Upload 20 files

README.md

@@ -0,0 +1,58 @@
+---
+license: other
+base_model: models/Vikhr-7B-instruct_0.53-PRO8-pt
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: Vikhr-7B-instruct_0.53-PRO8-sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# Vikhr-7B-instruct_0.53-PRO8-sft
+
+This model is a fine-tuned version of [models/Vikhr-7B-instruct_0.53-PRO8-pt](https://huggingface.co/models/Vikhr-7B-instruct_0.53-PRO8-pt) on the atechsplit+ruod+lenta0306x3_sft_2048 dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.1
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,16 @@
+{
+  "<|future_token_0|>": 79085,
+  "<|future_token_10|>": 79095,
+  "<|future_token_11|>": 79096,
+  "<|future_token_1|>": 79086,
+  "<|future_token_2|>": 79087,
+  "<|future_token_3|>": 79088,
+  "<|future_token_4|>": 79089,
+  "<|future_token_5|>": 79090,
+  "<|future_token_6|>": 79091,
+  "<|future_token_7|>": 79092,
+  "<|future_token_8|>": 79093,
+  "<|future_token_9|>": 79094,
+  "<|im_end|>": 79097,
+  "<|im_start|>": 79098
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9998899122967965,
+    "total_flos": 3.2891568428128666e+18,
+    "train_loss": 0.7668657067657847,
+    "train_runtime": 24228.5265,
+    "train_samples_per_second": 4.499,
+    "train_steps_per_second": 0.141
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "models/Vikhr-7B-instruct_0.53-PRO8-pt",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.41.2",
+  "use_cache": false,
+  "vocab_size": 79104
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.41.2",
+  "use_cache": false
+}

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a96cdd4cab427e3be23727972e215a5341b11f5938696a6fb83001cf018ea05
+size 4892812136

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65e934a92e0649ec740d9e665e056afe67a7ebba57cb088a5bd0f46dbe3c5e50
+size 4999817160

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28d7627af26a0dcf91464dcb0e3763d8069a08891d38237bb40f62cf7467444c
+size 4915914008

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6ff9aacb388fd72e17fb1b43e4d3feb60fa6b8993437d45b5b6573901cf04b
+size 4915914008

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:281d7eb3d18d37a9252f1fb3822dac06890ac915d4cbada08b17d1e063cc30f2
+size 2510384720

model.safetensors.index.json

@@ -0,0 +1,370 @@
+{
+  "metadata": {
+    "total_size": 22234800128
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00005-of-00005.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
+    "model.norm.weight": "model-00005-of-00005.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3f0f84b42f79947ab92931c7c5ded699e845e6862e4e29f0b97f87e279da601
+size 1636166

tokenizer_config.json

@@ -0,0 +1,160 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79085": {
+      "content": "<|future_token_0|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79086": {
+      "content": "<|future_token_1|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79087": {
+      "content": "<|future_token_2|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79088": {
+      "content": "<|future_token_3|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79089": {
+      "content": "<|future_token_4|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79090": {
+      "content": "<|future_token_5|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79091": {
+      "content": "<|future_token_6|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79092": {
+      "content": "<|future_token_7|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79093": {
+      "content": "<|future_token_8|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79094": {
+      "content": "<|future_token_9|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79095": {
+      "content": "<|future_token_10|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79096": {
+      "content": "<|future_token_11|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "79097": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "79098": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\n' + system_message + '<|im_end|>\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\n' + content + '<|im_end|>\n<|im_start|>assistant\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9998899122967965,
+    "total_flos": 3.2891568428128666e+18,
+    "train_loss": 0.7668657067657847,
+    "train_runtime": 24228.5265,
+    "train_samples_per_second": 4.499,
+    "train_steps_per_second": 0.141
+}

