Upload folder using huggingface_hub

.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

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/linzhihang/zhangyuhao/ACLlama_s2s/output/S2S/S2S_finetune_small_lr1e-4_S2S-KD-unit-languge-new-0804-filter_kd_offline_base_merge_0808_20string_1e-4/checkpoint-16000",
+  "adapter_size": 1280,
+  "architectures": [
+    "ACLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "audio_token_len": 750,
+  "audio_tower": "/linzhihang/LLMs/whisper-v3",
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "ACLlama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.48.1",
+  "unit_output": "finetune_kd",
+  "unit_vocab": "/linzhihang/zhangyuhao/unit_language/v6.8k.dict",
+  "unit_vocab_size": 7807,
+  "use_cache": false,
+  "vocab_size": 128257
+}

finetune_lora_llama3.1_8B_Instruct_s2s_zyh.sh

@@ -0,0 +1,90 @@
+source /linzhihang/conda_env/init.sh
+conda activate s2s
+cd /linzhihang/zhangyuhao/ACLlama_s2s/scripts
+
+prefix=/linzhihang/zhangyuhao/ACLlama_s2s
+
+# NAME
+TASK=S2S
+stage=finetune  # edit in config
+model_size=small    # edit in config
+lr=3e-5
+# subtag=shareEmbW_CR_0507_base_Echox_s2s_pretrained_0503
+# subtag=FirstTurnS2T+aligner_0505
+# subtag=QA_OneTurn+aligner_Lora_0510
+# subtag=ASR_UnitLanguage_4gram_BPE+aligner_0513
+# subtag=QA_OneTurn_ALL_Lora_0516
+# subtag=QA_OneTurn_ALL_Lora_0517
+#subtag=QA_OneTurn_ALL_Lora_0618_newGen_80k_spm_epoch10-embedcon-10epoch-large-adapter-add-prefix
+subtag=kd_offline_base_merge_0820_tune_bench
+
+
+
+# base_model=/mnt/speech/zhangyuhao/text_to_speech/ACLlama_t2u/Echox_s2s_0516 # unit
+#base_model=/linzhihang/zhangyuhao/ACLlama_s2s/Echox_s2s_unit_language_0529 # unit language
+#base_model=/linzhihang/zhangyuhao/ACLlama_s2s/Echox_s2s_unit_language_0625 # unit language
+#base_model=/linzhihang/zhangyuhao/ACLlama_s2s/Echox_s2s_KD_unit_langauge_0802_large_8B_check
+base_model=/linzhihang/zhangyuhao/ACLlama_s2s/output/S2S/S2S_finetune_small_lr1e-4_S2S-KD-unit-languge-new-0804-filter_kd_offline_base_merge_0808_20string_1e-4/checkpoint-16000
+#base_model=/linzhihang/zhangyuhao/ACLlama_s2s/output/S2S/S2S_finetune_small_lr1e-4_S2S-KD-unit-new-0812-bench-filter-8B_kd_offline_base_merge_0814/checkpoint-12200
+# DATA
+
+# data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/magpie_wer-filter-kd-40k-echo-ul-spm.json
+#data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/magpie-slice-unit-languge-new-0618.json
+#data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/magpie-slice-unit-languge-new-0629-filter.json
+#data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/magpie-slice-unit-languge-new-0706-filter.json
+#data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/magpie-slice-unit-languge-new-0717-filter.json
+#data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/S2S-KD-unit-languge-new-0804-filter.json
+data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/S2S-KD-unit-languge-new-0808-bench-filter-8B.json
+#data_json=/linzhihang/zhangyuhao/ACLlama_s2s/data/S2S-KD-unit-new-0812-bench-filter-8B.json
+
+
+training_set=${TASK}_${stage}_${model_size}_lr${lr}
+model_tag="${training_set}_$(basename "$data_json" .json)_${subtag}"
+
+checkpoint_dir=$prefix/output/$TASK/$model_tag
+echo $checkpoint_dir
+mkdir -p $checkpoint_dir
+cp $0 $checkpoint_dir/
+
+# CMD
+NCCL_P2P_DISABLE=1 \
+NCCL_IB_DISABLE=1 \
+CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7 \
+torchrun \
+--nproc_per_node 8 \
+--nnodes 1 \
+--node_rank 0 \
+--master_addr localhost \
+--master_port 7897 \
+$prefix/finetune_acllama_s2s_zyh.py \
+--audio_model_name_or_path "/linzhihang/LLMs/whisper-v3" \
+--text_model_name_or_path $base_model \
+--data_path "$data_json" \
+--fp16 True \
+--output_dir "$checkpoint_dir" \
+--num_train_epochs 1 \
+--per_device_train_batch_size 1 \
+--per_device_eval_batch_size 1 \
+--gradient_accumulation_steps 1 \
+--evaluation_strategy "no" \
+--save_strategy "steps" \
+--save_steps 100 \
+--save_total_limit 1 \
+--learning_rate $lr \
+--weight_decay 0.1 \
+--adam_beta2 0.95 \
+--warmup_ratio 0.01 \
+--lr_scheduler_type "inverse_sqrt" \
+--logging_steps 1 \
+--report_to "none" \
+--model_max_length 1024 \
+--gradient_checkpointing True \
+--lazy_preprocess True \
+--deepspeed "$prefix/config/ds_config_zero2.json" #\
+#--use_lora #> $checkpoint_dir/train.log # 2>&1
+
+# --use_lora
+#--data_path "$prefix/data/libri_train_update.json" \
+#--text_model_name_or_path "/mnt/user/zhangyuhao/LLM/llama3-instruct/llama3_1-8B/" \
+#--data_path "../data/libri_train_other460.json" \
+#--data_path "../data/train_mt_orgnize.json" \

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.48.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bd267beafe68de4b132e0719cba40e5c8ad5581ac3fb64803d3b52d03d248bb
+size 4976706784

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029f0eb72b0f7e6a46c2237425686aa063799720f7071e9923a403fa2b4edce9
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d415012d58d8177e99151ccb2ba8fd4ac8ce44c0f1a33601317dc0f0d33b70f4
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8a1641d1405012c16de4af1e47378abccf540b535488d0af278d980a192043a
+size 4320743784

model.safetensors.index.json

@@ -0,0 +1,403 @@
+{
+  "metadata": {
+    "total_size": 19213122560
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.linear1.bias": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.linear1.weight": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.linear2.bias": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.linear2.weight": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.norm1.bias": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.norm1.weight": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.norm2.bias": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.norm2.weight": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.self_attn.in_proj_bias": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.self_attn.in_proj_weight": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.self_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.asr_transformer_encoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.audio_feature_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.lbm.atten_layer_norm.bias": "model-00004-of-00004.safetensors",
+    "model.lbm.atten_layer_norm.weight": "model-00004-of-00004.safetensors",
+    "model.lbm.encoder_attn.in_proj_bias": "model-00004-of-00004.safetensors",
+    "model.lbm.encoder_attn.in_proj_weight": "model-00004-of-00004.safetensors",
+    "model.lbm.encoder_attn.out_proj.bias": "model-00004-of-00004.safetensors",
+    "model.lbm.encoder_attn.out_proj.weight": "model-00004-of-00004.safetensors",
+    "model.mm_projector1.bias": "model-00004-of-00004.safetensors",
+    "model.mm_projector1.weight": "model-00004-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.out_norm.bias": "model-00004-of-00004.safetensors",
+    "model.out_norm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.adapter.bias": "model-00004-of-00004.safetensors",
+    "unit_translator.adapter.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.aligner_MLP.0.bias": "model-00004-of-00004.safetensors",
+    "unit_translator.aligner_MLP.0.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.aligner_MLP.3.bias": "model-00004-of-00004.safetensors",
+    "unit_translator.aligner_MLP.3.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.lm_head.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.embed_tokens.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.0.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.3.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.6.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.model.norm.weight": "model-00004-of-00004.safetensors",
+    "unit_translator.unit_embedding.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a865fdb055caa7756668269331a01eb5a104a8b9ad3e4571f6b08dd8135451c
+size 18735896

trainer_state.json

@@ -0,0 +1,2982 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 420,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002380952380952381,
+      "grad_norm": 0.0,
+      "learning_rate": 0,
+      "loss": 0.5013,
+      "step": 1
+    },
+    {
+      "epoch": 0.004761904761904762,
+      "grad_norm": 1.2982189655303955,
+      "learning_rate": 0.0,
+      "loss": 0.4693,
+      "step": 2
+    },
+    {
+      "epoch": 0.007142857142857143,
+      "grad_norm": 1.3160841464996338,
+      "learning_rate": 1.2920296742201791e-05,
+      "loss": 0.4462,
+      "step": 3
+    },
+    {
+      "epoch": 0.009523809523809525,
+      "grad_norm": 1.3160841464996338,
+      "learning_rate": 1.2920296742201791e-05,
+      "loss": 0.8593,
+      "step": 4
+    },
+    {
+      "epoch": 0.011904761904761904,
+      "grad_norm": 1.3160841464996338,
+      "learning_rate": 1.2920296742201791e-05,
+      "loss": 0.8663,
+      "step": 5
+    },
+    {
+      "epoch": 0.014285714285714285,
+      "grad_norm": 1.0395259857177734,
+      "learning_rate": 2.0478185834579563e-05,
+      "loss": 0.5107,
+      "step": 6
+    },
+    {
+      "epoch": 0.016666666666666666,
+      "grad_norm": 1.0972439050674438,
+      "learning_rate": 2.5840593484403582e-05,
+      "loss": 0.5832,
+      "step": 7
+    },
+    {
+      "epoch": 0.01904761904761905,
+      "grad_norm": 1.2451457977294922,
+      "learning_rate": 3e-05,
+      "loss": 0.4994,
+      "step": 8
+    },
+    {
+      "epoch": 0.02142857142857143,
