+    },
+    {
+      "epoch": 0.9897172236503856,
+      "grad_norm": 0.9391217231750488,
+      "learning_rate": 2.406943840824876e-05,
+      "loss": 0.6775,
+      "step": 385
+    },
+    {
+      "epoch": 1.0025706940874035,
+      "grad_norm": 1.0621761083602905,
+      "learning_rate": 2.3899153131769004e-05,
+      "loss": 0.5779,
+      "step": 390
+    },
+    {
+      "epoch": 1.0154241645244215,
+      "grad_norm": 1.1610355377197266,
+      "learning_rate": 2.3727079303008752e-05,
+      "loss": 0.5174,
+      "step": 395
+    },
+    {
+      "epoch": 1.0282776349614395,
+      "grad_norm": 1.0333514213562012,
+      "learning_rate": 2.355325150537548e-05,
+      "loss": 0.5463,
+      "step": 400
+    },
+    {
+      "epoch": 1.0411311053984575,
+      "grad_norm": 1.0891033411026,
+      "learning_rate": 2.337770467478939e-05,
+      "loss": 0.5143,
+      "step": 405
+    },
+    {
+      "epoch": 1.0539845758354756,
+      "grad_norm": 1.020695686340332,
+      "learning_rate": 2.320047409266206e-05,
+      "loss": 0.5294,
+      "step": 410
+    },
+    {
+      "epoch": 1.0668380462724936,
+      "grad_norm": 1.1019823551177979,
+      "learning_rate": 2.3021595378805517e-05,
+      "loss": 0.5681,
+      "step": 415
+    },
+    {
+      "epoch": 1.0796915167095116,
+      "grad_norm": 1.0059539079666138,
+      "learning_rate": 2.284110448427341e-05,
+      "loss": 0.567,
+      "step": 420
+    },
+    {
+      "epoch": 1.0925449871465296,
+      "grad_norm": 1.012967824935913,
+      "learning_rate": 2.2659037684135527e-05,
+      "loss": 0.5236,
+      "step": 425
+    },
+    {
+      "epoch": 1.1053984575835476,
+      "grad_norm": 0.8912418484687805,
+      "learning_rate": 2.2475431570187282e-05,
+      "loss": 0.5411,
+      "step": 430
+    },
+    {
+      "epoch": 1.1182519280205656,
+      "grad_norm": 1.1079907417297363,
+      "learning_rate": 2.2290323043595433e-05,
+      "loss": 0.5168,
+      "step": 435
+    },
+    {
+      "epoch": 1.1311053984575836,
+      "grad_norm": 1.075018286705017,
+      "learning_rate": 2.210374930748172e-05,
+      "loss": 0.5321,
+      "step": 440
+    },
+    {
+      "epoch": 1.1439588688946016,
+      "grad_norm": 1.0196655988693237,
+      "learning_rate": 2.1915747859445784e-05,
+      "loss": 0.5887,
+      "step": 445
+    },
+    {
+      "epoch": 1.1568123393316196,
+      "grad_norm": 1.1480021476745605,
+      "learning_rate": 2.1726356484028865e-05,
+      "loss": 0.4976,
+      "step": 450
+    },
+    {
+      "epoch": 1.1696658097686377,
+      "grad_norm": 1.1243963241577148,
+      "learning_rate": 2.1535613245119913e-05,
+      "loss": 0.478,
+      "step": 455
+    },
+    {
+      "epoch": 1.1825192802056554,
+      "grad_norm": 1.0790624618530273,
+      "learning_rate": 2.1343556478305444e-05,
+      "loss": 0.52,
+      "step": 460
+    },
+    {
+      "epoch": 1.1953727506426735,
+      "grad_norm": 1.0526539087295532,
+      "learning_rate": 2.1150224783164913e-05,
+      "loss": 0.4827,
+      "step": 465
+    },
+    {
+      "epoch": 1.2082262210796915,
+      "grad_norm": 1.1312202215194702,
+      "learning_rate": 2.0955657015512916e-05,
+      "loss": 0.5017,
+      "step": 470
+    },
+    {
+      "epoch": 1.2210796915167095,
+      "grad_norm": 1.0134834051132202,
+      "learning_rate": 2.0759892279589983e-05,
+      "loss": 0.505,
+      "step": 475
+    },
+    {
+      "epoch": 1.2339331619537275,
+      "grad_norm": 0.9722588658332825,
+      "learning_rate": 2.056296992020339e-05,
+      "loss": 0.5298,
+      "step": 480