trainer_log.jsonl

@@ -0,0 +1,341 @@
+{"current_steps": 10, "total_steps": 3406, "loss": 1.4046, "learning_rate": 1.9999583060217186e-05, "epoch": 0.0029356720854280577, "percentage": 0.29, "elapsed_time": "0:01:10", "remaining_time": "6:40:13"}
+{"current_steps": 20, "total_steps": 3406, "loss": 1.2805, "learning_rate": 1.9998315387870395e-05, "epoch": 0.005871344170856115, "percentage": 0.59, "elapsed_time": "0:02:22", "remaining_time": "6:42:38"}
+{"current_steps": 30, "total_steps": 3406, "loss": 1.2627, "learning_rate": 1.9996197048273697e-05, "epoch": 0.008807016256284174, "percentage": 0.88, "elapsed_time": "0:03:36", "remaining_time": "6:46:12"}
+{"current_steps": 40, "total_steps": 3406, "loss": 1.34, "learning_rate": 1.999322822165767e-05, "epoch": 0.01174268834171223, "percentage": 1.17, "elapsed_time": "0:04:44", "remaining_time": "6:38:58"}
+{"current_steps": 50, "total_steps": 3406, "loss": 1.2963, "learning_rate": 1.998940916061322e-05, "epoch": 0.014678360427140288, "percentage": 1.47, "elapsed_time": "0:05:55", "remaining_time": "6:37:17"}
+{"current_steps": 60, "total_steps": 3406, "loss": 1.3513, "learning_rate": 1.9984740190070102e-05, "epoch": 0.017614032512568347, "percentage": 1.76, "elapsed_time": "0:07:00", "remaining_time": "6:30:28"}
+{"current_steps": 70, "total_steps": 3406, "loss": 1.2629, "learning_rate": 1.9979221707269273e-05, "epoch": 0.020549704597996404, "percentage": 2.06, "elapsed_time": "0:08:09", "remaining_time": "6:28:53"}
+{"current_steps": 80, "total_steps": 3406, "loss": 1.2504, "learning_rate": 1.997285418172908e-05, "epoch": 0.02348537668342446, "percentage": 2.35, "elapsed_time": "0:09:17", "remaining_time": "6:26:05"}
+{"current_steps": 90, "total_steps": 3406, "loss": 1.2854, "learning_rate": 1.9965638155205335e-05, "epoch": 0.02642104876885252, "percentage": 2.64, "elapsed_time": "0:10:33", "remaining_time": "6:29:04"}
+{"current_steps": 100, "total_steps": 3406, "loss": 1.2583, "learning_rate": 1.995757424164521e-05, "epoch": 0.029356720854280576, "percentage": 2.94, "elapsed_time": "0:11:39", "remaining_time": "6:25:35"}
+{"current_steps": 110, "total_steps": 3406, "loss": 1.2612, "learning_rate": 1.9948663127135003e-05, "epoch": 0.03229239293970863, "percentage": 3.23, "elapsed_time": "0:12:49", "remaining_time": "6:24:08"}
+{"current_steps": 120, "total_steps": 3406, "loss": 1.237, "learning_rate": 1.9938905569841754e-05, "epoch": 0.035228065025136694, "percentage": 3.52, "elapsed_time": "0:14:00", "remaining_time": "6:23:25"}
+{"current_steps": 130, "total_steps": 3406, "loss": 1.2394, "learning_rate": 1.9928302399948767e-05, "epoch": 0.03816373711056475, "percentage": 3.82, "elapsed_time": "0:15:10", "remaining_time": "6:22:17"}
+{"current_steps": 140, "total_steps": 3406, "loss": 1.1899, "learning_rate": 1.991685451958495e-05, "epoch": 0.04109940919599281, "percentage": 4.11, "elapsed_time": "0:16:21", "remaining_time": "6:21:38"}
+{"current_steps": 150, "total_steps": 3406, "loss": 1.1939, "learning_rate": 1.990456290274808e-05, "epoch": 0.04403508128142086, "percentage": 4.4, "elapsed_time": "0:17:33", "remaining_time": "6:21:05"}
+{"current_steps": 160, "total_steps": 3406, "loss": 1.2212, "learning_rate": 1.9891428595221914e-05, "epoch": 0.04697075336684892, "percentage": 4.7, "elapsed_time": "0:18:43", "remaining_time": "6:19:58"}