+      "grad_norm": 1.5299328565597534,
+      "learning_rate": 3e-05,
+      "loss": 0.5632,
+      "step": 9
+    },
+    {
+      "epoch": 0.023809523809523808,
+      "grad_norm": 1.456752061843872,
+      "learning_rate": 3e-05,
+      "loss": 0.5448,
+      "step": 10
+    },
+    {
+      "epoch": 0.02619047619047619,
+      "grad_norm": 0.7797374725341797,
+      "learning_rate": 3e-05,
+      "loss": 0.4222,
+      "step": 11
+    },
+    {
+      "epoch": 0.02857142857142857,
+      "grad_norm": 0.992181658744812,
+      "learning_rate": 3e-05,
+      "loss": 0.5173,
+      "step": 12
+    },
+    {
+      "epoch": 0.030952380952380953,
+      "grad_norm": 1.0963839292526245,
+      "learning_rate": 3e-05,
+      "loss": 0.4048,
+      "step": 13
+    },
+    {
+      "epoch": 0.03333333333333333,
+      "grad_norm": 1.3775476217269897,
+      "learning_rate": 3e-05,
+      "loss": 0.4774,
+      "step": 14
+    },
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 1.551168441772461,
+      "learning_rate": 3e-05,
+      "loss": 0.5603,
+      "step": 15
+    },
+    {
+      "epoch": 0.0380952380952381,
+      "grad_norm": 1.189092993736267,
+      "learning_rate": 3e-05,
+      "loss": 0.4756,
+      "step": 16
+    },
+    {
+      "epoch": 0.04047619047619048,
+      "grad_norm": 1.0813432931900024,
+      "learning_rate": 3e-05,
+      "loss": 0.4955,
+      "step": 17
+    },
+    {
+      "epoch": 0.04285714285714286,
+      "grad_norm": 1.224169373512268,
+      "learning_rate": 3e-05,
+      "loss": 0.4906,
+      "step": 18
+    },
+    {
+      "epoch": 0.04523809523809524,
+      "grad_norm": 0.7351661324501038,
+      "learning_rate": 3e-05,
+      "loss": 0.4717,
+      "step": 19
+    },
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 0.8378927707672119,
+      "learning_rate": 3e-05,
+      "loss": 0.4436,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.2906426191329956,
+      "learning_rate": 3e-05,
+      "loss": 0.4294,
+      "step": 21
+    },
+    {
+      "epoch": 0.05238095238095238,
+      "grad_norm": 0.9292688369750977,
+      "learning_rate": 3e-05,
+      "loss": 0.4252,
+      "step": 22
+    },
+    {
+      "epoch": 0.05476190476190476,
+      "grad_norm": 0.757605254650116,
+      "learning_rate": 3e-05,
+      "loss": 0.4078,
+      "step": 23
+    },
+    {
+      "epoch": 0.05714285714285714,
+      "grad_norm": 0.8978239893913269,
+      "learning_rate": 3e-05,
+      "loss": 0.4561,
+      "step": 24
+    },
+    {
+      "epoch": 0.05952380952380952,
+      "grad_norm": 0.7445272207260132,
+      "learning_rate": 3e-05,
+      "loss": 0.4007,
+      "step": 25
+    },
+    {
+      "epoch": 0.06190476190476191,
+      "grad_norm": 0.755946934223175,
+      "learning_rate": 3e-05,
+      "loss": 0.3974,
+      "step": 26
+    },
+    {
+      "epoch": 0.06428571428571428,
+      "grad_norm": 1.2127957344055176,
+      "learning_rate": 3e-05,
+      "loss": 0.5496,
+      "step": 27
+    },
+    {
+      "epoch": 0.06666666666666667,
+      "grad_norm": 1.2571460008621216,
+      "learning_rate": 3e-05,
+      "loss": 0.4526,
+      "step": 28
+    },
+    {
+      "epoch": 0.06904761904761905,
+      "grad_norm": 0.9187604784965515,
+      "learning_rate": 3e-05,
+      "loss": 0.4042,
+      "step": 29
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.990939736366272,
+      "learning_rate": 3e-05,
+      "loss": 0.4855,
+      "step": 30
+    },
+    {
+      "epoch": 0.07380952380952381,
+      "grad_norm": 1.0081547498703003,
+      "learning_rate": 3e-05,
+      "loss": 0.5543,
+      "step": 31
+    },
+    {
+      "epoch": 0.0761904761904762,
+      "grad_norm": 0.696738600730896,
+      "learning_rate": 3e-05,
+      "loss": 0.4036,
+      "step": 32
+    },
+    {
+      "epoch": 0.07857142857142857,
+      "grad_norm": 1.7002297639846802,
+      "learning_rate": 3e-05,
+      "loss": 0.4686,
+      "step": 33
+    },
+    {
+      "epoch": 0.08095238095238096,
+      "grad_norm": 0.8276028633117676,
+      "learning_rate": 3e-05,
+      "loss": 0.4009,
+      "step": 34
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 1.270995020866394,
+      "learning_rate": 3e-05,
+      "loss": 0.4926,
+      "step": 35
+    },
+    {
+      "epoch": 0.08571428571428572,
+      "grad_norm": 1.0746862888336182,
+      "learning_rate": 3e-05,
+      "loss": 0.4982,
+      "step": 36
+    },
+    {
+      "epoch": 0.0880952380952381,
+      "grad_norm": 1.0116355419158936,
+      "learning_rate": 3e-05,
+      "loss": 0.3548,
+      "step": 37
+    },
+    {
+      "epoch": 0.09047619047619047,
+      "grad_norm": 0.9556488394737244,
+      "learning_rate": 3e-05,
+      "loss": 0.4268,
+      "step": 38
+    },
+    {
+      "epoch": 0.09285714285714286,
+      "grad_norm": 0.752404510974884,
+      "learning_rate": 3e-05,
+      "loss": 0.4496,
+      "step": 39
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.7381091713905334,
+      "learning_rate": 3e-05,
+      "loss": 0.4412,
+      "step": 40
+    },
+    {
+      "epoch": 0.09761904761904762,
+      "grad_norm": 1.2671267986297607,
+      "learning_rate": 3e-05,
+      "loss": 0.4382,
+      "step": 41
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.7863288521766663,
+      "learning_rate": 3e-05,
+      "loss": 0.4186,
+      "step": 42
+    },
+    {
+      "epoch": 0.10238095238095238,
+      "grad_norm": 0.9142912030220032,
+      "learning_rate": 3e-05,
+      "loss": 0.442,
+      "step": 43
+    },
+    {
+      "epoch": 0.10476190476190476,
+      "grad_norm": 0.9501491189002991,
+      "learning_rate": 3e-05,
+      "loss": 0.5339,
+      "step": 44
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 0.888054609298706,
+      "learning_rate": 3e-05,
+      "loss": 0.4928,
+      "step": 45
+    },
+    {
+      "epoch": 0.10952380952380952,
+      "grad_norm": 0.8860450983047485,
+      "learning_rate": 3e-05,
+      "loss": 0.4081,
+      "step": 46
+    },
+    {
+      "epoch": 0.11190476190476191,
+      "grad_norm": 0.894538164138794,
+      "learning_rate": 3e-05,
+      "loss": 0.4213,
+      "step": 47
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.657795786857605,
+      "learning_rate": 3e-05,
+      "loss": 0.4112,
+      "step": 48
+    },
+    {
+      "epoch": 0.11666666666666667,
+      "grad_norm": 1.4137582778930664,
+      "learning_rate": 3e-05,
+      "loss": 0.5444,
+      "step": 49
+    },
+    {
+      "epoch": 0.11904761904761904,
+      "grad_norm": 1.1915364265441895,
+      "learning_rate": 3e-05,
+      "loss": 0.4655,
+      "step": 50
+    },
+    {
+      "epoch": 0.12142857142857143,
+      "grad_norm": 0.8001396059989929,
+      "learning_rate": 3e-05,
+      "loss": 0.4571,
+      "step": 51
+    },
+    {
+      "epoch": 0.12380952380952381,
+      "grad_norm": 0.9784255623817444,
+      "learning_rate": 3e-05,
+      "loss": 0.4589,
+      "step": 52
+    },
+    {
+      "epoch": 0.1261904761904762,
+      "grad_norm": 1.1923211812973022,
+      "learning_rate": 3e-05,
+      "loss": 0.5349,
+      "step": 53
+    },
+    {
+      "epoch": 0.12857142857142856,
+      "grad_norm": 1.6921881437301636,
+      "learning_rate": 3e-05,
+      "loss": 0.5921,
+      "step": 54
+    },
+    {
+      "epoch": 0.13095238095238096,
+      "grad_norm": 1.4049354791641235,
+      "learning_rate": 3e-05,
+      "loss": 0.3999,
+      "step": 55
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.6025511026382446,
+      "learning_rate": 3e-05,
+      "loss": 0.3708,
+      "step": 56
+    },
+    {
+      "epoch": 0.1357142857142857,
+      "grad_norm": 1.200055480003357,
+      "learning_rate": 3e-05,
+      "loss": 0.6888,
+      "step": 57
+    },
+    {
+      "epoch": 0.1380952380952381,
+      "grad_norm": 0.9409858584403992,
+      "learning_rate": 3e-05,
+      "loss": 0.4722,
+      "step": 58
+    },
+    {
+      "epoch": 0.14047619047619048,
+      "grad_norm": 1.47160804271698,
+      "learning_rate": 3e-05,
+      "loss": 1.0772,
+      "step": 59
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.935752809047699,
+      "learning_rate": 3e-05,
+      "loss": 0.3725,
+      "step": 60
+    },
+    {
+      "epoch": 0.14523809523809525,
+      "grad_norm": 0.8135111927986145,
+      "learning_rate": 3e-05,
+      "loss": 0.4312,
+      "step": 61
+    },
+    {
+      "epoch": 0.14761904761904762,
+      "grad_norm": 1.1500678062438965,
+      "learning_rate": 3e-05,
+      "loss": 0.4317,
+      "step": 62
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.0388532876968384,
+      "learning_rate": 3e-05,
+      "loss": 0.5262,
+      "step": 63
+    },
+    {
+      "epoch": 0.1523809523809524,
+      "grad_norm": 1.0478947162628174,
+      "learning_rate": 3e-05,
+      "loss": 0.5224,
+      "step": 64
+    },
+    {
+      "epoch": 0.15476190476190477,
+      "grad_norm": 0.6370094418525696,
+      "learning_rate": 3e-05,
+      "loss": 0.4117,
+      "step": 65
+    },
+    {
+      "epoch": 0.15714285714285714,
+      "grad_norm": 0.8117276430130005,
+      "learning_rate": 3e-05,
+      "loss": 0.4513,
+      "step": 66
+    },
+    {
+      "epoch": 0.1595238095238095,
+      "grad_norm": 1.4209480285644531,
+      "learning_rate": 3e-05,
+      "loss": 0.419,
+      "step": 67
+    },
+    {
+      "epoch": 0.1619047619047619,
+      "grad_norm": 1.3270151615142822,
+      "learning_rate": 3e-05,