+    },
+    {
+      "epoch": 1.2467866323907455,
+      "grad_norm": 1.0303668975830078,
+      "learning_rate": 2.036492951481963e-05,
+      "loss": 0.4743,
+      "step": 485
+    },
+    {
+      "epoch": 1.2596401028277635,
+      "grad_norm": 0.9975312352180481,
+      "learning_rate": 2.016581086561016e-05,
+      "loss": 0.4836,
+      "step": 490
+    },
+    {
+      "epoch": 1.2724935732647815,
+      "grad_norm": 1.1557528972625732,
+      "learning_rate": 1.996565399145192e-05,
+      "loss": 0.4743,
+      "step": 495
+    },
+    {
+      "epoch": 1.2853470437017995,
+      "grad_norm": 1.1802899837493896,
+      "learning_rate": 1.976449911988438e-05,
+      "loss": 0.544,
+      "step": 500
+    },
+    {
+      "epoch": 1.2982005141388175,
+      "grad_norm": 1.479546308517456,
+      "learning_rate": 1.956238667902455e-05,
+      "loss": 0.4948,
+      "step": 505
+    },
+    {
+      "epoch": 1.3110539845758356,
+      "grad_norm": 0.971333384513855,
+      "learning_rate": 1.93593572894418e-05,
+      "loss": 0.4858,
+      "step": 510
+    },
+    {
+      "epoch": 1.3239074550128533,
+      "grad_norm": 1.181843876838684,
+      "learning_rate": 1.9155451755993896e-05,
+      "loss": 0.4797,
+      "step": 515
+    },
+    {
+      "epoch": 1.3367609254498714,
+      "grad_norm": 1.0240259170532227,
+      "learning_rate": 1.8950711059626032e-05,
+      "loss": 0.4533,
+      "step": 520
+    },
+    {
+      "epoch": 1.3496143958868894,
+      "grad_norm": 1.1917214393615723,
+      "learning_rate": 1.8745176349134498e-05,
+      "loss": 0.4788,
+      "step": 525
+    },
+    {
+      "epoch": 1.3624678663239074,
+      "grad_norm": 1.0517791509628296,
+      "learning_rate": 1.853888893289661e-05,
+      "loss": 0.4834,
+      "step": 530
+    },
+    {
+      "epoch": 1.3753213367609254,
+      "grad_norm": 1.1179429292678833,
+      "learning_rate": 1.833189027056848e-05,
+      "loss": 0.4413,
+      "step": 535
+    },
+    {
+      "epoch": 1.3881748071979434,
+      "grad_norm": 1.0520955324172974,
+      "learning_rate": 1.8124221964752535e-05,
+      "loss": 0.4475,
+      "step": 540
+    },
+    {
+      "epoch": 1.4010282776349614,
+      "grad_norm": 1.0830186605453491,
+      "learning_rate": 1.7915925752636164e-05,
+      "loss": 0.4255,
+      "step": 545
+    },
+    {
+      "epoch": 1.4138817480719794,
+      "grad_norm": 1.0880262851715088,
+      "learning_rate": 1.7707043497603426e-05,
+      "loss": 0.494,
+      "step": 550
+    },
+    {
+      "epoch": 1.4267352185089974,
+      "grad_norm": 1.0987969636917114,
+      "learning_rate": 1.7497617180821287e-05,
+      "loss": 0.4767,
+      "step": 555
+    },
+    {
+      "epoch": 1.4395886889460154,
+      "grad_norm": 1.0733847618103027,
+      "learning_rate": 1.728768889280229e-05,
+      "loss": 0.4312,
+      "step": 560
+    },
+    {
+      "epoch": 1.4524421593830334,
+      "grad_norm": 1.0616512298583984,
+      "learning_rate": 1.7077300824945174e-05,
+      "loss": 0.4768,
+      "step": 565
+    },
+    {
+      "epoch": 1.4652956298200515,
+      "grad_norm": 1.136430263519287,
+      "learning_rate": 1.6866495261055265e-05,
+      "loss": 0.4573,
+      "step": 570
+    },
+    {
+      "epoch": 1.4781491002570695,
+      "grad_norm": 1.0720285177230835,
+      "learning_rate": 1.6655314568846265e-05,
+      "loss": 0.4503,
+      "step": 575
+    },
+    {
+      "epoch": 1.4910025706940875,
+      "grad_norm": 1.0543419122695923,
+      "learning_rate": 1.6443801191425176e-05,
+      "loss": 0.4801,
+      "step": 580
