Upload 13 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,52 @@
----
-license: apache-2.0
----
+---
+license: gemma
+library_name: peft
+tags:
+- alignment-handbook
+- generated_from_trainer
+base_model: google/gemma-2b
+datasets:
+- Ritvik19/open-hermes-2_5-reformatted
+model-index:
+- name: openhermes-2b-gemma-sft-qlora
+  results: []
+---
+
+**Note**: This model card has been generated automatically according to the information the Trainer had access to. 
+Visit the [model card](https://ritvik19.github.io/small-llms/) to see the full description
+
+# openhermes-2b-gemma-sft-qlora
+
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the Ritvik19/open-hermes-2_5-reformatted dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3468
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1166        | 0.9997 | 1505 | 1.3468          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.40.1
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88161c5e5af5f852a99bc2ba855b21111d5bd5946a045af005b590e512f15192
+size 39256960

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.9996678844237795,
+    "eval_loss": 1.3468068838119507,
+    "eval_runtime": 2440.5191,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 5.607,
+    "eval_steps_per_second": 5.607,
+    "total_flos": 4.73786206333698e+18,
+    "train_loss": 0.5388378948072262,
+    "train_runtime": 65741.8056,
+    "train_samples": 1001538,
+    "train_samples_per_second": 2.931,
+    "train_steps_per_second": 0.023
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/gemma-2b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 18,
+  "num_key_value_heads": 1,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9996678844237795,
+    "eval_loss": 1.3468068838119507,
+    "eval_runtime": 2440.5191,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 5.607,
+    "eval_steps_per_second": 5.607
+}

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7da53ca29fb16f6b2489482fc0bc6a394162cdab14d12764a1755ebc583fea79
+size 17518525

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,1757 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "5": {
+      "content": "<2mass>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "6": {
+      "content": "[@BOS@]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "7": {
+      "content": "<unused0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "8": {
+      "content": "<unused1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "9": {
+      "content": "<unused2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "10": {
+      "content": "<unused3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "11": {
+      "content": "<unused4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "12": {
+      "content": "<unused5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "13": {
+      "content": "<unused6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "14": {
+      "content": "<unused7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "15": {
+      "content": "<unused8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "16": {
+      "content": "<unused9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "17": {
+      "content": "<unused10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "18": {
+      "content": "<unused11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "19": {
+      "content": "<unused12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "20": {
+      "content": "<unused13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "21": {
+      "content": "<unused14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "22": {
+      "content": "<unused15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "23": {
+      "content": "<unused16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "24": {
+      "content": "<unused17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "25": {
+      "content": "<unused18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "26": {
+      "content": "<unused19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "27": {
+      "content": "<unused20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "28": {
+      "content": "<unused21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "29": {
+      "content": "<unused22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "30": {
+      "content": "<unused23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "31": {
+      "content": "<unused24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32": {
+      "content": "<unused25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "33": {
+      "content": "<unused26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "34": {
+      "content": "<unused27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "35": {
+      "content": "<unused28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "36": {
+      "content": "<unused29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "37": {
+      "content": "<unused30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "38": {
+      "content": "<unused31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "39": {
+      "content": "<unused32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "40": {
+      "content": "<unused33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "41": {
+      "content": "<unused34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "42": {
+      "content": "<unused35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "43": {
+      "content": "<unused36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "44": {
+      "content": "<unused37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "45": {
+      "content": "<unused38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "46": {
+      "content": "<unused39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "47": {
+      "content": "<unused40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "48": {
+      "content": "<unused41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "49": {
+      "content": "<unused42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50": {
+      "content": "<unused43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "51": {
+      "content": "<unused44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "52": {
+      "content": "<unused45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "53": {
+      "content": "<unused46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "54": {
+      "content": "<unused47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "55": {
+      "content": "<unused48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "56": {
+      "content": "<unused49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "57": {
+      "content": "<unused50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58": {
+      "content": "<unused51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "59": {
+      "content": "<unused52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "60": {
+      "content": "<unused53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "61": {
+      "content": "<unused54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "62": {
+      "content": "<unused55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "63": {
+      "content": "<unused56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "64": {
+      "content": "<unused57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "65": {
+      "content": "<unused58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "66": {
+      "content": "<unused59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "67": {
+      "content": "<unused60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "68": {
+      "content": "<unused61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "69": {
+      "content": "<unused62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "70": {
+      "content": "<unused63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "71": {
+      "content": "<unused64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "72": {
+      "content": "<unused65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "73": {
+      "content": "<unused66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "74": {
+      "content": "<unused67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "75": {
+      "content": "<unused68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "76": {
+      "content": "<unused69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "77": {
+      "content": "<unused70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "78": {
+      "content": "<unused71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79": {
+      "content": "<unused72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "80": {
+      "content": "<unused73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "81": {
+      "content": "<unused74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "82": {