+{"current_steps": 170, "total_steps": 3406, "loss": 1.1824, "learning_rate": 1.9877452714487232e-05, "epoch": 0.049906425452276984, "percentage": 4.99, "elapsed_time": "0:19:55", "remaining_time": "6:19:11"}
+{"current_steps": 180, "total_steps": 3406, "loss": 1.2118, "learning_rate": 1.9862636449626752e-05, "epoch": 0.05284209753770504, "percentage": 5.28, "elapsed_time": "0:21:15", "remaining_time": "6:21:07"}
+{"current_steps": 190, "total_steps": 3406, "loss": 1.2377, "learning_rate": 1.9846981061223958e-05, "epoch": 0.0557777696231331, "percentage": 5.58, "elapsed_time": "0:22:24", "remaining_time": "6:19:20"}
+{"current_steps": 200, "total_steps": 3406, "loss": 1.1995, "learning_rate": 1.9830487881255864e-05, "epoch": 0.05871344170856115, "percentage": 5.87, "elapsed_time": "0:23:25", "remaining_time": "6:15:28"}
+{"current_steps": 210, "total_steps": 3406, "loss": 1.1114, "learning_rate": 1.981315831297966e-05, "epoch": 0.06164911379398921, "percentage": 6.17, "elapsed_time": "0:24:36", "remaining_time": "6:14:33"}
+{"current_steps": 220, "total_steps": 3406, "loss": 1.1897, "learning_rate": 1.9794993830813358e-05, "epoch": 0.06458478587941727, "percentage": 6.46, "elapsed_time": "0:25:50", "remaining_time": "6:14:09"}
+{"current_steps": 230, "total_steps": 3406, "loss": 1.1592, "learning_rate": 1.9775995980210306e-05, "epoch": 0.06752045796484532, "percentage": 6.75, "elapsed_time": "0:26:56", "remaining_time": "6:11:55"}
+{"current_steps": 240, "total_steps": 3406, "loss": 1.1712, "learning_rate": 1.9756166377527734e-05, "epoch": 0.07045613005027339, "percentage": 7.05, "elapsed_time": "0:28:04", "remaining_time": "6:10:17"}
+{"current_steps": 250, "total_steps": 3406, "loss": 1.1724, "learning_rate": 1.9735506709889213e-05, "epoch": 0.07339180213570144, "percentage": 7.34, "elapsed_time": "0:29:16", "remaining_time": "6:09:35"}
+{"current_steps": 260, "total_steps": 3406, "loss": 1.1767, "learning_rate": 1.9714018735041125e-05, "epoch": 0.0763274742211295, "percentage": 7.63, "elapsed_time": "0:30:29", "remaining_time": "6:09:02"}
+{"current_steps": 270, "total_steps": 3406, "loss": 1.1553, "learning_rate": 1.9691704281203098e-05, "epoch": 0.07926314630655756, "percentage": 7.93, "elapsed_time": "0:31:40", "remaining_time": "6:07:57"}
+{"current_steps": 280, "total_steps": 3406, "loss": 1.1577, "learning_rate": 1.966856524691247e-05, "epoch": 0.08219881839198562, "percentage": 8.22, "elapsed_time": "0:32:49", "remaining_time": "6:06:29"}
+{"current_steps": 290, "total_steps": 3406, "loss": 1.1627, "learning_rate": 1.9644603600862753e-05, "epoch": 0.08513449047741367, "percentage": 8.51, "elapsed_time": "0:33:56", "remaining_time": "6:04:41"}
+{"current_steps": 300, "total_steps": 3406, "loss": 1.1483, "learning_rate": 1.961982138173615e-05, "epoch": 0.08807016256284173, "percentage": 8.81, "elapsed_time": "0:35:13", "remaining_time": "6:04:43"}
+{"current_steps": 310, "total_steps": 3406, "loss": 1.2015, "learning_rate": 1.959422069803007e-05, "epoch": 0.09100583464826979, "percentage": 9.1, "elapsed_time": "0:36:21", "remaining_time": "6:03:03"}
+{"current_steps": 320, "total_steps": 3406, "loss": 1.1068, "learning_rate": 1.956780372787777e-05, "epoch": 0.09394150673369785, "percentage": 9.4, "elapsed_time": "0:37:35", "remaining_time": "6:02:30"}