+      "loss": 0.5064,
+      "step": 68
+    },
+    {
+      "epoch": 0.16428571428571428,
+      "grad_norm": 1.4599213600158691,
+      "learning_rate": 3e-05,
+      "loss": 0.5342,
+      "step": 69
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.7401596307754517,
+      "learning_rate": 3e-05,
+      "loss": 0.4609,
+      "step": 70
+    },
+    {
+      "epoch": 0.16904761904761906,
+      "grad_norm": 0.6574556827545166,
+      "learning_rate": 3e-05,
+      "loss": 0.3689,
+      "step": 71
+    },
+    {
+      "epoch": 0.17142857142857143,
+      "grad_norm": 1.6753238439559937,
+      "learning_rate": 3e-05,
+      "loss": 0.5226,
+      "step": 72
+    },
+    {
+      "epoch": 0.1738095238095238,
+      "grad_norm": 0.8294124603271484,
+      "learning_rate": 3e-05,
+      "loss": 0.4176,
+      "step": 73
+    },
+    {
+      "epoch": 0.1761904761904762,
+      "grad_norm": 0.9138219356536865,
+      "learning_rate": 3e-05,
+      "loss": 0.4123,
+      "step": 74
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 0.8199627995491028,
+      "learning_rate": 3e-05,
+      "loss": 0.4374,
+      "step": 75
+    },
+    {
+      "epoch": 0.18095238095238095,
+      "grad_norm": 0.7391550540924072,
+      "learning_rate": 3e-05,
+      "loss": 0.3825,
+      "step": 76
+    },
+    {
+      "epoch": 0.18333333333333332,
+      "grad_norm": 0.729434609413147,
+      "learning_rate": 3e-05,
+      "loss": 0.4824,
+      "step": 77
+    },
+    {
+      "epoch": 0.18571428571428572,
+      "grad_norm": 0.7266400456428528,
+      "learning_rate": 3e-05,
+      "loss": 0.3481,
+      "step": 78
+    },
+    {
+      "epoch": 0.1880952380952381,
+      "grad_norm": 0.8050060272216797,
+      "learning_rate": 3e-05,
+      "loss": 0.4694,
+      "step": 79
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 1.172167181968689,
+      "learning_rate": 3e-05,
+      "loss": 0.4291,
+      "step": 80
+    },
+    {
+      "epoch": 0.19285714285714287,
+      "grad_norm": 1.1613800525665283,
+      "learning_rate": 3e-05,
+      "loss": 0.483,
+      "step": 81
+    },
+    {
+      "epoch": 0.19523809523809524,
+      "grad_norm": 0.8675224184989929,
+      "learning_rate": 3e-05,
+      "loss": 0.4436,
+      "step": 82
+    },
+    {
+      "epoch": 0.1976190476190476,
+      "grad_norm": 0.899101734161377,
+      "learning_rate": 3e-05,
+      "loss": 0.4858,
+      "step": 83
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.030885934829712,
+      "learning_rate": 3e-05,
+      "loss": 0.5346,
+      "step": 84
+    },
+    {
+      "epoch": 0.20238095238095238,
+      "grad_norm": 0.9242229461669922,
+      "learning_rate": 3e-05,
+      "loss": 0.4349,
+      "step": 85
+    },
+    {
+      "epoch": 0.20476190476190476,
+      "grad_norm": 0.7717217803001404,
+      "learning_rate": 3e-05,
+      "loss": 0.3759,
+      "step": 86
+    },
+    {
+      "epoch": 0.20714285714285716,
+      "grad_norm": 1.2170741558074951,
+      "learning_rate": 3e-05,
+      "loss": 0.4937,
+      "step": 87
+    },
+    {
+      "epoch": 0.20952380952380953,
+      "grad_norm": 1.2934021949768066,
+      "learning_rate": 3e-05,
+      "loss": 0.4993,
+      "step": 88
+    },
+    {
+      "epoch": 0.2119047619047619,
+      "grad_norm": 1.3435097932815552,
+      "learning_rate": 3e-05,
+      "loss": 0.4603,
+      "step": 89
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.8454081416130066,
+      "learning_rate": 3e-05,
+      "loss": 0.5203,
+      "step": 90
+    },
+    {
+      "epoch": 0.21666666666666667,
+      "grad_norm": 0.8319071531295776,
+      "learning_rate": 3e-05,
+      "loss": 0.4997,
+      "step": 91
+    },
+    {
+      "epoch": 0.21904761904761905,
+      "grad_norm": 0.6560430526733398,
+      "learning_rate": 3e-05,
+      "loss": 0.4763,
+      "step": 92
+    },
+    {
+      "epoch": 0.22142857142857142,
+      "grad_norm": 2.126009941101074,
+      "learning_rate": 3e-05,
+      "loss": 0.7399,
+      "step": 93
+    },
+    {
+      "epoch": 0.22380952380952382,
+      "grad_norm": 1.1273273229599,
+      "learning_rate": 3e-05,
+      "loss": 0.5303,
+      "step": 94
+    },
+    {
+      "epoch": 0.2261904761904762,
+      "grad_norm": 0.9536347985267639,
+      "learning_rate": 3e-05,
+      "loss": 0.5147,
+      "step": 95
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.6337579488754272,
+      "learning_rate": 3e-05,
+      "loss": 0.4474,
+      "step": 96
+    },
+    {
+      "epoch": 0.23095238095238096,
+      "grad_norm": 0.6355674862861633,
+      "learning_rate": 3e-05,
+      "loss": 0.3958,
+      "step": 97
+    },
+    {
+      "epoch": 0.23333333333333334,
+      "grad_norm": 0.9631844758987427,
+      "learning_rate": 3e-05,
+      "loss": 0.4463,
+      "step": 98
+    },
+    {
+      "epoch": 0.2357142857142857,
+      "grad_norm": 0.7559183239936829,
+      "learning_rate": 3e-05,
+      "loss": 0.4952,
+      "step": 99
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.926929771900177,
+      "learning_rate": 3e-05,
+      "loss": 0.5318,
+      "step": 100
+    },
+    {
+      "epoch": 0.24047619047619048,
+      "grad_norm": 0.8441896438598633,
+      "learning_rate": 3e-05,
+      "loss": 0.4411,
+      "step": 101
+    },
+    {
+      "epoch": 0.24285714285714285,
+      "grad_norm": 1.1027876138687134,
+      "learning_rate": 3e-05,
+      "loss": 0.5618,
+      "step": 102
+    },
+    {
+      "epoch": 0.24523809523809523,
+      "grad_norm": 0.6018999814987183,
+      "learning_rate": 3e-05,
+      "loss": 0.4046,
+      "step": 103
+    },
+    {
+      "epoch": 0.24761904761904763,
+      "grad_norm": 0.8065565228462219,
+      "learning_rate": 3e-05,
+      "loss": 0.4195,
+      "step": 104
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.6117183566093445,
+      "learning_rate": 3e-05,
+      "loss": 0.3556,
+      "step": 105
+    },
+    {
+      "epoch": 0.2523809523809524,
+      "grad_norm": 1.0436320304870605,
+      "learning_rate": 3e-05,
+      "loss": 0.4699,
+      "step": 106
+    },
+    {
+      "epoch": 0.25476190476190474,
+      "grad_norm": 1.1943013668060303,
+      "learning_rate": 3e-05,
+      "loss": 0.5636,
+      "step": 107
+    },
+    {
+      "epoch": 0.2571428571428571,
+      "grad_norm": 0.8576936721801758,
+      "learning_rate": 3e-05,
+      "loss": 0.4178,
+      "step": 108
+    },
+    {
+      "epoch": 0.25952380952380955,
+      "grad_norm": 0.7651050686836243,
+      "learning_rate": 3e-05,
+      "loss": 0.436,
+      "step": 109
+    },
+    {
+      "epoch": 0.2619047619047619,
+      "grad_norm": 0.787661612033844,
+      "learning_rate": 3e-05,
+      "loss": 0.4378,
+      "step": 110
+    },
+    {
+      "epoch": 0.2642857142857143,
+      "grad_norm": 0.961089551448822,
+      "learning_rate": 3e-05,
+      "loss": 0.4979,
+      "step": 111
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.7426000833511353,
+      "learning_rate": 3e-05,
+      "loss": 0.4908,
+      "step": 112
+    },
+    {
+      "epoch": 0.26904761904761904,
+      "grad_norm": 1.0738164186477661,
+      "learning_rate": 3e-05,
+      "loss": 0.5052,
+      "step": 113
+    },
+    {
+      "epoch": 0.2714285714285714,
+      "grad_norm": 1.3592005968093872,
+      "learning_rate": 3e-05,
+      "loss": 0.5155,
+      "step": 114
+    },
+    {
+      "epoch": 0.27380952380952384,
+      "grad_norm": 0.776147723197937,
+      "learning_rate": 3e-05,
+      "loss": 0.4199,
+      "step": 115
+    },
+    {
+      "epoch": 0.2761904761904762,
+      "grad_norm": 1.184778094291687,
+      "learning_rate": 3e-05,
+      "loss": 0.4471,
+      "step": 116
+    },
+    {
+      "epoch": 0.2785714285714286,
+      "grad_norm": 0.9415385127067566,
+      "learning_rate": 3e-05,
+      "loss": 0.4518,
+      "step": 117
+    },
+    {
+      "epoch": 0.28095238095238095,
+      "grad_norm": 0.9082314372062683,
+      "learning_rate": 3e-05,
+      "loss": 0.4986,
+      "step": 118
+    },
+    {
+      "epoch": 0.2833333333333333,
+      "grad_norm": 1.6528809070587158,
+      "learning_rate": 3e-05,
+      "loss": 0.6329,
+      "step": 119
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.6157988905906677,
+      "learning_rate": 3e-05,
+      "loss": 0.346,
+      "step": 120
+    },
+    {
+      "epoch": 0.28809523809523807,
+      "grad_norm": 1.335919737815857,
+      "learning_rate": 3e-05,
+      "loss": 0.5417,
+      "step": 121
+    },
+    {
+      "epoch": 0.2904761904761905,
+      "grad_norm": 1.7414772510528564,
+      "learning_rate": 3e-05,
+      "loss": 0.513,
+      "step": 122
+    },
+    {
+      "epoch": 0.29285714285714287,
+      "grad_norm": 1.0106985569000244,
+      "learning_rate": 3e-05,
+      "loss": 0.5358,
+      "step": 123
+    },
+    {
+      "epoch": 0.29523809523809524,
+      "grad_norm": 0.8379469513893127,
+      "learning_rate": 3e-05,
+      "loss": 0.4548,
+      "step": 124
+    },
+    {
+      "epoch": 0.2976190476190476,
+      "grad_norm": 0.8793790340423584,
+      "learning_rate": 3e-05,
+      "loss": 0.5191,
+      "step": 125
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.7612943053245544,
+      "learning_rate": 3e-05,
+      "loss": 0.4913,
+      "step": 126
+    },
+    {
+      "epoch": 0.30238095238095236,
+      "grad_norm": 1.0233980417251587,
+      "learning_rate": 3e-05,
+      "loss": 0.5259,
+      "step": 127