+      "content": "<unused75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "83": {
+      "content": "<unused76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "84": {
+      "content": "<unused77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "85": {
+      "content": "<unused78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "86": {
+      "content": "<unused79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "87": {
+      "content": "<unused80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "88": {
+      "content": "<unused81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "89": {
+      "content": "<unused82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "90": {
+      "content": "<unused83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "91": {
+      "content": "<unused84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "92": {
+      "content": "<unused85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "93": {
+      "content": "<unused86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "94": {
+      "content": "<unused87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "95": {
+      "content": "<unused88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "96": {
+      "content": "<unused89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "97": {
+      "content": "<unused90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "98": {
+      "content": "<unused91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "99": {
+      "content": "<unused92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100": {
+      "content": "<unused93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "101": {
+      "content": "<unused94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "102": {
+      "content": "<unused95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "103": {
+      "content": "<unused96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "104": {
+      "content": "<unused97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "105": {
+      "content": "<unused98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "108": {
+      "content": "\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "109": {
+      "content": "\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "110": {
+      "content": "\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "111": {
+      "content": "\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "112": {
+      "content": "\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "113": {
+      "content": "\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "114": {
+      "content": "\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "115": {
+      "content": "\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "116": {
+      "content": "\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "117": {
+      "content": "\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "118": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "119": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "120": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "121": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "122": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "123": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "124": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "125": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "126": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "127": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "128": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "129": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "130": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "131": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "132": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "133": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "134": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "135": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "136": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "137": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "138": {
+      "content": "\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "139": {
+      "content": "▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "140": {
+      "content": "▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "141": {
+      "content": "▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "142": {
+      "content": "▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "143": {
+      "content": "▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "144": {
+      "content": "▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "145": {
+      "content": "▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "146": {
+      "content": "▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "147": {
+      "content": "▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "148": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "149": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "150": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "152": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "153": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "154": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "155": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "156": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "157": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "158": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "159": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "160": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "161": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "162": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "163": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "164": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "165": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "166": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "167": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "168": {
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "169": {
+      "content": "<table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "170": {
+      "content": "<caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "171": {
+      "content": "<thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "172": {
+      "content": "<tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "173": {
+      "content": "<tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "174": {
+      "content": "<tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "175": {
+      "content": "<th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "176": {
+      "content": "<td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "177": {
+      "content": "</table>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "178": {
+      "content": "</caption>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "179": {
+      "content": "</thead>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "180": {
+      "content": "</tbody>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "181": {
+      "content": "</tfoot>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "182": {
+      "content": "</tr>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "183": {
+      "content": "</th>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "184": {
+      "content": "</td>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "185": {
+      "content": "<h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "186": {
+      "content": "<h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "187": {
+      "content": "<h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "188": {
+      "content": "<h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "189": {
+      "content": "<h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "190": {
+      "content": "<h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "191": {
+      "content": "<blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "192": {
+      "content": "</h1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "193": {
+      "content": "</h2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "194": {
+      "content": "</h3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "195": {
+      "content": "</h4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "196": {
+      "content": "</h5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "197": {
+      "content": "</h6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "198": {
+      "content": "</blockquote>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "199": {
+      "content": "<strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "200": {
+      "content": "<em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "201": {
+      "content": "<b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "202": {