+{"current_steps": 330, "total_steps": 3406, "loss": 1.1424, "learning_rate": 1.9540572718863012e-05, "epoch": 0.0968771788191259, "percentage": 9.69, "elapsed_time": "0:38:49", "remaining_time": "6:01:52"}
+{"current_steps": 340, "total_steps": 3406, "loss": 1.1508, "learning_rate": 1.9512529987828853e-05, "epoch": 0.09981285090455397, "percentage": 9.98, "elapsed_time": "0:40:02", "remaining_time": "6:01:08"}
+{"current_steps": 350, "total_steps": 3406, "loss": 1.1623, "learning_rate": 1.9483677920680512e-05, "epoch": 0.10274852298998202, "percentage": 10.28, "elapsed_time": "0:41:08", "remaining_time": "5:59:14"}
+{"current_steps": 360, "total_steps": 3406, "loss": 1.161, "learning_rate": 1.9454018972182383e-05, "epoch": 0.10568419507541008, "percentage": 10.57, "elapsed_time": "0:42:19", "remaining_time": "5:58:09"}
+{"current_steps": 370, "total_steps": 3406, "loss": 1.1444, "learning_rate": 1.9423555665749182e-05, "epoch": 0.10861986716083813, "percentage": 10.86, "elapsed_time": "0:43:28", "remaining_time": "5:56:40"}
+{"current_steps": 380, "total_steps": 3406, "loss": 1.171, "learning_rate": 1.939229059323124e-05, "epoch": 0.1115555392462662, "percentage": 11.16, "elapsed_time": "0:44:36", "remaining_time": "5:55:11"}
+{"current_steps": 390, "total_steps": 3406, "loss": 1.1365, "learning_rate": 1.9360226414694008e-05, "epoch": 0.11449121133169425, "percentage": 11.45, "elapsed_time": "0:45:42", "remaining_time": "5:53:30"}
+{"current_steps": 400, "total_steps": 3406, "loss": 1.1342, "learning_rate": 1.932736585819171e-05, "epoch": 0.1174268834171223, "percentage": 11.74, "elapsed_time": "0:46:51", "remaining_time": "5:52:07"}
+{"current_steps": 410, "total_steps": 3406, "loss": 1.0428, "learning_rate": 1.929371171953526e-05, "epoch": 0.12036255550255036, "percentage": 12.04, "elapsed_time": "0:48:06", "remaining_time": "5:51:29"}
+{"current_steps": 420, "total_steps": 3406, "loss": 1.1135, "learning_rate": 1.9259266862054366e-05, "epoch": 0.12329822758797843, "percentage": 12.33, "elapsed_time": "0:49:20", "remaining_time": "5:50:49"}
+{"current_steps": 430, "total_steps": 3406, "loss": 1.1154, "learning_rate": 1.9224034216353947e-05, "epoch": 0.12623389967340648, "percentage": 12.62, "elapsed_time": "0:50:32", "remaining_time": "5:49:50"}
+{"current_steps": 440, "total_steps": 3406, "loss": 1.2029, "learning_rate": 1.9188016780064768e-05, "epoch": 0.12916957175883453, "percentage": 12.92, "elapsed_time": "0:51:47", "remaining_time": "5:49:07"}
+{"current_steps": 450, "total_steps": 3406, "loss": 1.1272, "learning_rate": 1.9151217617588412e-05, "epoch": 0.1321052438442626, "percentage": 13.21, "elapsed_time": "0:53:03", "remaining_time": "5:48:30"}
+{"current_steps": 460, "total_steps": 3406, "loss": 1.1421, "learning_rate": 1.9113639859836544e-05, "epoch": 0.13504091592969064, "percentage": 13.51, "elapsed_time": "0:54:13", "remaining_time": "5:47:19"}
+{"current_steps": 470, "total_steps": 3406, "loss": 1.14, "learning_rate": 1.9075286703964554e-05, "epoch": 0.13797658801511872, "percentage": 13.8, "elapsed_time": "0:55:22", "remaining_time": "5:45:52"}