+    },
+    {
+      "epoch": 1.5038560411311055,
+      "grad_norm": 1.1782740354537964,
+      "learning_rate": 1.6231997638762096e-05,
+      "loss": 0.4794,
+      "step": 585
+    },
+    {
+      "epoch": 1.5167095115681235,
+      "grad_norm": 0.9905291199684143,
+      "learning_rate": 1.6019946479146567e-05,
+      "loss": 0.464,
+      "step": 590
+    },
+    {
+      "epoch": 1.5295629820051415,
+      "grad_norm": 1.181352972984314,
+      "learning_rate": 1.5807690330632176e-05,
+      "loss": 0.3982,
+      "step": 595
+    },
+    {
+      "epoch": 1.5424164524421595,
+      "grad_norm": 1.0374727249145508,
+      "learning_rate": 1.5595271852471204e-05,
+      "loss": 0.418,
+      "step": 600
+    },
+    {
+      "epoch": 1.5552699228791775,
+      "grad_norm": 1.2970150709152222,
+      "learning_rate": 1.5382733736540936e-05,
+      "loss": 0.4703,
+      "step": 605
+    },
+    {
+      "epoch": 1.5681233933161953,
+      "grad_norm": 1.1550183296203613,
+      "learning_rate": 1.517011869876348e-05,
+      "loss": 0.4465,
+      "step": 610
+    },
+    {
+      "epoch": 1.5809768637532133,
+      "grad_norm": 1.1831550598144531,
+      "learning_rate": 1.4957469470520697e-05,
+      "loss": 0.443,
+      "step": 615
+    },
+    {
+      "epoch": 1.5938303341902313,
+      "grad_norm": 0.9924294352531433,
+      "learning_rate": 1.4744828790066041e-05,
+      "loss": 0.4229,
+      "step": 620
+    },
+    {
+      "epoch": 1.6066838046272494,
+      "grad_norm": 1.1424195766448975,
+      "learning_rate": 1.4532239393935035e-05,
+      "loss": 0.4545,
+      "step": 625
+    },
+    {
+      "epoch": 1.6195372750642674,
+      "grad_norm": 1.1600099802017212,
+      "learning_rate": 1.4319744008356085e-05,
+      "loss": 0.4347,
+      "step": 630
+    },
+    {
+      "epoch": 1.6323907455012854,
+      "grad_norm": 1.1284782886505127,
+      "learning_rate": 1.4107385340663331e-05,
+      "loss": 0.3835,
+      "step": 635
+    },
+    {
+      "epoch": 1.6452442159383034,
+      "grad_norm": 1.179620623588562,
+      "learning_rate": 1.3895206070713373e-05,
+      "loss": 0.4049,
+      "step": 640
+    },
+    {
+      "epoch": 1.6580976863753212,
+      "grad_norm": 1.1133368015289307,
+      "learning_rate": 1.3683248842307416e-05,
+      "loss": 0.402,
+      "step": 645
+    },
+    {
+      "epoch": 1.6709511568123392,
+      "grad_norm": 1.0367546081542969,
+      "learning_rate": 1.3471556254620751e-05,
+      "loss": 0.417,
+      "step": 650
+    },
+    {
+      "epoch": 1.6838046272493572,
+      "grad_norm": 1.139487385749817,
+      "learning_rate": 1.3260170853641178e-05,
+      "loss": 0.4127,
+      "step": 655
+    },
+    {
+      "epoch": 1.6966580976863752,
+      "grad_norm": 1.0176481008529663,
+      "learning_rate": 1.3049135123618073e-05,
+      "loss": 0.4179,
+      "step": 660
+    },
+    {
+      "epoch": 1.7095115681233932,
+      "grad_norm": 1.0314640998840332,
+      "learning_rate": 1.283849147852395e-05,
+      "loss": 0.4198,
+      "step": 665
+    },
+    {
+      "epoch": 1.7223650385604112,
+      "grad_norm": 1.2407605648040771,
+      "learning_rate": 1.2628282253530037e-05,
+      "loss": 0.3863,
+      "step": 670
+    },
+    {
+      "epoch": 1.7352185089974292,
+      "grad_norm": 1.2207111120224,
+      "learning_rate": 1.2418549696497832e-05,
+      "loss": 0.4148,
+      "step": 675
+    },
+    {
+      "epoch": 1.7480719794344473,
+      "grad_norm": 1.3839921951293945,
+      "learning_rate": 1.2209335959488037e-05,
+      "loss": 0.4062,
+      "step": 680