+      "content": "<i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "203": {
+      "content": "<u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "204": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "205": {
+      "content": "<sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "206": {
+      "content": "<sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "207": {
+      "content": "<code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "208": {
+      "content": "</strong>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "209": {
+      "content": "</em>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "210": {
+      "content": "</b>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "211": {
+      "content": "</i>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "212": {
+      "content": "</u>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "213": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "214": {
+      "content": "</sub>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "215": {
+      "content": "</sup>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "216": {
+      "content": "</code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9996678844237795,
+    "total_flos": 4.73786206333698e+18,
+    "train_loss": 0.5388378948072262,
+    "train_runtime": 65741.8056,
+    "train_samples": 1001538,
+    "train_samples_per_second": 2.931,
+    "train_steps_per_second": 0.023
+}

trainer_state.json

@@ -0,0 +1,2152 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9996678844237795,
+  "eval_steps": 500,
+  "global_step": 1505,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006642311524410495,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.3245033112582782e-06,
+      "loss": 1.8253,
+      "step": 1
+    },
+    {
+      "epoch": 0.0033211557622052474,
+      "grad_norm": 0.7421875,
+      "learning_rate": 6.622516556291391e-06,
+      "loss": 1.838,
+      "step": 5
+    },
+    {
+      "epoch": 0.006642311524410495,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.3245033112582782e-05,
+      "loss": 1.823,
+      "step": 10
+    },
+    {
+      "epoch": 0.009963467286615742,
+      "grad_norm": 0.58984375,
+      "learning_rate": 1.9867549668874173e-05,
+      "loss": 1.7917,
+      "step": 15
+    },
+    {
+      "epoch": 0.01328462304882099,
+      "grad_norm": 0.353515625,
+      "learning_rate": 2.6490066225165565e-05,
+      "loss": 1.7849,
+      "step": 20
+    },
+    {
+      "epoch": 0.016605778811026237,
+      "grad_norm": 0.375,
+      "learning_rate": 3.311258278145696e-05,
+      "loss": 1.7819,
+      "step": 25
+    },
+    {
+      "epoch": 0.019926934573231483,
+      "grad_norm": 0.4609375,
+      "learning_rate": 3.9735099337748346e-05,
+      "loss": 1.7091,
+      "step": 30
+    },
+    {
+      "epoch": 0.023248090335436733,
+      "grad_norm": 0.490234375,
+      "learning_rate": 4.635761589403974e-05,
+      "loss": 1.6498,
+      "step": 35
+    },
+    {
+      "epoch": 0.02656924609764198,
+      "grad_norm": 2.0,
+      "learning_rate": 5.298013245033113e-05,
+      "loss": 1.6126,
+      "step": 40
+    },
+    {
+      "epoch": 0.029890401859847225,
+      "grad_norm": 0.5078125,
+      "learning_rate": 5.960264900662252e-05,
+      "loss": 1.5847,
+      "step": 45
+    },
+    {
+      "epoch": 0.033211557622052475,
+      "grad_norm": 0.515625,
+      "learning_rate": 6.622516556291392e-05,
+      "loss": 1.4876,
+      "step": 50
+    },
+    {
+      "epoch": 0.036532713384257724,
+      "grad_norm": 0.33203125,
+      "learning_rate": 7.284768211920529e-05,
+      "loss": 1.4771,
+      "step": 55
+    },
+    {
+      "epoch": 0.03985386914646297,
+      "grad_norm": 0.234375,
+      "learning_rate": 7.947019867549669e-05,
+      "loss": 1.4546,
+      "step": 60
+    },
+    {
+      "epoch": 0.043175024908668216,
+      "grad_norm": 0.6015625,
+      "learning_rate": 8.609271523178808e-05,
+      "loss": 1.4066,
+      "step": 65
+    },
+    {
+      "epoch": 0.046496180670873466,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 9.271523178807948e-05,
+      "loss": 1.4112,
+      "step": 70
+    },
+    {
+      "epoch": 0.04981733643307871,
+      "grad_norm": 0.189453125,
+      "learning_rate": 9.933774834437086e-05,
+      "loss": 1.3762,
+      "step": 75
+    },
+    {
+      "epoch": 0.05313849219528396,
+      "grad_norm": 0.150390625,
+      "learning_rate": 0.00010596026490066226,
+      "loss": 1.3657,
+      "step": 80
+    },
+    {
+      "epoch": 0.05645964795748921,
+      "grad_norm": 0.1484375,
+      "learning_rate": 0.00011258278145695364,
+      "loss": 1.3309,
+      "step": 85
+    },
+    {
+      "epoch": 0.05978080371969445,
+      "grad_norm": 0.11865234375,
+      "learning_rate": 0.00011920529801324504,
+      "loss": 1.3321,
+      "step": 90
+    },
+    {
+      "epoch": 0.0631019594818997,
+      "grad_norm": 0.1083984375,
+      "learning_rate": 0.00012582781456953643,
+      "loss": 1.3179,
+      "step": 95
+    },
+    {
+      "epoch": 0.06642311524410495,
+      "grad_norm": 0.095703125,
+      "learning_rate": 0.00013245033112582784,
+      "loss": 1.3108,
+      "step": 100
+    },
+    {
+      "epoch": 0.0697442710063102,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.0001390728476821192,
+      "loss": 1.2985,
+      "step": 105
+    },
+    {
+      "epoch": 0.07306542676851545,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.00014569536423841059,
+      "loss": 1.2727,
+      "step": 110
+    },
+    {
+      "epoch": 0.07638658253072068,
+      "grad_norm": 0.11328125,
+      "learning_rate": 0.000152317880794702,
+      "loss": 1.2735,
+      "step": 115
+    },
+    {
+      "epoch": 0.07970773829292593,
+      "grad_norm": 0.06787109375,
+      "learning_rate": 0.00015894039735099338,
+      "loss": 1.2625,
+      "step": 120
+    },
+    {
+      "epoch": 0.08302889405513118,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.00016556291390728477,
+      "loss": 1.2354,
+      "step": 125
+    },
+    {
+      "epoch": 0.08635004981733643,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00017218543046357615,
+      "loss": 1.2534,
+      "step": 130
+    },
+    {
+      "epoch": 0.08967120557954168,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 0.00017880794701986757,
+      "loss": 1.2281,
+      "step": 135
+    },
+    {
+      "epoch": 0.09299236134174693,
+      "grad_norm": 0.146484375,
+      "learning_rate": 0.00018543046357615895,
+      "loss": 1.2436,
+      "step": 140
+    },
+    {
+      "epoch": 0.09631351710395218,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 0.00019205298013245034,
+      "loss": 1.2399,
+      "step": 145
+    },
+    {
+      "epoch": 0.09963467286615742,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 0.00019867549668874172,
+      "loss": 1.2157,
+      "step": 150
+    },
+    {
+      "epoch": 0.10295582862836267,
+      "grad_norm": 0.107421875,
+      "learning_rate": 0.00019999569325372926,
+      "loss": 1.2191,
+      "step": 155
+    },
+    {
+      "epoch": 0.10627698439056792,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001999781977327807,
+      "loss": 1.2421,
+      "step": 160
+    },
+    {
+      "epoch": 0.10959814015277317,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 0.00019994724661834065,
+      "loss": 1.2209,
+      "step": 165
+    },
+    {
+      "epoch": 0.11291929591497842,
+      "grad_norm": 0.11572265625,
+      "learning_rate": 0.0001999028440759734,
+      "loss": 1.1945,
+      "step": 170
+    },
+    {
+      "epoch": 0.11624045167718366,
+      "grad_norm": 0.11083984375,
+      "learning_rate": 0.00019984499608160746,
+      "loss": 1.2276,
+      "step": 175
+    },
+    {
+      "epoch": 0.1195616074393889,
+      "grad_norm": 0.07177734375,
+      "learning_rate": 0.00019977371042073115,
+      "loss": 1.2141,
+      "step": 180
+    },
+    {
+      "epoch": 0.12288276320159415,
+      "grad_norm": 0.126953125,
+      "learning_rate": 0.00019968899668734502,
+      "loss": 1.2088,
+      "step": 185
+    },
+    {
+      "epoch": 0.1262039189637994,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00019959086628267033,
+      "loss": 1.2116,
+      "step": 190
+    },
+    {
+      "epoch": 0.12952507472600466,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 0.00019947933241361483,
+      "loss": 1.2059,
+      "step": 195
+    },
+    {
+      "epoch": 0.1328462304882099,
+      "grad_norm": 0.0859375,
+      "learning_rate": 0.00019935441009099524,
+      "loss": 1.2049,
+      "step": 200
+    },
+    {
+      "epoch": 0.13616738625041513,
+      "grad_norm": 0.130859375,
+      "learning_rate": 0.00019921611612751708,
+      "loss": 1.1862,
+      "step": 205
+    },
+    {
+      "epoch": 0.1394885420126204,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00019906446913551173,
+      "loss": 1.1948,
+      "step": 210