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.9049614071846008,
+      "learning_rate": 3e-05,
+      "loss": 0.4164,
+      "step": 128
+    },
+    {
+      "epoch": 0.30714285714285716,
+      "grad_norm": 1.390436053276062,
+      "learning_rate": 3e-05,
+      "loss": 0.4505,
+      "step": 129
+    },
+    {
+      "epoch": 0.30952380952380953,
+      "grad_norm": 0.705032229423523,
+      "learning_rate": 3e-05,
+      "loss": 0.4763,
+      "step": 130
+    },
+    {
+      "epoch": 0.3119047619047619,
+      "grad_norm": 1.1658718585968018,
+      "learning_rate": 3e-05,
+      "loss": 0.4132,
+      "step": 131
+    },
+    {
+      "epoch": 0.3142857142857143,
+      "grad_norm": 1.0997470617294312,
+      "learning_rate": 3e-05,
+      "loss": 0.4877,
+      "step": 132
+    },
+    {
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.7365838885307312,
+      "learning_rate": 3e-05,
+      "loss": 0.3902,
+      "step": 133
+    },
+    {
+      "epoch": 0.319047619047619,
+      "grad_norm": 1.0315278768539429,
+      "learning_rate": 3e-05,
+      "loss": 0.5093,
+      "step": 134
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.8308622241020203,
+      "learning_rate": 3e-05,
+      "loss": 0.4309,
+      "step": 135
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "grad_norm": 0.8301631808280945,
+      "learning_rate": 3e-05,
+      "loss": 0.5057,
+      "step": 136
+    },
+    {
+      "epoch": 0.3261904761904762,
+      "grad_norm": 0.6643893122673035,
+      "learning_rate": 3e-05,
+      "loss": 0.44,
+      "step": 137
+    },
+    {
+      "epoch": 0.32857142857142857,
+      "grad_norm": 0.9323320984840393,
+      "learning_rate": 3e-05,
+      "loss": 0.4377,
+      "step": 138
+    },
+    {
+      "epoch": 0.33095238095238094,
+      "grad_norm": 0.8339701294898987,
+      "learning_rate": 3e-05,
+      "loss": 0.4982,
+      "step": 139
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.8500747680664062,
+      "learning_rate": 3e-05,
+      "loss": 0.4303,
+      "step": 140
+    },
+    {
+      "epoch": 0.3357142857142857,
+      "grad_norm": 0.697967529296875,
+      "learning_rate": 3e-05,
+      "loss": 0.447,
+      "step": 141
+    },
+    {
+      "epoch": 0.3380952380952381,
+      "grad_norm": 1.1016360521316528,
+      "learning_rate": 3e-05,
+      "loss": 0.4827,
+      "step": 142
+    },
+    {
+      "epoch": 0.3404761904761905,
+      "grad_norm": 0.9719865918159485,
+      "learning_rate": 3e-05,
+      "loss": 0.4719,
+      "step": 143
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.8482648134231567,
+      "learning_rate": 3e-05,
+      "loss": 0.4171,
+      "step": 144
+    },
+    {
+      "epoch": 0.34523809523809523,
+      "grad_norm": 1.2719123363494873,
+      "learning_rate": 3e-05,
+      "loss": 0.4444,
+      "step": 145
+    },
+    {
+      "epoch": 0.3476190476190476,
+      "grad_norm": 1.1623255014419556,
+      "learning_rate": 3e-05,
+      "loss": 0.4033,
+      "step": 146
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.7803097367286682,
+      "learning_rate": 3e-05,
+      "loss": 0.3299,
+      "step": 147
+    },
+    {
+      "epoch": 0.3523809523809524,
+      "grad_norm": 0.6812254786491394,
+      "learning_rate": 3e-05,
+      "loss": 0.3652,
+      "step": 148
+    },
+    {
+      "epoch": 0.3547619047619048,
+      "grad_norm": 1.0708630084991455,
+      "learning_rate": 3e-05,
+      "loss": 0.4121,
+      "step": 149
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 1.3431651592254639,
+      "learning_rate": 3e-05,
+      "loss": 0.4235,
+      "step": 150
+    },
+    {
+      "epoch": 0.3595238095238095,
+      "grad_norm": 0.779104471206665,
+      "learning_rate": 3e-05,
+      "loss": 0.3404,
+      "step": 151
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "grad_norm": 0.6354933381080627,
+      "learning_rate": 3e-05,
+      "loss": 0.4572,
+      "step": 152
+    },
+    {
+      "epoch": 0.36428571428571427,
+      "grad_norm": 0.6587569117546082,
+      "learning_rate": 3e-05,
+      "loss": 0.3692,
+      "step": 153
+    },
+    {
+      "epoch": 0.36666666666666664,
+      "grad_norm": 1.0237056016921997,
+      "learning_rate": 3e-05,
+      "loss": 0.4356,
+      "step": 154
+    },
+    {
+      "epoch": 0.36904761904761907,
+      "grad_norm": 0.9965682625770569,
+      "learning_rate": 3e-05,
+      "loss": 0.4609,
+      "step": 155
+    },
+    {
+      "epoch": 0.37142857142857144,
+      "grad_norm": 0.9826563000679016,
+      "learning_rate": 3e-05,
+      "loss": 0.4502,
+      "step": 156
+    },
+    {
+      "epoch": 0.3738095238095238,
+      "grad_norm": 1.2390687465667725,
+      "learning_rate": 3e-05,
+      "loss": 0.4734,
+      "step": 157
+    },
+    {
+      "epoch": 0.3761904761904762,
+      "grad_norm": 0.7621622681617737,
+      "learning_rate": 3e-05,
+      "loss": 0.4267,
+      "step": 158
+    },
+    {
+      "epoch": 0.37857142857142856,
+      "grad_norm": 1.300564169883728,
+      "learning_rate": 3e-05,
+      "loss": 0.4018,
+      "step": 159
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 1.2761445045471191,
+      "learning_rate": 3e-05,
+      "loss": 0.5127,
+      "step": 160
+    },
+    {
+      "epoch": 0.38333333333333336,
+      "grad_norm": 0.933185875415802,
+      "learning_rate": 3e-05,
+      "loss": 0.5515,
+      "step": 161
+    },
+    {
+      "epoch": 0.38571428571428573,
+      "grad_norm": 1.3930639028549194,
+      "learning_rate": 3e-05,
+      "loss": 0.5837,
+      "step": 162
+    },
+    {
+      "epoch": 0.3880952380952381,
+      "grad_norm": 1.7598650455474854,
+      "learning_rate": 3e-05,
+      "loss": 0.6716,
+      "step": 163
+    },
+    {
+      "epoch": 0.3904761904761905,
+      "grad_norm": 0.9068734645843506,
+      "learning_rate": 3e-05,
+      "loss": 0.4984,
+      "step": 164
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 1.5030951499938965,
+      "learning_rate": 3e-05,
+      "loss": 0.4181,
+      "step": 165
+    },
+    {
+      "epoch": 0.3952380952380952,
+      "grad_norm": 0.6494777798652649,
+      "learning_rate": 3e-05,
+      "loss": 0.4,
+      "step": 166
+    },
+    {
+      "epoch": 0.3976190476190476,
+      "grad_norm": 0.7952489256858826,
+      "learning_rate": 3e-05,
+      "loss": 0.4569,
+      "step": 167
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.175072193145752,
+      "learning_rate": 3e-05,
+      "loss": 0.4385,
+      "step": 168
+    },
+    {
+      "epoch": 0.4023809523809524,
+      "grad_norm": 0.8904735445976257,
+      "learning_rate": 3e-05,
+      "loss": 0.4107,
+      "step": 169
+    },
+    {
+      "epoch": 0.40476190476190477,
+      "grad_norm": 1.0196988582611084,
+      "learning_rate": 3e-05,
+      "loss": 0.3662,
+      "step": 170
+    },
+    {
+      "epoch": 0.40714285714285714,
+      "grad_norm": 1.025765299797058,
+      "learning_rate": 3e-05,
+      "loss": 0.4981,
+      "step": 171
+    },
+    {
+      "epoch": 0.4095238095238095,
+      "grad_norm": 0.8151318430900574,
+      "learning_rate": 3e-05,
+      "loss": 0.5131,
+      "step": 172
+    },
+    {
+      "epoch": 0.4119047619047619,
+      "grad_norm": 0.8304903507232666,
+      "learning_rate": 3e-05,
+      "loss": 0.4652,
+      "step": 173
+    },
+    {
+      "epoch": 0.4142857142857143,
+      "grad_norm": 0.8581998944282532,
+      "learning_rate": 3e-05,
+      "loss": 0.492,
+      "step": 174
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.7963671088218689,
+      "learning_rate": 3e-05,
+      "loss": 0.4149,
+      "step": 175
+    },
+    {
+      "epoch": 0.41904761904761906,
+      "grad_norm": 0.814155638217926,
+      "learning_rate": 3e-05,
+      "loss": 0.5259,
+      "step": 176
+    },
+    {
+      "epoch": 0.42142857142857143,
+      "grad_norm": 0.819995105266571,
+      "learning_rate": 3e-05,
+      "loss": 0.4502,
+      "step": 177
+    },
+    {
+      "epoch": 0.4238095238095238,
+      "grad_norm": 0.6711002588272095,
+      "learning_rate": 3e-05,
+      "loss": 0.4163,
+      "step": 178
+    },
+    {
+      "epoch": 0.4261904761904762,
+      "grad_norm": 0.8345437049865723,
+      "learning_rate": 3e-05,
+      "loss": 0.4161,
+      "step": 179
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.5476064682006836,
+      "learning_rate": 3e-05,
+      "loss": 0.38,
+      "step": 180
+    },
+    {
+      "epoch": 0.430952380952381,
+      "grad_norm": 0.836280882358551,
+      "learning_rate": 3e-05,
+      "loss": 0.4163,
+      "step": 181
+    },
+    {
+      "epoch": 0.43333333333333335,
+      "grad_norm": 0.8886452317237854,
+      "learning_rate": 3e-05,
+      "loss": 0.4447,
+      "step": 182
+    },
+    {
+      "epoch": 0.4357142857142857,
+      "grad_norm": 0.89081209897995,
+      "learning_rate": 3e-05,
+      "loss": 0.3914,
+      "step": 183
+    },
+    {
+      "epoch": 0.4380952380952381,
+      "grad_norm": 2.051706075668335,
+      "learning_rate": 3e-05,
+      "loss": 0.5365,
+      "step": 184
+    },
+    {
+      "epoch": 0.44047619047619047,
+      "grad_norm": 0.8237314224243164,
+      "learning_rate": 3e-05,
+      "loss": 0.4411,
+      "step": 185
+    },
+    {
+      "epoch": 0.44285714285714284,
+      "grad_norm": 0.8707730770111084,
+      "learning_rate": 3e-05,
+      "loss": 0.505,
+      "step": 186
+    },
+    {