+    },
+    {
+      "epoch": 1.7609254498714653,
+      "grad_norm": 1.17417573928833,
+      "learning_rate": 1.2000683090288901e-05,
+      "loss": 0.3793,
+      "step": 685
+    },
+    {
+      "epoch": 1.7737789203084833,
+      "grad_norm": 1.0947905778884888,
+      "learning_rate": 1.1792633023965433e-05,
+      "loss": 0.3913,
+      "step": 690
+    },
+    {
+      "epoch": 1.7866323907455013,
+      "grad_norm": 1.081061601638794,
+      "learning_rate": 1.1585227574431263e-05,
+      "loss": 0.3699,
+      "step": 695
+    },
+    {
+      "epoch": 1.7994858611825193,
+      "grad_norm": 1.1680364608764648,
+      "learning_rate": 1.1378508426044943e-05,
+      "loss": 0.3838,
+      "step": 700
+    },
+    {
+      "epoch": 1.8123393316195373,
+      "grad_norm": 0.9839363098144531,
+      "learning_rate": 1.1172517125232142e-05,
+      "loss": 0.3677,
+      "step": 705
+    },
+    {
+      "epoch": 1.8251928020565553,
+      "grad_norm": 1.1776559352874756,
+      "learning_rate": 1.0967295072135706e-05,
+      "loss": 0.3772,
+      "step": 710
+    },
+    {
+      "epoch": 1.8380462724935733,
+      "grad_norm": 1.2421525716781616,
+      "learning_rate": 1.0762883512295037e-05,
+      "loss": 0.3676,
+      "step": 715
+    },
+    {
+      "epoch": 1.8508997429305913,
+      "grad_norm": 1.1171281337738037,
+      "learning_rate": 1.0559323528356542e-05,
+      "loss": 0.3715,
+      "step": 720
+    },
+    {
+      "epoch": 1.8637532133676094,
+      "grad_norm": 1.3870981931686401,
+      "learning_rate": 1.0356656031816873e-05,
+      "loss": 0.3696,
+      "step": 725
+    },
+    {
+      "epoch": 1.8766066838046274,
+      "grad_norm": 1.24127197265625,
+      "learning_rate": 1.0154921754800501e-05,
+      "loss": 0.3745,
+      "step": 730
+    },
+    {
+      "epoch": 1.8894601542416454,
+      "grad_norm": 1.144382357597351,
+      "learning_rate": 9.9541612418734e-06,
+      "loss": 0.3584,
+      "step": 735
+    },
+    {
+      "epoch": 1.9023136246786634,
+      "grad_norm": 1.0645383596420288,
+      "learning_rate": 9.754414841894377e-06,
+      "loss": 0.3746,
+      "step": 740
+    },
+    {
+      "epoch": 1.9151670951156814,
+      "grad_norm": 1.0271685123443604,
+      "learning_rate": 9.55572269990576e-06,
+      "loss": 0.3933,
+      "step": 745
+    },
+    {
+      "epoch": 1.9280205655526992,
+      "grad_norm": 1.1679786443710327,
+      "learning_rate": 9.358124749065068e-06,
+      "loss": 0.3498,
+      "step": 750
+    },
+    {
+      "epoch": 1.9408740359897172,
+      "grad_norm": 1.2249962091445923,
+      "learning_rate": 9.161660702619186e-06,
+      "loss": 0.3714,
+      "step": 755
+    },
+    {
+      "epoch": 1.9537275064267352,
+      "grad_norm": 1.0866971015930176,
+      "learning_rate": 8.966370045922881e-06,
+      "loss": 0.3864,
+      "step": 760
+    },
+    {
+      "epoch": 1.9665809768637532,
+      "grad_norm": 1.0349154472351074,
+      "learning_rate": 8.77229202850294e-06,
+      "loss": 0.3548,
+      "step": 765
+    },
+    {
+      "epoch": 1.9794344473007712,
+      "grad_norm": 1.1307743787765503,
+      "learning_rate": 8.57946565616987e-06,
+      "loss": 0.3608,
+      "step": 770
+    },
+    {
+      "epoch": 1.9922879177377892,
+      "grad_norm": 1.1768754720687866,
+      "learning_rate": 8.38792968317847e-06,
+      "loss": 0.3732,
+      "step": 775
+    },
+    {
+      "epoch": 2.005141388174807,
+      "grad_norm": 1.0680352449417114,
+      "learning_rate": 8.19772260443901e-06,
+      "loss": 0.313,
+      "step": 780