+    },
+    {
+      "epoch": 0.14280969777482563,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 0.00019889948952443173,
+      "loss": 1.1951,
+      "step": 215
+    },
+    {
+      "epoch": 0.1461308535370309,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 0.0001987211994981039,
+      "loss": 1.1761,
+      "step": 220
+    },
+    {
+      "epoch": 0.14945200929923613,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.00019852962305174078,
+      "loss": 1.2026,
+      "step": 225
+    },
+    {
+      "epoch": 0.15277316506144137,
+      "grad_norm": 0.2421875,
+      "learning_rate": 0.00019832478596871166,
+      "loss": 1.1896,
+      "step": 230
+    },
+    {
+      "epoch": 0.15609432082364663,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 0.00019810671581707223,
+      "loss": 1.1745,
+      "step": 235
+    },
+    {
+      "epoch": 0.15941547658585187,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00019787544194585434,
+      "loss": 1.1878,
+      "step": 240
+    },
+    {
+      "epoch": 0.16273663234805713,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019763099548111615,
+      "loss": 1.1851,
+      "step": 245
+    },
+    {
+      "epoch": 0.16605778811026237,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.00019737340932175296,
+      "loss": 1.1765,
+      "step": 250
+    },
+    {
+      "epoch": 0.16937894387246763,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00019710271813506953,
+      "loss": 1.1818,
+      "step": 255
+    },
+    {
+      "epoch": 0.17270009963467287,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 0.00019681895835211438,
+      "loss": 1.1489,
+      "step": 260
+    },
+    {
+      "epoch": 0.1760212553968781,
+      "grad_norm": 0.134765625,
+      "learning_rate": 0.00019652216816277656,
+      "loss": 1.1565,
+      "step": 265
+    },
+    {
+      "epoch": 0.17934241115908336,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 0.0001962123875106462,
+      "loss": 1.1663,
+      "step": 270
+    },
+    {
+      "epoch": 0.1826635669212886,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 0.0001958896580876383,
+      "loss": 1.187,
+      "step": 275
+    },
+    {
+      "epoch": 0.18598472268349386,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 0.00019555402332838178,
+      "loss": 1.1769,
+      "step": 280
+    },
+    {
+      "epoch": 0.1893058784456991,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 0.00019520552840437394,
+      "loss": 1.1765,
+      "step": 285
+    },
+    {
+      "epoch": 0.19262703420790436,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 0.00019484422021790083,
+      "loss": 1.1769,
+      "step": 290
+    },
+    {
+      "epoch": 0.1959481899701096,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00019447014739572502,
+      "loss": 1.1654,
+      "step": 295
+    },
+    {
+      "epoch": 0.19926934573231483,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001940833602825411,
+      "loss": 1.1695,
+      "step": 300
+    },
+    {
+      "epoch": 0.2025905014945201,
+      "grad_norm": 0.11376953125,
+      "learning_rate": 0.00019368391093420003,
+      "loss": 1.1685,
+      "step": 305
+    },
+    {
+      "epoch": 0.20591165725672533,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 0.0001932718531107033,
+      "loss": 1.1502,
+      "step": 310
+    },
+    {
+      "epoch": 0.2092328130189306,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.00019284724226896737,
+      "loss": 1.1694,
+      "step": 315
+    },
+    {
+      "epoch": 0.21255396878113583,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.0001924101355553603,
+      "loss": 1.1701,
+      "step": 320
+    },
+    {
+      "epoch": 0.2158751245433411,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.0001919605917980104,
+      "loss": 1.1501,
+      "step": 325
+    },
+    {
+      "epoch": 0.21919628030554633,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.00019149867149888906,
+      "loss": 1.1645,
+      "step": 330
+    },
+    {
+      "epoch": 0.22251743606775157,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00019102443682566793,
+      "loss": 1.1432,
+      "step": 335
+    },
+    {
+      "epoch": 0.22583859182995683,
+      "grad_norm": 0.126953125,
+      "learning_rate": 0.00019053795160335214,
+      "loss": 1.1632,
+      "step": 340
+    },
+    {
+      "epoch": 0.22915974759216207,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 0.00019003928130569039,
+      "loss": 1.1464,
+      "step": 345
+    },
+    {
+      "epoch": 0.23248090335436733,
+      "grad_norm": 0.1064453125,
+      "learning_rate": 0.00018952849304636307,
+      "loss": 1.1568,
+      "step": 350
+    },
+    {
+      "epoch": 0.23580205911657257,
+      "grad_norm": 0.107421875,
+      "learning_rate": 0.00018900565556994984,
+      "loss": 1.156,
+      "step": 355
+    },
+    {
+      "epoch": 0.2391232148787778,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001884708392426776,
+      "loss": 1.1471,
+      "step": 360
+    },
+    {
+      "epoch": 0.24244437064098306,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 0.00018792411604295014,
+      "loss": 1.1302,
+      "step": 365
+    },
+    {
+      "epoch": 0.2457655264031883,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.0001873655595516611,
+      "loss": 1.1276,
+      "step": 370
+    },
+    {
+      "epoch": 0.24908668216539356,
+      "grad_norm": 0.279296875,
+      "learning_rate": 0.0001867952449422909,
+      "loss": 1.165,
+      "step": 375
+    },
+    {
+      "epoch": 0.2524078379275988,
+      "grad_norm": 0.19921875,
+      "learning_rate": 0.0001862132489707895,
+      "loss": 1.1524,
+      "step": 380
+    },
+    {
+      "epoch": 0.25572899368980406,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00018561964996524627,
+      "loss": 1.1459,
+      "step": 385
+    },
+    {
+      "epoch": 0.2590501494520093,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00018501452781534812,
+      "loss": 1.1375,
+      "step": 390
+    },
+    {
+      "epoch": 0.26237130521421453,
+      "grad_norm": 0.1083984375,
+      "learning_rate": 0.00018439796396162755,
+      "loss": 1.1394,
+      "step": 395
+    },
+    {
+      "epoch": 0.2656924609764198,
+      "grad_norm": 0.109375,
+      "learning_rate": 0.00018377004138450196,
+      "loss": 1.146,
+      "step": 400
+    },
+    {
+      "epoch": 0.26901361673862506,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 0.00018313084459310568,
+      "loss": 1.1391,
+      "step": 405
+    },
+    {
+      "epoch": 0.27233477250083027,
+      "grad_norm": 0.421875,
+      "learning_rate": 0.0001824804596139163,
+      "loss": 1.1368,
+      "step": 410
+    },
+    {
+      "epoch": 0.27565592826303553,
+      "grad_norm": 0.095703125,
+      "learning_rate": 0.00018181897397917673,
+      "loss": 1.1573,
+      "step": 415
+    },
+    {
+      "epoch": 0.2789770840252408,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 0.00018114647671511473,
+      "loss": 1.1502,
+      "step": 420
+    },
+    {
+      "epoch": 0.282298239787446,
+      "grad_norm": 0.09765625,
+      "learning_rate": 0.00018046305832996126,
+      "loss": 1.1461,
+      "step": 425
+    },
+    {
+      "epoch": 0.28561939554965127,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00017976881080176938,
+      "loss": 1.163,
+      "step": 430
+    },
+    {
+      "epoch": 0.28894055131185653,
+      "grad_norm": 0.10546875,
+      "learning_rate": 0.00017906382756603534,
+      "loss": 1.155,
+      "step": 435
+    },
+    {
+      "epoch": 0.2922617070740618,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001783482035031236,
+      "loss": 1.1576,
+      "step": 440
+    },
+    {
+      "epoch": 0.295582862836267,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 0.00017762203492549728,
+      "loss": 1.1548,
+      "step": 445
+    },
+    {
+      "epoch": 0.29890401859847227,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 0.000176885419564756,
+      "loss": 1.1501,
+      "step": 450
+    },
+    {
+      "epoch": 0.30222517436067753,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 0.00017613845655848248,
+      "loss": 1.1265,
+      "step": 455
+    },
+    {
+      "epoch": 0.30554633012288274,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 0.00017538124643690033,
+      "loss": 1.1424,
+      "step": 460
+    },
+    {
+      "epoch": 0.308867485885088,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00017461389110934382,
+      "loss": 1.1632,
+      "step": 465
+    },
+    {
+      "epoch": 0.31218864164729326,
+      "grad_norm": 0.1279296875,
+      "learning_rate": 0.00017383649385054276,
+      "loss": 1.1293,
+      "step": 470
+    },
+    {
+      "epoch": 0.3155097974094985,
+      "grad_norm": 0.103515625,
+      "learning_rate": 0.000173049159286723,