+      "epoch": 0.4452380952380952,
+      "grad_norm": 0.922207772731781,
+      "learning_rate": 3e-05,
+      "loss": 0.4698,
+      "step": 187
+    },
+    {
+      "epoch": 0.44761904761904764,
+      "grad_norm": 1.2687690258026123,
+      "learning_rate": 3e-05,
+      "loss": 0.5653,
+      "step": 188
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.8072938919067383,
+      "learning_rate": 3e-05,
+      "loss": 0.3777,
+      "step": 189
+    },
+    {
+      "epoch": 0.4523809523809524,
+      "grad_norm": 0.8983867764472961,
+      "learning_rate": 3e-05,
+      "loss": 0.4334,
+      "step": 190
+    },
+    {
+      "epoch": 0.45476190476190476,
+      "grad_norm": 0.9799190163612366,
+      "learning_rate": 3e-05,
+      "loss": 0.567,
+      "step": 191
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.8757649660110474,
+      "learning_rate": 3e-05,
+      "loss": 0.4425,
+      "step": 192
+    },
+    {
+      "epoch": 0.4595238095238095,
+      "grad_norm": 1.6467727422714233,
+      "learning_rate": 3e-05,
+      "loss": 0.484,
+      "step": 193
+    },
+    {
+      "epoch": 0.46190476190476193,
+      "grad_norm": 0.6561694741249084,
+      "learning_rate": 3e-05,
+      "loss": 0.4947,
+      "step": 194
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.8178306818008423,
+      "learning_rate": 3e-05,
+      "loss": 0.4398,
+      "step": 195
+    },
+    {
+      "epoch": 0.4666666666666667,
+      "grad_norm": 0.9850760102272034,
+      "learning_rate": 3e-05,
+      "loss": 0.4436,
+      "step": 196
+    },
+    {
+      "epoch": 0.46904761904761905,
+      "grad_norm": 0.8389570713043213,
+      "learning_rate": 3e-05,
+      "loss": 0.4303,
+      "step": 197
+    },
+    {
+      "epoch": 0.4714285714285714,
+      "grad_norm": 1.0063328742980957,
+      "learning_rate": 3e-05,
+      "loss": 0.4574,
+      "step": 198
+    },
+    {
+      "epoch": 0.4738095238095238,
+      "grad_norm": 0.7931296229362488,
+      "learning_rate": 3e-05,
+      "loss": 0.4096,
+      "step": 199
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.4383584260940552,
+      "learning_rate": 3e-05,
+      "loss": 0.5578,
+      "step": 200
+    },
+    {
+      "epoch": 0.4785714285714286,
+      "grad_norm": 1.2136746644973755,
+      "learning_rate": 3e-05,
+      "loss": 0.505,
+      "step": 201
+    },
+    {
+      "epoch": 0.48095238095238096,
+      "grad_norm": 0.8902712464332581,
+      "learning_rate": 3e-05,
+      "loss": 0.385,
+      "step": 202
+    },
+    {
+      "epoch": 0.48333333333333334,
+      "grad_norm": 0.6584445238113403,
+      "learning_rate": 3e-05,
+      "loss": 0.4603,
+      "step": 203
+    },
+    {
+      "epoch": 0.4857142857142857,
+      "grad_norm": 1.4439114332199097,
+      "learning_rate": 3e-05,
+      "loss": 0.4835,
+      "step": 204
+    },
+    {
+      "epoch": 0.4880952380952381,
+      "grad_norm": 1.160464882850647,
+      "learning_rate": 3e-05,
+      "loss": 0.4695,
+      "step": 205
+    },
+    {
+      "epoch": 0.49047619047619045,
+      "grad_norm": 1.3329150676727295,
+      "learning_rate": 3e-05,
+      "loss": 0.493,
+      "step": 206
+    },
+    {
+      "epoch": 0.4928571428571429,
+      "grad_norm": 0.7865476012229919,
+      "learning_rate": 3e-05,
+      "loss": 0.3839,
+      "step": 207
+    },
+    {
+      "epoch": 0.49523809523809526,
+      "grad_norm": 0.6394692063331604,
+      "learning_rate": 3e-05,
+      "loss": 0.4198,
+      "step": 208
+    },
+    {
+      "epoch": 0.4976190476190476,
+      "grad_norm": 0.7849683165550232,
+      "learning_rate": 3e-05,
+      "loss": 0.4416,
+      "step": 209
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8394088745117188,
+      "learning_rate": 3e-05,
+      "loss": 0.4106,
+      "step": 210
+    },
+    {
+      "epoch": 0.5023809523809524,
+      "grad_norm": 1.2182062864303589,
+      "learning_rate": 3e-05,
+      "loss": 0.4312,
+      "step": 211
+    },
+    {
+      "epoch": 0.5047619047619047,
+      "grad_norm": 1.8101513385772705,
+      "learning_rate": 3e-05,
+      "loss": 0.4463,
+      "step": 212
+    },
+    {
+      "epoch": 0.5071428571428571,
+      "grad_norm": 1.2146952152252197,
+      "learning_rate": 3e-05,
+      "loss": 0.4194,
+      "step": 213
+    },
+    {
+      "epoch": 0.5095238095238095,
+      "grad_norm": 1.2878483533859253,
+      "learning_rate": 3e-05,
+      "loss": 0.4494,
+      "step": 214
+    },
+    {
+      "epoch": 0.5119047619047619,
+      "grad_norm": 0.6163401007652283,
+      "learning_rate": 3e-05,
+      "loss": 0.3637,
+      "step": 215
+    },
+    {
+      "epoch": 0.5142857142857142,
+      "grad_norm": 0.8795377016067505,
+      "learning_rate": 3e-05,
+      "loss": 0.4442,
+      "step": 216
+    },
+    {
+      "epoch": 0.5166666666666667,
+      "grad_norm": 1.1143704652786255,
+      "learning_rate": 3e-05,
+      "loss": 0.5383,
+      "step": 217
+    },
+    {
+      "epoch": 0.5190476190476191,
+      "grad_norm": 0.9760447144508362,
+      "learning_rate": 3e-05,
+      "loss": 0.5384,
+      "step": 218
+    },
+    {
+      "epoch": 0.5214285714285715,
+      "grad_norm": 0.9762544631958008,
+      "learning_rate": 3e-05,
+      "loss": 0.4292,
+      "step": 219
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 1.2184864282608032,
+      "learning_rate": 3e-05,
+      "loss": 0.6392,
+      "step": 220
+    },
+    {
+      "epoch": 0.5261904761904762,
+      "grad_norm": 0.9517297148704529,
+      "learning_rate": 3e-05,
+      "loss": 0.4863,
+      "step": 221
+    },
+    {
+      "epoch": 0.5285714285714286,
+      "grad_norm": 0.7961365580558777,
+      "learning_rate": 3e-05,
+      "loss": 0.3822,
+      "step": 222
+    },
+    {
+      "epoch": 0.530952380952381,
+      "grad_norm": 0.8735774755477905,
+      "learning_rate": 3e-05,
+      "loss": 0.5283,
+      "step": 223
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.6506310105323792,
+      "learning_rate": 3e-05,
+      "loss": 0.3831,
+      "step": 224
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 1.1028398275375366,
+      "learning_rate": 3e-05,
+      "loss": 0.5849,
+      "step": 225
+    },
+    {
+      "epoch": 0.5380952380952381,
+      "grad_norm": 0.646365225315094,
+      "learning_rate": 3e-05,
+      "loss": 0.4134,
+      "step": 226
+    },
+    {
+      "epoch": 0.5404761904761904,
+      "grad_norm": 0.7208945751190186,
+      "learning_rate": 3e-05,
+      "loss": 0.4387,
+      "step": 227
+    },
+    {
+      "epoch": 0.5428571428571428,
+      "grad_norm": 1.1932159662246704,
+      "learning_rate": 3e-05,
+      "loss": 0.4882,
+      "step": 228
+    },
+    {
+      "epoch": 0.5452380952380952,
+      "grad_norm": 0.5648031234741211,
+      "learning_rate": 3e-05,
+      "loss": 0.3583,
+      "step": 229
+    },
+    {
+      "epoch": 0.5476190476190477,
+      "grad_norm": 0.8216423988342285,
+      "learning_rate": 3e-05,
+      "loss": 0.4276,
+      "step": 230
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.6750469207763672,
+      "learning_rate": 3e-05,
+      "loss": 0.429,
+      "step": 231
+    },
+    {
+      "epoch": 0.5523809523809524,
+      "grad_norm": 0.6576554179191589,
+      "learning_rate": 3e-05,
+      "loss": 0.4449,
+      "step": 232
+    },
+    {
+      "epoch": 0.5547619047619048,
+      "grad_norm": 1.514758586883545,
+      "learning_rate": 3e-05,
+      "loss": 0.4153,
+      "step": 233
+    },
+    {
+      "epoch": 0.5571428571428572,
+      "grad_norm": 1.1545631885528564,
+      "learning_rate": 3e-05,
+      "loss": 0.4554,
+      "step": 234
+    },
+    {
+      "epoch": 0.5595238095238095,
+      "grad_norm": 0.7327958941459656,
+      "learning_rate": 3e-05,
+      "loss": 0.3641,
+      "step": 235
+    },
+    {
+      "epoch": 0.5619047619047619,
+      "grad_norm": 1.4862022399902344,
+      "learning_rate": 3e-05,
+      "loss": 0.5283,
+      "step": 236
+    },
+    {
+      "epoch": 0.5642857142857143,
+      "grad_norm": 1.2565538883209229,
+      "learning_rate": 3e-05,
+      "loss": 0.4605,
+      "step": 237
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.5355277061462402,
+      "learning_rate": 3e-05,
+      "loss": 0.3679,
+      "step": 238
+    },
+    {
+      "epoch": 0.569047619047619,
+      "grad_norm": 0.8581258058547974,
+      "learning_rate": 3e-05,
+      "loss": 0.462,
+      "step": 239
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.9366555213928223,
+      "learning_rate": 3e-05,
+      "loss": 0.4788,
+      "step": 240
+    },
+    {
+      "epoch": 0.5738095238095238,
+      "grad_norm": 0.927740216255188,
+      "learning_rate": 3e-05,
+      "loss": 0.4406,
+      "step": 241
+    },
+    {
+      "epoch": 0.5761904761904761,
+      "grad_norm": 0.8326394557952881,
+      "learning_rate": 3e-05,
+      "loss": 0.3595,
+      "step": 242
+    },
+    {
+      "epoch": 0.5785714285714286,
+      "grad_norm": 1.214613676071167,
+      "learning_rate": 3e-05,
+      "loss": 0.5004,
+      "step": 243
+    },
+    {
+      "epoch": 0.580952380952381,
+      "grad_norm": 0.9543561935424805,
+      "learning_rate": 3e-05,
+      "loss": 0.4941,
+      "step": 244
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 1.1488438844680786,
+      "learning_rate": 3e-05,
+      "loss": 0.5066,
+      "step": 245
+    },
+    {
+      "epoch": 0.5857142857142857,
+      "grad_norm": 0.9091154932975769,