+    },
+    {
+      "epoch": 2.017994858611825,
+      "grad_norm": 1.073745608329773,
+      "learning_rate": 8.008882647780518e-06,
+      "loss": 0.2986,
+      "step": 785
+    },
+    {
+      "epoch": 2.030848329048843,
+      "grad_norm": 1.2686152458190918,
+      "learning_rate": 7.821447766267752e-06,
+      "loss": 0.3201,
+      "step": 790
+    },
+    {
+      "epoch": 2.043701799485861,
+      "grad_norm": 1.081129550933838,
+      "learning_rate": 7.635455630573408e-06,
+      "loss": 0.2893,
+      "step": 795
+    },
+    {
+      "epoch": 2.056555269922879,
+      "grad_norm": 1.5379725694656372,
+      "learning_rate": 7.450943621407026e-06,
+      "loss": 0.2864,
+      "step": 800
+    },
+    {
+      "epoch": 2.069408740359897,
+      "grad_norm": 1.207736849784851,
+      "learning_rate": 7.267948822002248e-06,
+      "loss": 0.3101,
+      "step": 805
+    },
+    {
+      "epoch": 2.082262210796915,
+      "grad_norm": 1.311033010482788,
+      "learning_rate": 7.086508010663808e-06,
+      "loss": 0.2891,
+      "step": 810
+    },
+    {
+      "epoch": 2.095115681233933,
+      "grad_norm": 1.1332662105560303,
+      "learning_rate": 6.906657653375839e-06,
+      "loss": 0.3185,
+      "step": 815
+    },
+    {
+      "epoch": 2.107969151670951,
+      "grad_norm": 0.9989017844200134,
+      "learning_rate": 6.7284338964729366e-06,
+      "loss": 0.2965,
+      "step": 820
+    },
+    {
+      "epoch": 2.120822622107969,
+      "grad_norm": 1.4260122776031494,
+      "learning_rate": 6.5518725593754465e-06,
+      "loss": 0.3104,
+      "step": 825
+    },
+    {
+      "epoch": 2.133676092544987,
+      "grad_norm": 1.1024667024612427,
+      "learning_rate": 6.377009127390523e-06,
+      "loss": 0.2704,
+      "step": 830
+    },
+    {
+      "epoch": 2.146529562982005,
+      "grad_norm": 1.1210920810699463,
+      "learning_rate": 6.203878744580218e-06,
+      "loss": 0.2519,
+      "step": 835
+    },
+    {
+      "epoch": 2.159383033419023,
+      "grad_norm": 1.2821919918060303,
+      "learning_rate": 6.032516206698289e-06,
+      "loss": 0.3181,
+      "step": 840
+    },
+    {
+      "epoch": 2.172236503856041,
+      "grad_norm": 1.0716218948364258,
+      "learning_rate": 5.862955954196931e-06,
+      "loss": 0.2851,
+      "step": 845
+    },
+    {
+      "epoch": 2.185089974293059,
+      "grad_norm": 1.0852926969528198,
+      "learning_rate": 5.69523206530491e-06,
+      "loss": 0.2641,
+      "step": 850
+    },
+    {
+      "epoch": 2.197943444730077,
+      "grad_norm": 1.2312536239624023,
+      "learning_rate": 5.529378249178538e-06,
+      "loss": 0.2891,
+      "step": 855
+    },
+    {
+      "epoch": 2.210796915167095,
+      "grad_norm": 1.14886474609375,
+      "learning_rate": 5.365427839126795e-06,
+      "loss": 0.2899,
+      "step": 860
+    },
+    {
+      "epoch": 2.223650385604113,
+      "grad_norm": 1.2088441848754883,
+      "learning_rate": 5.203413785912031e-06,
+      "loss": 0.35,
+      "step": 865
+    },
+    {
+      "epoch": 2.236503856041131,
+      "grad_norm": 1.1419215202331543,
+      "learning_rate": 5.043368651127455e-06,
+      "loss": 0.3195,
+      "step": 870
+    },
+    {
+      "epoch": 2.2493573264781492,
+      "grad_norm": 1.470544695854187,
+      "learning_rate": 4.885324600652963e-06,
+      "loss": 0.2838,
+      "step": 875
+    },
+    {
+      "epoch": 2.2622107969151672,
+      "grad_norm": 1.2379597425460815,
+      "learning_rate": 4.729313398190428e-06,
+      "loss": 0.3099,
+      "step": 880
+    },
+    {