+      "loss": 1.1472,
+      "step": 475
+    },
+    {
+      "epoch": 0.31883095317170373,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 0.0001722519933815253,
+      "loss": 1.1435,
+      "step": 480
+    },
+    {
+      "epoch": 0.322152108933909,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 0.0001714451034217443,
+      "loss": 1.1612,
+      "step": 485
+    },
+    {
+      "epoch": 0.32547326469611426,
+      "grad_norm": 0.0859375,
+      "learning_rate": 0.0001706285980028892,
+      "loss": 1.1242,
+      "step": 490
+    },
+    {
+      "epoch": 0.32879442045831947,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016980258701456845,
+      "loss": 1.1492,
+      "step": 495
+    },
+    {
+      "epoch": 0.33211557622052473,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 0.00016896718162570009,
+      "loss": 1.1566,
+      "step": 500
+    },
+    {
+      "epoch": 0.33543673198273,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 0.00016812249426955032,
+      "loss": 1.1261,
+      "step": 505
+    },
+    {
+      "epoch": 0.33875788774493526,
+      "grad_norm": 0.125,
+      "learning_rate": 0.00016726863862860146,
+      "loss": 1.1389,
+      "step": 510
+    },
+    {
+      "epoch": 0.34207904350714047,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016640572961925182,
+      "loss": 1.1283,
+      "step": 515
+    },
+    {
+      "epoch": 0.34540019926934573,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00016553388337635,
+      "loss": 1.1372,
+      "step": 520
+    },
+    {
+      "epoch": 0.348721355031551,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016465321723756464,
+      "loss": 1.1392,
+      "step": 525
+    },
+    {
+      "epoch": 0.3520425107937562,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 0.00016376384972759236,
+      "loss": 1.1359,
+      "step": 530
+    },
+    {
+      "epoch": 0.35536366655596147,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00016286590054220642,
+      "loss": 1.129,
+      "step": 535
+    },
+    {
+      "epoch": 0.35868482231816673,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 0.00016195949053214709,
+      "loss": 1.1348,
+      "step": 540
+    },
+    {
+      "epoch": 0.362005978080372,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 0.00016104474168685725,
+      "loss": 1.1489,
+      "step": 545
+    },
+    {
+      "epoch": 0.3653271338425772,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 0.000160121777118064,
+      "loss": 1.1367,
+      "step": 550
+    },
+    {
+      "epoch": 0.36864828960478246,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.0001591907210432102,
+      "loss": 1.1236,
+      "step": 555
+    },
+    {
+      "epoch": 0.3719694453669877,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 0.00015825169876873592,
+      "loss": 1.1313,
+      "step": 560
+    },
+    {
+      "epoch": 0.37529060112919294,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.0001573048366732147,
+      "loss": 1.1452,
+      "step": 565
+    },
+    {
+      "epoch": 0.3786117568913982,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.00015635026219034445,
+      "loss": 1.1364,
+      "step": 570
+    },
+    {
+      "epoch": 0.38193291265360346,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00015538810379179694,
+      "loss": 1.1348,
+      "step": 575
+    },
+    {
+      "epoch": 0.3852540684158087,
+      "grad_norm": 0.10595703125,
+      "learning_rate": 0.0001544184909699272,
+      "loss": 1.1367,
+      "step": 580
+    },
+    {
+      "epoch": 0.38857522417801393,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.00015344155422034609,
+      "loss": 1.1194,
+      "step": 585
+    },
+    {
+      "epoch": 0.3918963799402192,
+      "grad_norm": 0.11376953125,
+      "learning_rate": 0.00015245742502435712,
+      "loss": 1.1346,
+      "step": 590
+    },
+    {
+      "epoch": 0.39521753570242446,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 0.00015146623583126134,
+      "loss": 1.1223,
+      "step": 595
+    },
+    {
+      "epoch": 0.39853869146462967,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 0.00015046812004053134,
+      "loss": 1.1088,
+      "step": 600
+    },
+    {
+      "epoch": 0.40185984722683493,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00014946321198385795,
+      "loss": 1.1381,
+      "step": 605
+    },
+    {
+      "epoch": 0.4051810029890402,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.00014845164690707087,
+      "loss": 1.1354,
+      "step": 610
+    },
+    {
+      "epoch": 0.40850215875124546,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 0.00014743356095193666,
+      "loss": 1.1204,
+      "step": 615
+    },
+    {
+      "epoch": 0.41182331451345067,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 0.00014640909113783622,
+      "loss": 1.1322,
+      "step": 620
+    },
+    {
+      "epoch": 0.41514447027565593,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.00014537837534332385,
+      "loss": 1.1271,
+      "step": 625
+    },
+    {
+      "epoch": 0.4184656260378612,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.0001443415522875708,
+      "loss": 1.1458,
+      "step": 630
+    },
+    {
+      "epoch": 0.4217867818000664,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.0001432987615116958,
+      "loss": 1.133,
+      "step": 635
+    },
+    {
+      "epoch": 0.42510793756227166,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 0.00014225014335998492,
+      "loss": 1.1346,
+      "step": 640
+    },
+    {
+      "epoch": 0.42842909332447693,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 0.0001411958389610031,
+      "loss": 1.1061,
+      "step": 645
+    },
+    {
+      "epoch": 0.4317502490866822,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 0.00014013599020860047,
+      "loss": 1.1341,
+      "step": 650
+    },
+    {
+      "epoch": 0.4350714048488874,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00013907073974281562,
+      "loss": 1.1186,
+      "step": 655
+    },
+    {
+      "epoch": 0.43839256061109266,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 0.00013800023093067814,
+      "loss": 1.1225,
+      "step": 660
+    },
+    {
+      "epoch": 0.4417137163732979,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 0.00013692460784691356,
+      "loss": 1.125,
+      "step": 665
+    },
+    {
+      "epoch": 0.44503487213550313,
+      "grad_norm": 0.09375,
+      "learning_rate": 0.0001358440152545533,
+      "loss": 1.1509,
+      "step": 670
+    },
+    {
+      "epoch": 0.4483560278977084,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001347585985854512,
+      "loss": 1.1305,
+      "step": 675
+    },
+    {
+      "epoch": 0.45167718365991366,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 0.000133668503920711,
+      "loss": 1.1143,
+      "step": 680
+    },
+    {
+      "epoch": 0.4549983394221189,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 0.0001325738779710257,
+      "loss": 1.1207,
+      "step": 685
+    },
+    {
+      "epoch": 0.45831949518432413,
+      "grad_norm": 0.091796875,
+      "learning_rate": 0.00013147486805693256,
+      "loss": 1.1355,
+      "step": 690
+    },
+    {
+      "epoch": 0.4616406509465294,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 0.0001303716220889859,
+      "loss": 1.1294,
+      "step": 695
+    },
+    {
+      "epoch": 0.46496180670873466,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00012926428854785052,
+      "loss": 1.1368,
+      "step": 700
+    },
+    {
+      "epoch": 0.46828296247093987,
+      "grad_norm": 0.08984375,
+      "learning_rate": 0.00012815301646431845,
+      "loss": 1.1347,
+      "step": 705
+    },
+    {
+      "epoch": 0.47160411823314513,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00012703795539925142,
+      "loss": 1.129,
+      "step": 710
+    },
+    {
+      "epoch": 0.4749252739953504,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 0.00012591925542345243,
+      "loss": 1.1162,
+      "step": 715
+    },
+    {
+      "epoch": 0.4782464297575556,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 0.0001247970670974682,
+      "loss": 1.147,
+      "step": 720
+    },
+    {
+      "epoch": 0.48156758551976087,
+      "grad_norm": 0.10546875,
+      "learning_rate": 0.00012367154145132608,
+      "loss": 1.1165,
+      "step": 725
+    },
+    {
+      "epoch": 0.48488874128196613,
+      "grad_norm": 0.1103515625,
+      "learning_rate": 0.00012254282996420753,
+      "loss": 1.1372,
+      "step": 730
+    },
+    {
+      "epoch": 0.4882098970441714,
+      "grad_norm": 0.107421875,
+      "learning_rate": 0.0001214110845440613,
+      "loss": 1.1144,
+      "step": 735
+    },
+    {
+      "epoch": 0.4915310528063766,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 0.00012027645750715892,