+{"current_steps": 480, "total_steps": 3406, "loss": 1.1699, "learning_rate": 1.9036161413099512e-05, "epoch": 0.14091226010054678, "percentage": 14.09, "elapsed_time": "0:56:29", "remaining_time": "5:44:24"}
+{"current_steps": 490, "total_steps": 3406, "loss": 1.0919, "learning_rate": 1.899626731606255e-05, "epoch": 0.14384793218597483, "percentage": 14.39, "elapsed_time": "0:57:36", "remaining_time": "5:42:52"}
+{"current_steps": 500, "total_steps": 3406, "loss": 1.0625, "learning_rate": 1.895560780708565e-05, "epoch": 0.14678360427140288, "percentage": 14.68, "elapsed_time": "0:58:43", "remaining_time": "5:41:17"}
+{"current_steps": 510, "total_steps": 3406, "loss": 1.0899, "learning_rate": 1.8914186345522846e-05, "epoch": 0.14971927635683094, "percentage": 14.97, "elapsed_time": "1:00:01", "remaining_time": "5:40:52"}
+{"current_steps": 520, "total_steps": 3406, "loss": 1.1148, "learning_rate": 1.8872006455555906e-05, "epoch": 0.152654948442259, "percentage": 15.27, "elapsed_time": "1:01:14", "remaining_time": "5:39:53"}
+{"current_steps": 530, "total_steps": 3406, "loss": 1.02, "learning_rate": 1.8829071725894483e-05, "epoch": 0.15559062052768705, "percentage": 15.56, "elapsed_time": "1:02:24", "remaining_time": "5:38:38"}
+{"current_steps": 540, "total_steps": 3406, "loss": 1.1167, "learning_rate": 1.87853858094708e-05, "epoch": 0.15852629261311513, "percentage": 15.85, "elapsed_time": "1:03:32", "remaining_time": "5:37:14"}
+{"current_steps": 550, "total_steps": 3406, "loss": 1.0181, "learning_rate": 1.8740952423128842e-05, "epoch": 0.16146196469854318, "percentage": 16.15, "elapsed_time": "1:04:49", "remaining_time": "5:36:37"}
+{"current_steps": 560, "total_steps": 3406, "loss": 1.1118, "learning_rate": 1.869577534730812e-05, "epoch": 0.16439763678397123, "percentage": 16.44, "elapsed_time": "1:06:03", "remaining_time": "5:35:45"}
+{"current_steps": 570, "total_steps": 3406, "loss": 1.0666, "learning_rate": 1.8649858425722033e-05, "epoch": 0.1673333088693993, "percentage": 16.74, "elapsed_time": "1:07:13", "remaining_time": "5:34:30"}
+{"current_steps": 580, "total_steps": 3406, "loss": 1.108, "learning_rate": 1.8603205565030846e-05, "epoch": 0.17026898095482734, "percentage": 17.03, "elapsed_time": "1:08:26", "remaining_time": "5:33:27"}
+{"current_steps": 590, "total_steps": 3406, "loss": 1.0833, "learning_rate": 1.8555820734509297e-05, "epoch": 0.1732046530402554, "percentage": 17.32, "elapsed_time": "1:09:34", "remaining_time": "5:32:05"}
+{"current_steps": 600, "total_steps": 3406, "loss": 1.0283, "learning_rate": 1.8507707965708892e-05, "epoch": 0.17614032512568345, "percentage": 17.62, "elapsed_time": "1:10:48", "remaining_time": "5:31:07"}
+{"current_steps": 610, "total_steps": 3406, "loss": 1.0747, "learning_rate": 1.8458871352114894e-05, "epoch": 0.17907599721111153, "percentage": 17.91, "elapsed_time": "1:11:56", "remaining_time": "5:29:44"}
+{"current_steps": 620, "total_steps": 3406, "loss": 1.11, "learning_rate": 1.840931504879806e-05, "epoch": 0.18201166929653959, "percentage": 18.2, "elapsed_time": "1:13:09", "remaining_time": "5:28:44"}
+{"current_steps": 630, "total_steps": 3406, "loss": 1.0424, "learning_rate": 1.8359043272061086e-05, "epoch": 0.18494734138196764, "percentage": 18.5, "elapsed_time": "1:14:21", "remaining_time": "5:27:37"}