+      "epoch": 2.2750642673521853,
+      "grad_norm": 1.0652796030044556,
+      "learning_rate": 4.575366398879799e-06,
+      "loss": 0.2871,
+      "step": 885
+    },
+    {
+      "epoch": 2.2879177377892033,
+      "grad_norm": 1.1224174499511719,
+      "learning_rate": 4.4235145429973725e-06,
+      "loss": 0.291,
+      "step": 890
+    },
+    {
+      "epoch": 2.3007712082262213,
+      "grad_norm": 1.1823378801345825,
+      "learning_rate": 4.273788349737403e-06,
+      "loss": 0.3064,
+      "step": 895
+    },
+    {
+      "epoch": 2.3136246786632393,
+      "grad_norm": 1.158951997756958,
+      "learning_rate": 4.126217911078359e-06,
+      "loss": 0.2879,
+      "step": 900
+    },
+    {
+      "epoch": 2.3264781491002573,
+      "grad_norm": 1.1736172437667847,
+      "learning_rate": 3.980832885735027e-06,
+      "loss": 0.247,
+      "step": 905
+    },
+    {
+      "epoch": 2.3393316195372753,
+      "grad_norm": 1.0421558618545532,
+      "learning_rate": 3.837662493197704e-06,
+      "loss": 0.284,
+      "step": 910
+    },
+    {
+      "epoch": 2.352185089974293,
+      "grad_norm": 1.1019563674926758,
+      "learning_rate": 3.696735507859685e-06,
+      "loss": 0.2828,
+      "step": 915
+    },
+    {
+      "epoch": 2.365038560411311,
+      "grad_norm": 1.1632064580917358,
+      "learning_rate": 3.5580802532341293e-06,
+      "loss": 0.2575,
+      "step": 920
+    },
+    {
+      "epoch": 2.377892030848329,
+      "grad_norm": 1.0827430486679077,
+      "learning_rate": 3.42172459626167e-06,
+      "loss": 0.2693,
+      "step": 925
+    },
+    {
+      "epoch": 2.390745501285347,
+      "grad_norm": 1.1585731506347656,
+      "learning_rate": 3.287695941709655e-06,
+      "loss": 0.2889,
+      "step": 930
+    },
+    {
+      "epoch": 2.403598971722365,
+      "grad_norm": 1.1649552583694458,
+      "learning_rate": 3.156021226664367e-06,
+      "loss": 0.2812,
+      "step": 935
+    },
+    {
+      "epoch": 2.416452442159383,
+      "grad_norm": 1.187164306640625,
+      "learning_rate": 3.026726915117201e-06,
+      "loss": 0.289,
+      "step": 940
+    },
+    {
+      "epoch": 2.429305912596401,
+      "grad_norm": 1.183590054512024,
+      "learning_rate": 2.899838992645918e-06,
+      "loss": 0.2591,
+      "step": 945
+    },
+    {
+      "epoch": 2.442159383033419,
+      "grad_norm": 1.1535863876342773,
+      "learning_rate": 2.7753829611920906e-06,
+      "loss": 0.2504,
+      "step": 950
+    },
+    {
+      "epoch": 2.455012853470437,
+      "grad_norm": 1.0849297046661377,
+      "learning_rate": 2.653383833935675e-06,
+      "loss": 0.2425,
+      "step": 955
+    },
+    {
+      "epoch": 2.467866323907455,
+      "grad_norm": 1.1707229614257812,
+      "learning_rate": 2.5338661302679146e-06,
+      "loss": 0.2998,
+      "step": 960
+    },
+    {
+      "epoch": 2.480719794344473,
+      "grad_norm": 1.3136762380599976,
+      "learning_rate": 2.4168538708633924e-06,
+      "loss": 0.2526,
+      "step": 965
+    },
+    {
+      "epoch": 2.493573264781491,
+      "grad_norm": 1.1424813270568848,
+      "learning_rate": 2.3023705728523635e-06,
+      "loss": 0.2816,
+      "step": 970
+    },
+    {
+      "epoch": 2.506426735218509,
+      "grad_norm": 1.1173136234283447,
+      "learning_rate": 2.190439245094294e-06,
+      "loss": 0.2367,
+      "step": 975
+    },
+    {
+      "epoch": 2.519280205655527,
+      "grad_norm": 1.189194679260254,
+      "learning_rate": 2.081082383553523e-06,
+      "loss": 0.257,
+      "step": 980
+    },
+    {
+      "epoch": 2.532133676092545,