+      "loss": 1.1397,
+      "step": 740
+    },
+    {
+      "epoch": 0.49485220856858186,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 0.0001191391015575951,
+      "loss": 1.1364,
+      "step": 745
+    },
+    {
+      "epoch": 0.4981733643307871,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00011799916976673589,
+      "loss": 1.1234,
+      "step": 750
+    },
+    {
+      "epoch": 0.5014945200929923,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00011685681555261786,
+      "loss": 1.1223,
+      "step": 755
+    },
+    {
+      "epoch": 0.5048156758551976,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 0.00011571219265929998,
+      "loss": 1.1357,
+      "step": 760
+    },
+    {
+      "epoch": 0.5081368316174029,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 0.00011456545513617198,
+      "loss": 1.133,
+      "step": 765
+    },
+    {
+      "epoch": 0.5114579873796081,
+      "grad_norm": 0.12890625,
+      "learning_rate": 0.00011341675731722175,
+      "loss": 1.1346,
+      "step": 770
+    },
+    {
+      "epoch": 0.5147791431418134,
+      "grad_norm": 0.1611328125,
+      "learning_rate": 0.00011226625380026407,
+      "loss": 1.1094,
+      "step": 775
+    },
+    {
+      "epoch": 0.5181002989040187,
+      "grad_norm": 0.1376953125,
+      "learning_rate": 0.0001111140994261341,
+      "loss": 1.1246,
+      "step": 780
+    },
+    {
+      "epoch": 0.5214214546662238,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 0.00010996044925784806,
+      "loss": 1.0992,
+      "step": 785
+    },
+    {
+      "epoch": 0.5247426104284291,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 0.00010880545855973405,
+      "loss": 1.1271,
+      "step": 790
+    },
+    {
+      "epoch": 0.5280637661906343,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00010764928277653576,
+      "loss": 1.1272,
+      "step": 795
+    },
+    {
+      "epoch": 0.5313849219528396,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 0.00010649207751249188,
+      "loss": 1.1211,
+      "step": 800
+    },
+    {
+      "epoch": 0.5347060777150449,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 0.0001053339985103941,
+      "loss": 1.1108,
+      "step": 805
+    },
+    {
+      "epoch": 0.5380272334772501,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.00010417520163062626,
+      "loss": 1.1259,
+      "step": 810
+    },
+    {
+      "epoch": 0.5413483892394554,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 0.00010301584283018813,
+      "loss": 1.1131,
+      "step": 815
+    },
+    {
+      "epoch": 0.5446695450016605,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00010185607814170561,
+      "loss": 1.1278,
+      "step": 820
+    },
+    {
+      "epoch": 0.5479907007638658,
+      "grad_norm": 0.09765625,
+      "learning_rate": 0.00010069606365243123,
+      "loss": 1.1259,
+      "step": 825
+    },
+    {
+      "epoch": 0.5513118565260711,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 9.953595548323699e-05,
+      "loss": 1.1277,
+      "step": 830
+    },
+    {
+      "epoch": 0.5546330122882763,
+      "grad_norm": 0.11083984375,
+      "learning_rate": 9.837590976760282e-05,
+      "loss": 1.125,
+      "step": 835
+    },
+    {
+      "epoch": 0.5579541680504816,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 9.721608263060341e-05,
+      "loss": 1.1217,
+      "step": 840
+    },
+    {
+      "epoch": 0.5612753238126869,
+      "grad_norm": 0.109375,
+      "learning_rate": 9.605663016789583e-05,
+      "loss": 1.1234,
+      "step": 845
+    },
+    {
+      "epoch": 0.564596479574892,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 9.489770842471159e-05,
+      "loss": 1.1118,
+      "step": 850
+    },
+    {
+      "epoch": 0.5679176353370973,
+      "grad_norm": 0.1005859375,
+      "learning_rate": 9.373947337485522e-05,
+      "loss": 1.1207,
+      "step": 855
+    },
+    {
+      "epoch": 0.5712387910993025,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 9.258208089971232e-05,
+      "loss": 1.1324,
+      "step": 860
+    },
+    {
+      "epoch": 0.5745599468615078,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 9.142568676727043e-05,
+      "loss": 1.1263,
+      "step": 865
+    },
+    {
+      "epoch": 0.5778811026237131,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 9.027044661115485e-05,
+      "loss": 1.1263,
+      "step": 870
+    },
+    {
+      "epoch": 0.5812022583859183,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 8.911651590968259e-05,
+      "loss": 1.1125,
+      "step": 875
+    },
+    {
+      "epoch": 0.5845234141481236,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 8.79640499649374e-05,
+      "loss": 1.1256,
+      "step": 880
+    },
+    {
+      "epoch": 0.5878445699103287,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 8.68132038818684e-05,
+      "loss": 1.1185,
+      "step": 885
+    },
+    {
+      "epoch": 0.591165725672534,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 8.5664132547415e-05,
+      "loss": 1.146,
+      "step": 890
+    },
+    {
+      "epoch": 0.5944868814347393,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 8.451699060966173e-05,
+      "loss": 1.105,
+      "step": 895
+    },
+    {
+      "epoch": 0.5978080371969445,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 8.33719324570247e-05,
+      "loss": 1.1334,
+      "step": 900
+    },
+    {
+      "epoch": 0.6011291929591498,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 8.222911219747316e-05,
+      "loss": 1.1373,
+      "step": 905
+    },
+    {
+      "epoch": 0.6044503487213551,
+      "grad_norm": 0.1044921875,
+      "learning_rate": 8.108868363778894e-05,
+      "loss": 1.1089,
+      "step": 910
+    },
+    {
+      "epoch": 0.6077715044835603,
+      "grad_norm": 0.1240234375,
+      "learning_rate": 7.995080026286631e-05,
+      "loss": 1.1296,
+      "step": 915
+    },
+    {
+      "epoch": 0.6110926602457655,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 7.881561521505514e-05,
+      "loss": 1.1318,
+      "step": 920
+    },
+    {
+      "epoch": 0.6144138160079707,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 7.768328127355007e-05,
+      "loss": 1.1231,
+      "step": 925
+    },
+    {
+      "epoch": 0.617734971770176,
+      "grad_norm": 0.0859375,
+      "learning_rate": 7.655395083382899e-05,
+      "loss": 1.13,
+      "step": 930
+    },
+    {
+      "epoch": 0.6210561275323813,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 7.542777588714256e-05,
+      "loss": 1.1109,
+      "step": 935
+    },
+    {
+      "epoch": 0.6243772832945865,
+      "grad_norm": 0.09423828125,
+      "learning_rate": 7.430490800005854e-05,
+      "loss": 1.1166,
+      "step": 940
+    },
+    {
+      "epoch": 0.6276984390567918,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 7.318549829406318e-05,
+      "loss": 1.1117,
+      "step": 945
+    },
+    {
+      "epoch": 0.631019594818997,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 7.206969742522252e-05,
+      "loss": 1.121,
+      "step": 950
+    },
+    {
+      "epoch": 0.6343407505812022,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 7.095765556390606e-05,
+      "loss": 1.1349,
+      "step": 955
+    },
+    {
+      "epoch": 0.6376619063434075,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 6.984952237457647e-05,
+      "loss": 1.0884,
+      "step": 960
+    },
+    {
+      "epoch": 0.6409830621056127,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 6.874544699564663e-05,
+      "loss": 1.1405,
+      "step": 965
+    },
+    {
+      "epoch": 0.644304217867818,
+      "grad_norm": 0.203125,
+      "learning_rate": 6.764557801940771e-05,
+      "loss": 1.1103,
+      "step": 970
+    },
+    {
+      "epoch": 0.6476253736300233,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 6.655006347203128e-05,
+      "loss": 1.1222,
+      "step": 975
+    },
+    {
+      "epoch": 0.6509465293922285,
+      "grad_norm": 0.0927734375,
+      "learning_rate": 6.545905079364678e-05,
+      "loss": 1.1323,
+      "step": 980
+    },
+    {
+      "epoch": 0.6542676851544338,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 6.437268681849825e-05,
+      "loss": 1.1185,
+      "step": 985
+    },
+    {
+      "epoch": 0.6575888409166389,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 6.329111775518284e-05,
+      "loss": 1.1153,
+      "step": 990
+    },
+    {
+      "epoch": 0.6609099966788442,
+      "grad_norm": 0.09375,
+      "learning_rate": 6.221448916697323e-05,
+      "loss": 1.1356,
+      "step": 995
+    },
+    {
+      "epoch": 0.6642311524410495,
+      "grad_norm": 0.09716796875,
+      "learning_rate": 6.114294595222667e-05,
+      "loss": 1.1316,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6675523082032547,
+      "grad_norm": 0.1484375,
+      "learning_rate": 6.0076632324884184e-05,