+      "learning_rate": 3e-05,
+      "loss": 0.4834,
+      "step": 246
+    },
+    {
+      "epoch": 0.5880952380952381,
+      "grad_norm": 0.7307273149490356,
+      "learning_rate": 3e-05,
+      "loss": 0.5543,
+      "step": 247
+    },
+    {
+      "epoch": 0.5904761904761905,
+      "grad_norm": 1.0417815446853638,
+      "learning_rate": 3e-05,
+      "loss": 0.4615,
+      "step": 248
+    },
+    {
+      "epoch": 0.5928571428571429,
+      "grad_norm": 0.7121735215187073,
+      "learning_rate": 3e-05,
+      "loss": 0.374,
+      "step": 249
+    },
+    {
+      "epoch": 0.5952380952380952,
+      "grad_norm": 1.0804853439331055,
+      "learning_rate": 3e-05,
+      "loss": 0.3975,
+      "step": 250
+    },
+    {
+      "epoch": 0.5976190476190476,
+      "grad_norm": 0.7743527293205261,
+      "learning_rate": 3e-05,
+      "loss": 0.4129,
+      "step": 251
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.7785153985023499,
+      "learning_rate": 3e-05,
+      "loss": 0.4027,
+      "step": 252
+    },
+    {
+      "epoch": 0.6023809523809524,
+      "grad_norm": 1.36514413356781,
+      "learning_rate": 3e-05,
+      "loss": 0.5362,
+      "step": 253
+    },
+    {
+      "epoch": 0.6047619047619047,
+      "grad_norm": 0.8658007979393005,
+      "learning_rate": 3e-05,
+      "loss": 0.4488,
+      "step": 254
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 0.807852566242218,
+      "learning_rate": 3e-05,
+      "loss": 0.4065,
+      "step": 255
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "grad_norm": 1.2672406435012817,
+      "learning_rate": 3e-05,
+      "loss": 0.4587,
+      "step": 256
+    },
+    {
+      "epoch": 0.611904761904762,
+      "grad_norm": 1.0440469980239868,
+      "learning_rate": 3e-05,
+      "loss": 0.4815,
+      "step": 257
+    },
+    {
+      "epoch": 0.6142857142857143,
+      "grad_norm": 0.9778774380683899,
+      "learning_rate": 3e-05,
+      "loss": 0.385,
+      "step": 258
+    },
+    {
+      "epoch": 0.6166666666666667,
+      "grad_norm": 0.8957841396331787,
+      "learning_rate": 3e-05,
+      "loss": 0.4405,
+      "step": 259
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.9312807321548462,
+      "learning_rate": 3e-05,
+      "loss": 0.4902,
+      "step": 260
+    },
+    {
+      "epoch": 0.6214285714285714,
+      "grad_norm": 0.6373504400253296,
+      "learning_rate": 3e-05,
+      "loss": 0.436,
+      "step": 261
+    },
+    {
+      "epoch": 0.6238095238095238,
+      "grad_norm": 0.8105682134628296,
+      "learning_rate": 3e-05,
+      "loss": 0.4,
+      "step": 262
+    },
+    {
+      "epoch": 0.6261904761904762,
+      "grad_norm": 1.1135553121566772,
+      "learning_rate": 3e-05,
+      "loss": 0.4624,
+      "step": 263
+    },
+    {
+      "epoch": 0.6285714285714286,
+      "grad_norm": 0.8639890551567078,
+      "learning_rate": 3e-05,
+      "loss": 0.3969,
+      "step": 264
+    },
+    {
+      "epoch": 0.6309523809523809,
+      "grad_norm": 1.8037925958633423,
+      "learning_rate": 3e-05,
+      "loss": 0.5693,
+      "step": 265
+    },
+    {
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.6781933307647705,
+      "learning_rate": 3e-05,
+      "loss": 0.4913,
+      "step": 266
+    },
+    {
+      "epoch": 0.6357142857142857,
+      "grad_norm": 0.8383111953735352,
+      "learning_rate": 3e-05,
+      "loss": 0.3797,
+      "step": 267
+    },
+    {
+      "epoch": 0.638095238095238,
+      "grad_norm": 0.7477337718009949,
+      "learning_rate": 3e-05,
+      "loss": 0.4539,
+      "step": 268
+    },
+    {
+      "epoch": 0.6404761904761904,
+      "grad_norm": 0.7518517971038818,
+      "learning_rate": 3e-05,
+      "loss": 0.445,
+      "step": 269
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.9350783824920654,
+      "learning_rate": 3e-05,
+      "loss": 0.4111,
+      "step": 270
+    },
+    {
+      "epoch": 0.6452380952380953,
+      "grad_norm": 0.7175120115280151,
+      "learning_rate": 3e-05,
+      "loss": 0.3893,
+      "step": 271
+    },
+    {
+      "epoch": 0.6476190476190476,
+      "grad_norm": 0.9294947981834412,
+      "learning_rate": 3e-05,
+      "loss": 0.4438,
+      "step": 272
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.9406439065933228,
+      "learning_rate": 3e-05,
+      "loss": 0.4953,
+      "step": 273
+    },
+    {
+      "epoch": 0.6523809523809524,
+      "grad_norm": 0.9267202019691467,
+      "learning_rate": 3e-05,
+      "loss": 0.4601,
+      "step": 274
+    },
+    {
+      "epoch": 0.6547619047619048,
+      "grad_norm": 0.9095003604888916,
+      "learning_rate": 3e-05,
+      "loss": 0.5238,
+      "step": 275
+    },
+    {
+      "epoch": 0.6571428571428571,
+      "grad_norm": 1.1330962181091309,
+      "learning_rate": 3e-05,
+      "loss": 0.4776,
+      "step": 276
+    },
+    {
+      "epoch": 0.6595238095238095,
+      "grad_norm": 0.8976531028747559,
+      "learning_rate": 3e-05,
+      "loss": 0.4945,
+      "step": 277
+    },
+    {
+      "epoch": 0.6619047619047619,
+      "grad_norm": 1.398485541343689,
+      "learning_rate": 3e-05,
+      "loss": 0.4164,
+      "step": 278
+    },
+    {
+      "epoch": 0.6642857142857143,
+      "grad_norm": 0.8878613710403442,
+      "learning_rate": 3e-05,
+      "loss": 0.4601,
+      "step": 279
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.6003170609474182,
+      "learning_rate": 3e-05,
+      "loss": 0.3919,
+      "step": 280
+    },
+    {
+      "epoch": 0.669047619047619,
+      "grad_norm": 0.6366980075836182,
+      "learning_rate": 3e-05,
+      "loss": 0.4499,
+      "step": 281
+    },
+    {
+      "epoch": 0.6714285714285714,
+      "grad_norm": 1.0374082326889038,
+      "learning_rate": 3e-05,
+      "loss": 0.4571,
+      "step": 282
+    },
+    {
+      "epoch": 0.6738095238095239,
+      "grad_norm": 1.0846024751663208,
+      "learning_rate": 3e-05,
+      "loss": 0.4331,
+      "step": 283
+    },
+    {
+      "epoch": 0.6761904761904762,
+      "grad_norm": 1.9345874786376953,
+      "learning_rate": 3e-05,
+      "loss": 0.4802,
+      "step": 284
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.9415948390960693,
+      "learning_rate": 3e-05,
+      "loss": 0.4953,
+      "step": 285
+    },
+    {
+      "epoch": 0.680952380952381,
+      "grad_norm": 0.7957614660263062,
+      "learning_rate": 3e-05,
+      "loss": 0.4365,
+      "step": 286
+    },
+    {
+      "epoch": 0.6833333333333333,
+      "grad_norm": 0.9216206669807434,
+      "learning_rate": 3e-05,
+      "loss": 0.4168,
+      "step": 287
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 1.051074743270874,
+      "learning_rate": 3e-05,
+      "loss": 0.4889,
+      "step": 288
+    },
+    {
+      "epoch": 0.6880952380952381,
+      "grad_norm": 0.7795323729515076,
+      "learning_rate": 3e-05,
+      "loss": 0.3523,
+      "step": 289
+    },
+    {
+      "epoch": 0.6904761904761905,
+      "grad_norm": 0.8779550790786743,
+      "learning_rate": 3e-05,
+      "loss": 0.3868,
+      "step": 290
+    },
+    {
+      "epoch": 0.6928571428571428,
+      "grad_norm": 0.8232953548431396,
+      "learning_rate": 3e-05,
+      "loss": 0.3555,
+      "step": 291
+    },
+    {
+      "epoch": 0.6952380952380952,
+      "grad_norm": 1.3102864027023315,
+      "learning_rate": 3e-05,
+      "loss": 0.5208,
+      "step": 292
+    },
+    {
+      "epoch": 0.6976190476190476,
+      "grad_norm": 0.6595520973205566,
+      "learning_rate": 3e-05,
+      "loss": 0.3986,
+      "step": 293
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9423562288284302,
+      "learning_rate": 3e-05,
+      "loss": 0.4447,
+      "step": 294
+    },
+    {
+      "epoch": 0.7023809523809523,
+      "grad_norm": 0.7358708381652832,
+      "learning_rate": 3e-05,
+      "loss": 0.4395,
+      "step": 295
+    },
+    {
+      "epoch": 0.7047619047619048,
+      "grad_norm": 0.8931717276573181,
+      "learning_rate": 3e-05,
+      "loss": 0.4249,
+      "step": 296
+    },
+    {
+      "epoch": 0.7071428571428572,
+      "grad_norm": 0.8583389520645142,
+      "learning_rate": 3e-05,
+      "loss": 0.4519,
+      "step": 297
+    },
+    {
+      "epoch": 0.7095238095238096,
+      "grad_norm": 0.824382483959198,
+      "learning_rate": 3e-05,
+      "loss": 0.4011,
+      "step": 298
+    },
+    {
+      "epoch": 0.7119047619047619,
+      "grad_norm": 0.7034823298454285,
+      "learning_rate": 3e-05,
+      "loss": 0.4816,
+      "step": 299
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.692171573638916,
+      "learning_rate": 3e-05,
+      "loss": 0.4142,
+      "step": 300
+    },
+    {
+      "epoch": 0.7166666666666667,
+      "grad_norm": 0.9514793753623962,
+      "learning_rate": 3e-05,
+      "loss": 0.4276,
+      "step": 301
+    },
+    {
+      "epoch": 0.719047619047619,
+      "grad_norm": 0.7801012396812439,
+      "learning_rate": 3e-05,
+      "loss": 0.4587,
+      "step": 302
+    },
+    {
+      "epoch": 0.7214285714285714,
+      "grad_norm": 0.7651001214981079,
+      "learning_rate": 3e-05,
+      "loss": 0.3756,
+      "step": 303
+    },
+    {
+      "epoch": 0.7238095238095238,
+      "grad_norm": 0.7955180406570435,
+      "learning_rate": 3e-05,
+      "loss": 0.4012,
+      "step": 304
+    },
+    {
+      "epoch": 0.7261904761904762,
+      "grad_norm": 1.8750542402267456,