+      "grad_norm": 1.195174217224121,
+      "learning_rate": 1.9743219667780325e-06,
+      "loss": 0.2891,
+      "step": 985
+    },
+    {
+      "epoch": 2.544987146529563,
+      "grad_norm": 1.2084566354751587,
+      "learning_rate": 1.8701794514821896e-06,
+      "loss": 0.2649,
+      "step": 990
+    },
+    {
+      "epoch": 2.557840616966581,
+      "grad_norm": 1.1842268705368042,
+      "learning_rate": 1.7686757682343891e-06,
+      "loss": 0.2869,
+      "step": 995
+    },
+    {
+      "epoch": 2.570694087403599,
+      "grad_norm": 1.1205123662948608,
+      "learning_rate": 1.6698313172504127e-06,
+      "loss": 0.2606,
+      "step": 1000
+    },
+    {
+      "epoch": 2.583547557840617,
+      "grad_norm": 1.145274043083191,
+      "learning_rate": 1.5736659642933847e-06,
+      "loss": 0.2835,
+      "step": 1005
+    },
+    {
+      "epoch": 2.596401028277635,
+      "grad_norm": 1.2438132762908936,
+      "learning_rate": 1.4801990366811836e-06,
+      "loss": 0.2446,
+      "step": 1010
+    },
+    {
+      "epoch": 2.609254498714653,
+      "grad_norm": 1.0696029663085938,
+      "learning_rate": 1.389449319402002e-06,
+      "loss": 0.2513,
+      "step": 1015
+    },
+    {
+      "epoch": 2.622107969151671,
+      "grad_norm": 1.1054593324661255,
+      "learning_rate": 1.3014350513389556e-06,
+      "loss": 0.2726,
+      "step": 1020
+    },
+    {
+      "epoch": 2.6349614395886887,
+      "grad_norm": 1.206030011177063,
+      "learning_rate": 1.2161739216044243e-06,
+      "loss": 0.2816,
+      "step": 1025
+    },
+    {
+      "epoch": 2.6478149100257067,
+      "grad_norm": 1.147189974784851,
+      "learning_rate": 1.1336830659849046e-06,
+      "loss": 0.271,
+      "step": 1030
+    },
+    {
+      "epoch": 2.6606683804627247,
+      "grad_norm": 0.9926533102989197,
+      "learning_rate": 1.0539790634970459e-06,
+      "loss": 0.2487,
+      "step": 1035
+    },
+    {
+      "epoch": 2.6735218508997427,
+      "grad_norm": 1.0686745643615723,
+      "learning_rate": 9.770779330555978e-07,
+      "loss": 0.2774,
+      "step": 1040
+    },
+    {
+      "epoch": 2.6863753213367607,
+      "grad_norm": 1.0455516576766968,
+      "learning_rate": 9.029951302539458e-07,
+      "loss": 0.2616,
+      "step": 1045
+    },
+    {
+      "epoch": 2.6992287917737787,
+      "grad_norm": 1.1300852298736572,
+      "learning_rate": 8.317455442578231e-07,
+      "loss": 0.2511,
+      "step": 1050
+    },
+    {
+      "epoch": 2.7120822622107967,
+      "grad_norm": 1.060441493988037,
+      "learning_rate": 7.633434948128992e-07,
+      "loss": 0.2789,
+      "step": 1055
+    },
+    {
+      "epoch": 2.7249357326478147,
+      "grad_norm": 1.1717143058776855,
+      "learning_rate": 6.978027293667943e-07,
+      "loss": 0.2763,
+      "step": 1060
+    },
+    {
+      "epoch": 2.7377892030848328,
+      "grad_norm": 0.9858744740486145,
+      "learning_rate": 6.351364203061116e-07,
+      "loss": 0.2649,
+      "step": 1065
+    },
+    {
+      "epoch": 2.7506426735218508,
+      "grad_norm": 1.1933311223983765,
+      "learning_rate": 5.753571623090531e-07,
+      "loss": 0.2882,
+      "step": 1070
+    },
+    {
+      "epoch": 2.763496143958869,
+      "grad_norm": 1.2357069253921509,
+      "learning_rate": 5.184769698141445e-07,
+      "loss": 0.2876,
+      "step": 1075
+    },
+    {
+      "epoch": 2.776349614395887,
+      "grad_norm": 1.308221697807312,
+      "learning_rate": 4.645072746055684e-07,
+      "loss": 0.2844,
+      "step": 1080
+    },
+    {
+      "epoch": 2.789203084832905,