+      "loss": 1.1045,
+      "step": 1005
+    },
+    {
+      "epoch": 0.67087346396546,
+      "grad_norm": 0.083984375,
+      "learning_rate": 5.9015691795061276e-05,
+      "loss": 1.1136,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6741946197276653,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 5.796026714973358e-05,
+      "loss": 1.1233,
+      "step": 1015
+    },
+    {
+      "epoch": 0.6775157754898705,
+      "grad_norm": 0.083984375,
+      "learning_rate": 5.691050043352e-05,
+      "loss": 1.1125,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6808369312520757,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 5.586653292956536e-05,
+      "loss": 1.1257,
+      "step": 1025
+    },
+    {
+      "epoch": 0.6841580870142809,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 5.482850514052593e-05,
+      "loss": 1.112,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6874792427764862,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 5.379655676965985e-05,
+      "loss": 1.1022,
+      "step": 1035
+    },
+    {
+      "epoch": 0.6908003985386915,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 5.2770826702025024e-05,
+      "loss": 1.1031,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6941215543008967,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 5.1751452985787294e-05,
+      "loss": 1.1314,
+      "step": 1045
+    },
+    {
+      "epoch": 0.697442710063102,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 5.073857281364116e-05,
+      "loss": 1.115,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7007638658253073,
+      "grad_norm": 0.087890625,
+      "learning_rate": 4.9732322504345784e-05,
+      "loss": 1.1162,
+      "step": 1055
+    },
+    {
+      "epoch": 0.7040850215875124,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 4.873283748437832e-05,
+      "loss": 1.1398,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7074061773497177,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 4.7740252269707545e-05,
+      "loss": 1.1165,
+      "step": 1065
+    },
+    {
+      "epoch": 0.7107273331119229,
+      "grad_norm": 0.09521484375,
+      "learning_rate": 4.6754700447690145e-05,
+      "loss": 1.1134,
+      "step": 1070
+    },
+    {
+      "epoch": 0.7140484888741282,
+      "grad_norm": 0.087890625,
+      "learning_rate": 4.57763146590916e-05,
+      "loss": 1.1101,
+      "step": 1075
+    },
+    {
+      "epoch": 0.7173696446363335,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 4.4805226580234794e-05,
+      "loss": 1.1058,
+      "step": 1080
+    },
+    {
+      "epoch": 0.7206908003985387,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 4.384156690527842e-05,
+      "loss": 1.1228,
+      "step": 1085
+    },
+    {
+      "epoch": 0.724011956160744,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 4.2885465328627275e-05,
+      "loss": 1.1173,
+      "step": 1090
+    },
+    {
+      "epoch": 0.7273331119229491,
+      "grad_norm": 0.10498046875,
+      "learning_rate": 4.193705052747737e-05,
+      "loss": 1.1233,
+      "step": 1095
+    },
+    {
+      "epoch": 0.7306542676851544,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 4.0996450144498044e-05,
+      "loss": 1.1163,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7339754234473597,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 4.0063790770652876e-05,
+      "loss": 1.1264,
+      "step": 1105
+    },
+    {
+      "epoch": 0.7372965792095649,
+      "grad_norm": 0.078125,
+      "learning_rate": 3.913919792816252e-05,
+      "loss": 1.1334,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7406177349717702,
+      "grad_norm": 0.076171875,
+      "learning_rate": 3.822279605361138e-05,
+      "loss": 1.1133,
+      "step": 1115
+    },
+    {
+      "epoch": 0.7439388907339755,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 3.731470848120005e-05,
+      "loss": 1.1068,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7472600464961807,
+      "grad_norm": 0.0947265625,
+      "learning_rate": 3.64150574261465e-05,
+      "loss": 1.1204,
+      "step": 1125
+    },
+    {
+      "epoch": 0.7505812022583859,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 3.552396396823774e-05,
+      "loss": 1.1446,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7539023580205911,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 3.464154803553408e-05,
+      "loss": 1.0895,
+      "step": 1135
+    },
+    {
+      "epoch": 0.7572235137827964,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 3.376792838822873e-05,
+      "loss": 1.1094,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7605446695450017,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 3.2903222602664464e-05,
+      "loss": 1.1178,
+      "step": 1145
+    },
+    {
+      "epoch": 0.7638658253072069,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 3.20475470555094e-05,
+      "loss": 1.1149,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7671869810694122,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 3.1201016908094514e-05,
+      "loss": 1.1282,
+      "step": 1155
+    },
+    {
+      "epoch": 0.7705081368316175,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 3.0363746090914724e-05,
+      "loss": 1.1392,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7738292925938226,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 2.9535847288295325e-05,
+      "loss": 1.0927,
+      "step": 1165
+    },
+    {
+      "epoch": 0.7771504483560279,
+      "grad_norm": 0.08642578125,
+      "learning_rate": 2.8717431923226422e-05,
+      "loss": 1.1235,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7804716041182331,
+      "grad_norm": 0.08740234375,
+      "learning_rate": 2.7908610142367143e-05,
+      "loss": 1.109,
+      "step": 1175
+    },
+    {
+      "epoch": 0.7837927598804384,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 2.7109490801221327e-05,
+      "loss": 1.1214,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7871139156426437,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 2.632018144948727e-05,
+      "loss": 1.1099,
+      "step": 1185
+    },
+    {
+      "epoch": 0.7904350714048489,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 2.5540788316583207e-05,
+      "loss": 1.1275,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7937562271670542,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 2.4771416297350247e-05,
+      "loss": 1.1306,
+      "step": 1195
+    },
+    {
+      "epoch": 0.7970773829292593,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 2.4012168937935096e-05,
+      "loss": 1.0969,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8003985386914646,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 2.326314842185443e-05,
+      "loss": 1.1186,
+      "step": 1205
+    },
+    {
+      "epoch": 0.8037196944536699,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 2.252445555624225e-05,
+      "loss": 1.1222,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8070408502158751,
+      "grad_norm": 0.0966796875,
+      "learning_rate": 2.1796189758282915e-05,
+      "loss": 1.1112,
+      "step": 1215
+    },
+    {
+      "epoch": 0.8103620059780804,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 2.107844904183096e-05,
+      "loss": 1.0992,
+      "step": 1220
+    },
+    {
+      "epoch": 0.8136831617402857,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 2.0371330004219967e-05,
+      "loss": 1.1067,
+      "step": 1225
+    },
+    {
+      "epoch": 0.8170043175024909,
+      "grad_norm": 0.0859375,
+      "learning_rate": 1.9674927813261856e-05,
+      "loss": 1.135,
+      "step": 1230
+    },
+    {
+      "epoch": 0.8203254732646961,
+      "grad_norm": 0.0849609375,
+      "learning_rate": 1.8989336194438757e-05,
+      "loss": 1.1272,
+      "step": 1235
+    },
+    {
+      "epoch": 0.8236466290269013,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 1.831464741828903e-05,
+      "loss": 1.11,
+      "step": 1240
+    },
+    {
+      "epoch": 0.8269677847891066,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 1.7650952287988864e-05,
+      "loss": 1.123,
+      "step": 1245
+    },
+    {
+      "epoch": 0.8302889405513119,
+      "grad_norm": 0.08203125,
+      "learning_rate": 1.699834012713155e-05,
+      "loss": 1.1179,
+      "step": 1250
+    },
+    {
+      "epoch": 0.8336100963135171,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 1.6356898767705954e-05,
+      "loss": 1.1216,
+      "step": 1255
+    },
+    {
+      "epoch": 0.8369312520757224,
+      "grad_norm": 0.078125,
+      "learning_rate": 1.5726714538275423e-05,
+      "loss": 1.1349,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8402524078379277,
+      "grad_norm": 0.0791015625,
+      "learning_rate": 1.5107872252359389e-05,
+      "loss": 1.1137,
+      "step": 1265
+    },
+    {