+      "learning_rate": 3e-05,
+      "loss": 0.5779,
+      "step": 305
+    },
+    {
+      "epoch": 0.7285714285714285,
+      "grad_norm": 1.1346620321273804,
+      "learning_rate": 3e-05,
+      "loss": 0.4389,
+      "step": 306
+    },
+    {
+      "epoch": 0.7309523809523809,
+      "grad_norm": 0.8639288544654846,
+      "learning_rate": 3e-05,
+      "loss": 0.4534,
+      "step": 307
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.8282825946807861,
+      "learning_rate": 3e-05,
+      "loss": 0.4218,
+      "step": 308
+    },
+    {
+      "epoch": 0.7357142857142858,
+      "grad_norm": 0.7293280959129333,
+      "learning_rate": 3e-05,
+      "loss": 0.3725,
+      "step": 309
+    },
+    {
+      "epoch": 0.7380952380952381,
+      "grad_norm": 0.747637927532196,
+      "learning_rate": 3e-05,
+      "loss": 0.4778,
+      "step": 310
+    },
+    {
+      "epoch": 0.7404761904761905,
+      "grad_norm": 0.6695718765258789,
+      "learning_rate": 3e-05,
+      "loss": 0.432,
+      "step": 311
+    },
+    {
+      "epoch": 0.7428571428571429,
+      "grad_norm": 1.0372726917266846,
+      "learning_rate": 3e-05,
+      "loss": 0.4589,
+      "step": 312
+    },
+    {
+      "epoch": 0.7452380952380953,
+      "grad_norm": 0.7464996576309204,
+      "learning_rate": 3e-05,
+      "loss": 0.404,
+      "step": 313
+    },
+    {
+      "epoch": 0.7476190476190476,
+      "grad_norm": 1.2544994354248047,
+      "learning_rate": 3e-05,
+      "loss": 0.5555,
+      "step": 314
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6378808617591858,
+      "learning_rate": 3e-05,
+      "loss": 0.4026,
+      "step": 315
+    },
+    {
+      "epoch": 0.7523809523809524,
+      "grad_norm": 0.8749919533729553,
+      "learning_rate": 3e-05,
+      "loss": 0.7496,
+      "step": 316
+    },
+    {
+      "epoch": 0.7547619047619047,
+      "grad_norm": 0.6927523016929626,
+      "learning_rate": 3e-05,
+      "loss": 0.4058,
+      "step": 317
+    },
+    {
+      "epoch": 0.7571428571428571,
+      "grad_norm": 1.0399421453475952,
+      "learning_rate": 3e-05,
+      "loss": 0.4785,
+      "step": 318
+    },
+    {
+      "epoch": 0.7595238095238095,
+      "grad_norm": 0.8676436543464661,
+      "learning_rate": 3e-05,
+      "loss": 0.4339,
+      "step": 319
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.9331671595573425,
+      "learning_rate": 3e-05,
+      "loss": 0.3896,
+      "step": 320
+    },
+    {
+      "epoch": 0.7642857142857142,
+      "grad_norm": 0.8491724729537964,
+      "learning_rate": 3e-05,
+      "loss": 0.3904,
+      "step": 321
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.6475184559822083,
+      "learning_rate": 3e-05,
+      "loss": 0.4101,
+      "step": 322
+    },
+    {
+      "epoch": 0.7690476190476191,
+      "grad_norm": 1.3740770816802979,
+      "learning_rate": 3e-05,
+      "loss": 0.498,
+      "step": 323
+    },
+    {
+      "epoch": 0.7714285714285715,
+      "grad_norm": 0.8867368102073669,
+      "learning_rate": 3e-05,
+      "loss": 0.4102,
+      "step": 324
+    },
+    {
+      "epoch": 0.7738095238095238,
+      "grad_norm": 0.7927978038787842,
+      "learning_rate": 3e-05,
+      "loss": 0.3936,
+      "step": 325
+    },
+    {
+      "epoch": 0.7761904761904762,
+      "grad_norm": 0.8019774556159973,
+      "learning_rate": 3e-05,
+      "loss": 0.402,
+      "step": 326
+    },
+    {
+      "epoch": 0.7785714285714286,
+      "grad_norm": 1.3307939767837524,
+      "learning_rate": 3e-05,
+      "loss": 0.4611,
+      "step": 327
+    },
+    {
+      "epoch": 0.780952380952381,
+      "grad_norm": 0.7460595965385437,
+      "learning_rate": 3e-05,
+      "loss": 0.4083,
+      "step": 328
+    },
+    {
+      "epoch": 0.7833333333333333,
+      "grad_norm": 0.5957393646240234,
+      "learning_rate": 3e-05,
+      "loss": 0.3989,
+      "step": 329
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.9565883278846741,
+      "learning_rate": 3e-05,
+      "loss": 0.4277,
+      "step": 330
+    },
+    {
+      "epoch": 0.7880952380952381,
+      "grad_norm": 0.7315310835838318,
+      "learning_rate": 3e-05,
+      "loss": 0.5165,
+      "step": 331
+    },
+    {
+      "epoch": 0.7904761904761904,
+      "grad_norm": 1.2769473791122437,
+      "learning_rate": 3e-05,
+      "loss": 0.42,
+      "step": 332
+    },
+    {
+      "epoch": 0.7928571428571428,
+      "grad_norm": 0.7580127120018005,
+      "learning_rate": 3e-05,
+      "loss": 0.4258,
+      "step": 333
+    },
+    {
+      "epoch": 0.7952380952380952,
+      "grad_norm": 0.7266448140144348,
+      "learning_rate": 3e-05,
+      "loss": 0.398,
+      "step": 334
+    },
+    {
+      "epoch": 0.7976190476190477,
+      "grad_norm": 0.6106278896331787,
+      "learning_rate": 3e-05,
+      "loss": 0.4565,
+      "step": 335
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.2278895378112793,
+      "learning_rate": 3e-05,
+      "loss": 0.5243,
+      "step": 336
+    },
+    {
+      "epoch": 0.8023809523809524,
+      "grad_norm": 0.8991657495498657,
+      "learning_rate": 3e-05,
+      "loss": 0.389,
+      "step": 337
+    },
+    {
+      "epoch": 0.8047619047619048,
+      "grad_norm": 0.9713463187217712,
+      "learning_rate": 3e-05,
+      "loss": 0.3885,
+      "step": 338
+    },
+    {
+      "epoch": 0.8071428571428572,
+      "grad_norm": 1.4198249578475952,
+      "learning_rate": 3e-05,
+      "loss": 0.433,
+      "step": 339
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.5804428458213806,
+      "learning_rate": 3e-05,
+      "loss": 0.3786,
+      "step": 340
+    },
+    {
+      "epoch": 0.8119047619047619,
+      "grad_norm": 0.7774984240531921,
+      "learning_rate": 3e-05,
+      "loss": 0.4649,
+      "step": 341
+    },
+    {
+      "epoch": 0.8142857142857143,
+      "grad_norm": 0.8857919573783875,
+      "learning_rate": 3e-05,
+      "loss": 0.4717,
+      "step": 342
+    },
+    {
+      "epoch": 0.8166666666666667,
+      "grad_norm": 0.7703973054885864,
+      "learning_rate": 3e-05,
+      "loss": 0.428,
+      "step": 343
+    },
+    {
+      "epoch": 0.819047619047619,
+      "grad_norm": 0.9551693797111511,
+      "learning_rate": 3e-05,
+      "loss": 0.4455,
+      "step": 344
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 0.6841679215431213,
+      "learning_rate": 3e-05,
+      "loss": 0.4176,
+      "step": 345
+    },
+    {
+      "epoch": 0.8238095238095238,
+      "grad_norm": 0.9121724963188171,
+      "learning_rate": 3e-05,
+      "loss": 0.4713,
+      "step": 346
+    },
+    {
+      "epoch": 0.8261904761904761,
+      "grad_norm": 0.8475046753883362,
+      "learning_rate": 3e-05,
+      "loss": 0.3869,
+      "step": 347
+    },
+    {
+      "epoch": 0.8285714285714286,
+      "grad_norm": 1.2067185640335083,
+      "learning_rate": 3e-05,
+      "loss": 0.4964,
+      "step": 348
+    },
+    {
+      "epoch": 0.830952380952381,
+      "grad_norm": 0.7562458515167236,
+      "learning_rate": 3e-05,
+      "loss": 0.4228,
+      "step": 349
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.6852816939353943,
+      "learning_rate": 3e-05,
+      "loss": 0.3723,
+      "step": 350
+    },
+    {
+      "epoch": 0.8357142857142857,
+      "grad_norm": 0.6030831336975098,
+      "learning_rate": 3e-05,
+      "loss": 0.5053,
+      "step": 351
+    },
+    {
+      "epoch": 0.8380952380952381,
+      "grad_norm": 1.0555213689804077,
+      "learning_rate": 3e-05,
+      "loss": 0.4575,
+      "step": 352
+    },
+    {
+      "epoch": 0.8404761904761905,
+      "grad_norm": 0.6861211657524109,
+      "learning_rate": 3e-05,
+      "loss": 0.3885,
+      "step": 353
+    },
+    {
+      "epoch": 0.8428571428571429,
+      "grad_norm": 0.9972875714302063,
+      "learning_rate": 3e-05,
+      "loss": 0.438,
+      "step": 354
+    },
+    {
+      "epoch": 0.8452380952380952,
+      "grad_norm": 0.7220526933670044,
+      "learning_rate": 3e-05,
+      "loss": 0.4236,
+      "step": 355
+    },
+    {
+      "epoch": 0.8476190476190476,
+      "grad_norm": 0.5923830270767212,
+      "learning_rate": 3e-05,
+      "loss": 0.3371,
+      "step": 356
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.9891591668128967,
+      "learning_rate": 3e-05,
+      "loss": 0.4189,
+      "step": 357
+    },
+    {
+      "epoch": 0.8523809523809524,
+      "grad_norm": 0.8928924798965454,
+      "learning_rate": 3e-05,
+      "loss": 0.4261,
+      "step": 358
+    },
+    {
+      "epoch": 0.8547619047619047,
+      "grad_norm": 0.6894112229347229,
+      "learning_rate": 3e-05,
+      "loss": 0.4658,
+      "step": 359
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.7407474517822266,
+      "learning_rate": 3e-05,
+      "loss": 0.4619,
+      "step": 360
+    },
+    {
+      "epoch": 0.8595238095238096,
+      "grad_norm": 0.6776091456413269,
+      "learning_rate": 3e-05,
+      "loss": 0.4396,
+      "step": 361
+    },
+    {
+      "epoch": 0.861904761904762,
+      "grad_norm": 1.4972211122512817,
+      "learning_rate": 3e-05,
+      "loss": 0.4552,
+      "step": 362
+    },
+    {
+      "epoch": 0.8642857142857143,
+      "grad_norm": 1.076313853263855,
+      "learning_rate": 3e-05,
+      "loss": 0.4211,
+      "step": 363
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.8312737345695496,
+      "learning_rate": 3e-05,
+      "loss": 0.3821,