+      "grad_norm": 1.0328681468963623,
+      "learning_rate": 4.134589235156022e-07,
+      "loss": 0.2826,
+      "step": 1085
+    },
+    {
+      "epoch": 2.802056555269923,
+      "grad_norm": 1.2023781538009644,
+      "learning_rate": 3.653421762446252e-07,
+      "loss": 0.2826,
+      "step": 1090
+    },
+    {
+      "epoch": 2.814910025706941,
+      "grad_norm": 1.0431300401687622,
+      "learning_rate": 3.201667032991212e-07,
+      "loss": 0.2599,
+      "step": 1095
+    },
+    {
+      "epoch": 2.827763496143959,
+      "grad_norm": 1.1678283214569092,
+      "learning_rate": 2.7794158404810034e-07,
+      "loss": 0.2617,
+      "step": 1100
+    },
+    {
+      "epoch": 2.840616966580977,
+      "grad_norm": 1.0511726140975952,
+      "learning_rate": 2.3867530489832643e-07,
+      "loss": 0.2544,
+      "step": 1105
+    },
+    {
+      "epoch": 2.853470437017995,
+      "grad_norm": 1.0670933723449707,
+      "learning_rate": 2.0237575758871697e-07,
+      "loss": 0.2523,
+      "step": 1110
+    },
+    {
+      "epoch": 2.866323907455013,
+      "grad_norm": 1.2315407991409302,
+      "learning_rate": 1.6905023760426797e-07,
+      "loss": 0.2339,
+      "step": 1115
+    },
+    {
+      "epoch": 2.879177377892031,
+      "grad_norm": 1.198808193206787,
+      "learning_rate": 1.3870544270979724e-07,
+      "loss": 0.2733,
+      "step": 1120
+    },
+    {
+      "epoch": 2.892030848329049,
+      "grad_norm": 1.003639578819275,
+      "learning_rate": 1.1134747160383263e-07,
+      "loss": 0.2855,
+      "step": 1125
+    },
+    {
+      "epoch": 2.904884318766067,
+      "grad_norm": 1.2919894456863403,
+      "learning_rate": 8.698182269289423e-08,
+      "loss": 0.2949,
+      "step": 1130
+    },
+    {
+      "epoch": 2.917737789203085,
+      "grad_norm": 1.0303324460983276,
+      "learning_rate": 6.561339298642999e-08,
+      "loss": 0.2367,
+      "step": 1135
+    },
+    {
+      "epoch": 2.930591259640103,
+      "grad_norm": 1.1857292652130127,
+      "learning_rate": 4.7246477112599665e-08,
+      "loss": 0.2483,
+      "step": 1140
+    },
+    {
+      "epoch": 2.943444730077121,
+      "grad_norm": 1.0782839059829712,
+      "learning_rate": 3.188476645515692e-08,
+      "loss": 0.2614,
+      "step": 1145
+    },
+    {
+      "epoch": 2.956298200514139,
+      "grad_norm": 1.2110518217086792,
+      "learning_rate": 1.953134841154447e-08,
+      "loss": 0.2973,
+      "step": 1150
+    },
+    {
+      "epoch": 2.969151670951157,
+      "grad_norm": 1.2743874788284302,
+      "learning_rate": 1.0188705772393725e-08,
+      "loss": 0.2881,
+      "step": 1155
+    },
+    {
+      "epoch": 2.982005141388175,
+      "grad_norm": 1.1455755233764648,
+      "learning_rate": 3.858716222530645e-09,
+      "loss": 0.264,
+      "step": 1160
+    },
+    {
+      "epoch": 2.994858611825193,
+      "grad_norm": 1.200308918952942,
+      "learning_rate": 5.426519635975958e-10,
+      "loss": 0.2743,
+      "step": 1165
+    },
+    {
+      "epoch": 3.0,
+      "step": 1167,
+      "total_flos": 1.8582176454431212e+18,
+      "train_loss": 0.5394563638152684,
+      "train_runtime": 871.0297,
+      "train_samples_per_second": 42.839,
+      "train_steps_per_second": 1.34
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1167,
+  "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": 1.8582176454431212e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

49_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ceeea4c7f96e815866a55cf052546bdf1e6d6250172d3f700986f5e9a06e66ba
+size 8145