+      "epoch": 0.8435735636001328,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 1.4500455197018703e-05,
+      "loss": 1.1134,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8468947193623381,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 1.3904545121646317e-05,
+      "loss": 1.1245,
+      "step": 1275
+    },
+    {
+      "epoch": 0.8502158751245433,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 1.3320222226965118e-05,
+      "loss": 1.1231,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8535370308867486,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 1.2747565154234109e-05,
+      "loss": 1.1352,
+      "step": 1285
+    },
+    {
+      "epoch": 0.8568581866489539,
+      "grad_norm": 0.0859375,
+      "learning_rate": 1.2186650974664337e-05,
+      "loss": 1.1065,
+      "step": 1290
+    },
+    {
+      "epoch": 0.8601793424111591,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 1.1637555179046345e-05,
+      "loss": 1.1235,
+      "step": 1295
+    },
+    {
+      "epoch": 0.8635004981733644,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 1.1100351667590204e-05,
+      "loss": 1.1458,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8668216539355695,
+      "grad_norm": 0.080078125,
+      "learning_rate": 1.057511273997962e-05,
+      "loss": 1.1097,
+      "step": 1305
+    },
+    {
+      "epoch": 0.8701428096977748,
+      "grad_norm": 0.08203125,
+      "learning_rate": 1.0061909085641396e-05,
+      "loss": 1.1038,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8734639654599801,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 9.560809774231871e-06,
+      "loss": 1.1226,
+      "step": 1315
+    },
+    {
+      "epoch": 0.8767851212221853,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 9.0718822463409e-06,
+      "loss": 1.1157,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8801062769843906,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 8.595192304415534e-06,
+      "loss": 1.0975,
+      "step": 1325
+    },
+    {
+      "epoch": 0.8834274327465959,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 8.130804103903956e-06,
+      "loss": 1.1056,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8867485885088011,
+      "grad_norm": 0.123046875,
+      "learning_rate": 7.678780144620956e-06,
+      "loss": 1.1328,
+      "step": 1335
+    },
+    {
+      "epoch": 0.8900697442710063,
+      "grad_norm": 0.083984375,
+      "learning_rate": 7.2391812623366025e-06,
+      "loss": 1.1226,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8933909000332115,
+      "grad_norm": 0.10400390625,
+      "learning_rate": 6.812066620588519e-06,
+      "loss": 1.1112,
+      "step": 1345
+    },
+    {
+      "epoch": 0.8967120557954168,
+      "grad_norm": 0.0888671875,
+      "learning_rate": 6.397493702719226e-06,
+      "loss": 1.121,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9000332115576221,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 5.995518304139991e-06,
+      "loss": 1.1104,
+      "step": 1355
+    },
+    {
+      "epoch": 0.9033543673198273,
+      "grad_norm": 0.08984375,
+      "learning_rate": 5.606194524821429e-06,
+      "loss": 1.1058,
+      "step": 1360
+    },
+    {
+      "epoch": 0.9066755230820326,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 5.229574762012379e-06,
+      "loss": 1.1069,
+      "step": 1365
+    },
+    {
+      "epoch": 0.9099966788442378,
+      "grad_norm": 0.08984375,
+      "learning_rate": 4.865709703188193e-06,
+      "loss": 1.1414,
+      "step": 1370
+    },
+    {
+      "epoch": 0.913317834606443,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 4.514648319228798e-06,
+      "loss": 1.1161,
+      "step": 1375
+    },
+    {
+      "epoch": 0.9166389903686483,
+      "grad_norm": 0.07763671875,
+      "learning_rate": 4.1764378578279865e-06,
+      "loss": 1.1083,
+      "step": 1380
+    },
+    {
+      "epoch": 0.9199601461308535,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 3.8511238371345845e-06,
+      "loss": 1.1135,
+      "step": 1385
+    },
+    {
+      "epoch": 0.9232813018930588,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 3.5387500396263483e-06,
+      "loss": 1.1137,
+      "step": 1390
+    },
+    {
+      "epoch": 0.9266024576552641,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 3.2393585062175493e-06,
+      "loss": 1.1097,
+      "step": 1395
+    },
+    {
+      "epoch": 0.9299236134174693,
+      "grad_norm": 0.08349609375,
+      "learning_rate": 2.9529895306007804e-06,
+      "loss": 1.1307,
+      "step": 1400
+    },
+    {
+      "epoch": 0.9332447691796745,
+      "grad_norm": 0.09619140625,
+      "learning_rate": 2.6796816538241065e-06,
+      "loss": 1.1214,
+      "step": 1405
+    },
+    {
+      "epoch": 0.9365659249418797,
+      "grad_norm": 0.083984375,
+      "learning_rate": 2.419471659104e-06,
+      "loss": 1.1157,
+      "step": 1410
+    },
+    {
+      "epoch": 0.939887080704085,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 2.1723945668748247e-06,
+      "loss": 1.1047,
+      "step": 1415
+    },
+    {
+      "epoch": 0.9432082364662903,
+      "grad_norm": 0.10205078125,
+      "learning_rate": 1.9384836300755937e-06,
+      "loss": 1.1367,
+      "step": 1420
+    },
+    {
+      "epoch": 0.9465293922284955,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 1.717770329674684e-06,
+      "loss": 1.0773,
+      "step": 1425
+    },
+    {
+      "epoch": 0.9498505479907008,
+      "grad_norm": 0.0771484375,
+      "learning_rate": 1.5102843704328684e-06,
+      "loss": 1.1348,
+      "step": 1430
+    },
+    {
+      "epoch": 0.953171703752906,
+      "grad_norm": 0.080078125,
+      "learning_rate": 1.3160536769055708e-06,
+      "loss": 1.1134,
+      "step": 1435
+    },
+    {
+      "epoch": 0.9564928595151112,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 1.1351043896846047e-06,
+      "loss": 1.1216,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9598140152773165,
+      "grad_norm": 0.09375,
+      "learning_rate": 9.674608618799985e-07,
+      "loss": 1.1085,
+      "step": 1445
+    },
+    {
+      "epoch": 0.9631351710395217,
+      "grad_norm": 0.0830078125,
+      "learning_rate": 8.131456558424622e-07,
+      "loss": 1.1218,
+      "step": 1450
+    },
+    {
+      "epoch": 0.966456326801727,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 6.721795401268493e-07,
+      "loss": 1.1021,
+      "step": 1455
+    },
+    {
+      "epoch": 0.9697774825639323,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 5.445814866969712e-07,
+      "loss": 1.1071,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9730986383261375,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 4.3036866837224964e-07,
+      "loss": 1.0951,
+      "step": 1465
+    },
+    {
+      "epoch": 0.9764197940883428,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 3.295564565165554e-07,
+      "loss": 1.1135,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9797409498505479,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 2.4215841896938487e-07,
+      "loss": 1.1155,
+      "step": 1475
+    },
+    {
+      "epoch": 0.9830621056127532,
+      "grad_norm": 0.1533203125,
+      "learning_rate": 1.681863182198984e-07,
+      "loss": 1.1137,
+      "step": 1480
+    },
+    {
+      "epoch": 0.9863832613749585,
+      "grad_norm": 0.083984375,
+      "learning_rate": 1.0765010982378699e-07,
+      "loss": 1.1328,
+      "step": 1485
+    },
+    {
+      "epoch": 0.9897044171371637,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 6.055794106347712e-08,
+      "loss": 1.1114,
+      "step": 1490
+    },
+    {
+      "epoch": 0.993025572899369,
+      "grad_norm": 0.0869140625,
+      "learning_rate": 2.6916149851563543e-08,
+      "loss": 1.1065,
+      "step": 1495
+    },
+    {
+      "epoch": 0.9963467286615743,
+      "grad_norm": 0.08251953125,
+      "learning_rate": 6.729263877847114e-09,
+      "loss": 1.1432,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9996678844237795,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.0,
+      "loss": 1.1166,
+      "step": 1505
+    },
+    {
+      "epoch": 0.9996678844237795,
+      "eval_loss": 1.3468068838119507,
+      "eval_runtime": 2438.0312,
+      "eval_samples_per_second": 5.613,
+      "eval_steps_per_second": 5.613,
+      "step": 1505
+    },
+    {
+      "epoch": 0.9996678844237795,
+      "step": 1505,
+      "total_flos": 4.73786206333698e+18,
+      "train_loss": 0.5388378948072262,
+      "train_runtime": 65741.8056,
+      "train_samples_per_second": 2.931,
+      "train_steps_per_second": 0.023
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1505,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "total_flos": 4.73786206333698e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a07f8eeee0117d1da987b7a80484f52ff03acdc93bc695bd367245b955d5f4c4
+size 5112