+      "step": 364
+    },
+    {
+      "epoch": 0.8690476190476191,
+      "grad_norm": 0.6959190368652344,
+      "learning_rate": 3e-05,
+      "loss": 0.4649,
+      "step": 365
+    },
+    {
+      "epoch": 0.8714285714285714,
+      "grad_norm": 0.9157832264900208,
+      "learning_rate": 3e-05,
+      "loss": 0.4405,
+      "step": 366
+    },
+    {
+      "epoch": 0.8738095238095238,
+      "grad_norm": 1.097048282623291,
+      "learning_rate": 3e-05,
+      "loss": 0.4014,
+      "step": 367
+    },
+    {
+      "epoch": 0.8761904761904762,
+      "grad_norm": 0.7263518571853638,
+      "learning_rate": 3e-05,
+      "loss": 0.3528,
+      "step": 368
+    },
+    {
+      "epoch": 0.8785714285714286,
+      "grad_norm": 1.4131529331207275,
+      "learning_rate": 3e-05,
+      "loss": 0.5023,
+      "step": 369
+    },
+    {
+      "epoch": 0.8809523809523809,
+      "grad_norm": 1.0101478099822998,
+      "learning_rate": 3e-05,
+      "loss": 0.4401,
+      "step": 370
+    },
+    {
+      "epoch": 0.8833333333333333,
+      "grad_norm": 1.016892433166504,
+      "learning_rate": 3e-05,
+      "loss": 0.4605,
+      "step": 371
+    },
+    {
+      "epoch": 0.8857142857142857,
+      "grad_norm": 1.1927547454833984,
+      "learning_rate": 3e-05,
+      "loss": 0.4652,
+      "step": 372
+    },
+    {
+      "epoch": 0.888095238095238,
+      "grad_norm": 0.7094401717185974,
+      "learning_rate": 3e-05,
+      "loss": 0.4653,
+      "step": 373
+    },
+    {
+      "epoch": 0.8904761904761904,
+      "grad_norm": 0.9114309549331665,
+      "learning_rate": 3e-05,
+      "loss": 0.4095,
+      "step": 374
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.7444086074829102,
+      "learning_rate": 3e-05,
+      "loss": 0.4333,
+      "step": 375
+    },
+    {
+      "epoch": 0.8952380952380953,
+      "grad_norm": 0.8845041990280151,
+      "learning_rate": 3e-05,
+      "loss": 0.5979,
+      "step": 376
+    },
+    {
+      "epoch": 0.8976190476190476,
+      "grad_norm": 1.1072129011154175,
+      "learning_rate": 3e-05,
+      "loss": 0.5131,
+      "step": 377
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.3130736351013184,
+      "learning_rate": 3e-05,
+      "loss": 0.5109,
+      "step": 378
+    },
+    {
+      "epoch": 0.9023809523809524,
+      "grad_norm": 0.8190350532531738,
+      "learning_rate": 3e-05,
+      "loss": 0.427,
+      "step": 379
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.7488160729408264,
+      "learning_rate": 3e-05,
+      "loss": 0.3939,
+      "step": 380
+    },
+    {
+      "epoch": 0.9071428571428571,
+      "grad_norm": 1.0414373874664307,
+      "learning_rate": 3e-05,
+      "loss": 0.391,
+      "step": 381
+    },
+    {
+      "epoch": 0.9095238095238095,
+      "grad_norm": 1.3301194906234741,
+      "learning_rate": 3e-05,
+      "loss": 0.5093,
+      "step": 382
+    },
+    {
+      "epoch": 0.9119047619047619,
+      "grad_norm": 0.9577381610870361,
+      "learning_rate": 3e-05,
+      "loss": 0.37,
+      "step": 383
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 1.357572078704834,
+      "learning_rate": 3e-05,
+      "loss": 0.466,
+      "step": 384
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.7440205812454224,
+      "learning_rate": 3e-05,
+      "loss": 0.4536,
+      "step": 385
+    },
+    {
+      "epoch": 0.919047619047619,
+      "grad_norm": 0.7036682367324829,
+      "learning_rate": 3e-05,
+      "loss": 0.4357,
+      "step": 386
+    },
+    {
+      "epoch": 0.9214285714285714,
+      "grad_norm": 1.2188128232955933,
+      "learning_rate": 3e-05,
+      "loss": 0.409,
+      "step": 387
+    },
+    {
+      "epoch": 0.9238095238095239,
+      "grad_norm": 0.5263180732727051,
+      "learning_rate": 3e-05,
+      "loss": 0.3951,
+      "step": 388
+    },
+    {
+      "epoch": 0.9261904761904762,
+      "grad_norm": 0.6690953373908997,
+      "learning_rate": 3e-05,
+      "loss": 0.3835,
+      "step": 389
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.9960648417472839,
+      "learning_rate": 3e-05,
+      "loss": 0.4646,
+      "step": 390
+    },
+    {
+      "epoch": 0.930952380952381,
+      "grad_norm": 1.1153391599655151,
+      "learning_rate": 3e-05,
+      "loss": 0.5308,
+      "step": 391
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.501700222492218,
+      "learning_rate": 3e-05,
+      "loss": 0.3454,
+      "step": 392
+    },
+    {
+      "epoch": 0.9357142857142857,
+      "grad_norm": 0.760089099407196,
+      "learning_rate": 3e-05,
+      "loss": 0.3501,
+      "step": 393
+    },
+    {
+      "epoch": 0.9380952380952381,
+      "grad_norm": 0.9005244970321655,
+      "learning_rate": 3e-05,
+      "loss": 0.4264,
+      "step": 394
+    },
+    {
+      "epoch": 0.9404761904761905,
+      "grad_norm": 0.9984633922576904,
+      "learning_rate": 3e-05,
+      "loss": 0.3715,
+      "step": 395
+    },
+    {
+      "epoch": 0.9428571428571428,
+      "grad_norm": 0.9046674370765686,
+      "learning_rate": 3e-05,
+      "loss": 0.4708,
+      "step": 396
+    },
+    {
+      "epoch": 0.9452380952380952,
+      "grad_norm": 1.6578477621078491,
+      "learning_rate": 3e-05,
+      "loss": 0.4625,
+      "step": 397
+    },
+    {
+      "epoch": 0.9476190476190476,
+      "grad_norm": 0.7396510243415833,
+      "learning_rate": 3e-05,
+      "loss": 0.3877,
+      "step": 398
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.679201066493988,
+      "learning_rate": 3e-05,
+      "loss": 0.4501,
+      "step": 399
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.8374237418174744,
+      "learning_rate": 3e-05,
+      "loss": 0.3419,
+      "step": 400
+    },
+    {
+      "epoch": 0.9547619047619048,
+      "grad_norm": 0.8782289624214172,
+      "learning_rate": 3e-05,
+      "loss": 0.4413,
+      "step": 401
+    },
+    {
+      "epoch": 0.9571428571428572,
+      "grad_norm": 1.0352013111114502,
+      "learning_rate": 3e-05,
+      "loss": 0.4878,
+      "step": 402
+    },
+    {
+      "epoch": 0.9595238095238096,
+      "grad_norm": 0.6308469176292419,
+      "learning_rate": 3e-05,
+      "loss": 0.386,
+      "step": 403
+    },
+    {
+      "epoch": 0.9619047619047619,
+      "grad_norm": 1.0782958269119263,
+      "learning_rate": 3e-05,
+      "loss": 0.4223,
+      "step": 404
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 2.6651995182037354,
+      "learning_rate": 3e-05,
+      "loss": 0.7216,
+      "step": 405
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.7647043466567993,
+      "learning_rate": 3e-05,
+      "loss": 0.4042,
+      "step": 406
+    },
+    {
+      "epoch": 0.969047619047619,
+      "grad_norm": 0.6673374176025391,
+      "learning_rate": 3e-05,
+      "loss": 0.4288,
+      "step": 407
+    },
+    {
+      "epoch": 0.9714285714285714,
+      "grad_norm": 0.6782795786857605,
+      "learning_rate": 3e-05,
+      "loss": 0.3983,
+      "step": 408
+    },
+    {
+      "epoch": 0.9738095238095238,
+      "grad_norm": 0.7260273694992065,
+      "learning_rate": 3e-05,
+      "loss": 0.4023,
+      "step": 409
+    },
+    {
+      "epoch": 0.9761904761904762,
+      "grad_norm": 0.8369085788726807,
+      "learning_rate": 3e-05,
+      "loss": 0.3733,
+      "step": 410
+    },
+    {
+      "epoch": 0.9785714285714285,
+      "grad_norm": 0.6836142539978027,
+      "learning_rate": 3e-05,
+      "loss": 0.3972,
+      "step": 411
+    },
+    {
+      "epoch": 0.9809523809523809,
+      "grad_norm": 1.2415976524353027,
+      "learning_rate": 3e-05,
+      "loss": 0.4806,
+      "step": 412
+    },
+    {
+      "epoch": 0.9833333333333333,
+      "grad_norm": 0.9629127979278564,
+      "learning_rate": 3e-05,
+      "loss": 0.4785,
+      "step": 413
+    },
+    {
+      "epoch": 0.9857142857142858,
+      "grad_norm": 0.8129779696464539,
+      "learning_rate": 3e-05,
+      "loss": 0.4583,
+      "step": 414
+    },
+    {
+      "epoch": 0.9880952380952381,
+      "grad_norm": 0.8651249408721924,
+      "learning_rate": 3e-05,
+      "loss": 0.4687,
+      "step": 415
+    },
+    {
+      "epoch": 0.9904761904761905,
+      "grad_norm": 0.6915225982666016,
+      "learning_rate": 3e-05,
+      "loss": 0.414,
+      "step": 416
+    },
+    {
+      "epoch": 0.9928571428571429,
+      "grad_norm": 1.0824182033538818,
+      "learning_rate": 3e-05,
+      "loss": 0.3789,
+      "step": 417
+    },
+    {
+      "epoch": 0.9952380952380953,
+      "grad_norm": 0.6016390919685364,
+      "learning_rate": 3e-05,
+      "loss": 0.3457,
+      "step": 418
+    },
+    {
+      "epoch": 0.9976190476190476,
+      "grad_norm": 1.211536169052124,
+      "learning_rate": 3e-05,
+      "loss": 0.5893,
+      "step": 419
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9525183439254761,
+      "learning_rate": 3e-05,
+      "loss": 0.4137,
+      "step": 420
+    },
+    {
+      "epoch": 1.0,
+      "step": 420,
+      "total_flos": 1.7662621293477888e+17,
+      "train_loss": 0.45642305286157697,
+      "train_runtime": 1778.0298,
+      "train_samples_per_second": 1.886,
+      "train_steps_per_second": 0.236
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 420,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7662621293477888e+17,
+  "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 sha256:7bb0b76061fd10a235ef63b283037cf21c7a45e78ec0ef11b1c255bd488c213f
+size 7864