+{"current_steps": 640, "total_steps": 3406, "loss": 1.0818, "learning_rate": 1.8308060299079926e-05, "epoch": 0.1878830134673957, "percentage": 18.79, "elapsed_time": "1:15:34", "remaining_time": "5:26:38"}
+{"current_steps": 650, "total_steps": 3406, "loss": 1.0883, "learning_rate": 1.8256370467539847e-05, "epoch": 0.19081868555282375, "percentage": 19.08, "elapsed_time": "1:16:46", "remaining_time": "5:25:29"}
+{"current_steps": 660, "total_steps": 3406, "loss": 1.0285, "learning_rate": 1.82039781752664e-05, "epoch": 0.1937543576382518, "percentage": 19.38, "elapsed_time": "1:17:53", "remaining_time": "5:24:04"}
+{"current_steps": 670, "total_steps": 3406, "loss": 0.9751, "learning_rate": 1.815088787985124e-05, "epoch": 0.19669002972367985, "percentage": 19.67, "elapsed_time": "1:19:03", "remaining_time": "5:22:48"}
+{"current_steps": 680, "total_steps": 3406, "loss": 1.0603, "learning_rate": 1.809710409827285e-05, "epoch": 0.19962570180910794, "percentage": 19.96, "elapsed_time": "1:20:14", "remaining_time": "5:21:41"}
+{"current_steps": 690, "total_steps": 3406, "loss": 1.0919, "learning_rate": 1.804263140651227e-05, "epoch": 0.202561373894536, "percentage": 20.26, "elapsed_time": "1:21:24", "remaining_time": "5:20:24"}
+{"current_steps": 700, "total_steps": 3406, "loss": 1.0553, "learning_rate": 1.798747443916374e-05, "epoch": 0.20549704597996404, "percentage": 20.55, "elapsed_time": "1:22:35", "remaining_time": "5:19:17"}
+{"current_steps": 710, "total_steps": 3406, "loss": 1.0711, "learning_rate": 1.793163788904038e-05, "epoch": 0.2084327180653921, "percentage": 20.85, "elapsed_time": "1:23:49", "remaining_time": "5:18:18"}
+{"current_steps": 720, "total_steps": 3406, "loss": 1.0423, "learning_rate": 1.7875126506774956e-05, "epoch": 0.21136839015082015, "percentage": 21.14, "elapsed_time": "1:25:05", "remaining_time": "5:17:27"}
+{"current_steps": 730, "total_steps": 3406, "loss": 1.0679, "learning_rate": 1.781794510041564e-05, "epoch": 0.2143040622362482, "percentage": 21.43, "elapsed_time": "1:26:16", "remaining_time": "5:16:15"}
+{"current_steps": 740, "total_steps": 3406, "loss": 1.0558, "learning_rate": 1.776009853501698e-05, "epoch": 0.21723973432167626, "percentage": 21.73, "elapsed_time": "1:27:21", "remaining_time": "5:14:41"}
+{"current_steps": 750, "total_steps": 3406, "loss": 1.0198, "learning_rate": 1.770159173222595e-05, "epoch": 0.2201754064071043, "percentage": 22.02, "elapsed_time": "1:28:32", "remaining_time": "5:13:32"}
+{"current_steps": 760, "total_steps": 3406, "loss": 0.9951, "learning_rate": 1.7642429669863225e-05, "epoch": 0.2231110784925324, "percentage": 22.31, "elapsed_time": "1:29:41", "remaining_time": "5:12:17"}
+{"current_steps": 770, "total_steps": 3406, "loss": 0.9906, "learning_rate": 1.7582617381499655e-05, "epoch": 0.22604675057796045, "percentage": 22.61, "elapsed_time": "1:30:48", "remaining_time": "5:10:53"}
+{"current_steps": 780, "total_steps": 3406, "loss": 1.0711, "learning_rate": 1.7522159956028003e-05, "epoch": 0.2289824226633885, "percentage": 22.9, "elapsed_time": "1:31:56", "remaining_time": "5:09:33"}
+{"current_steps": 790, "total_steps": 3406, "loss": 0.9909, "learning_rate": 1.7461062537229987e-05, "epoch": 0.23191809474881656, "percentage": 23.19, "elapsed_time": "1:33:07", "remaining_time": "5:08:21"}
+{"current_steps": 800, "total_steps": 3406, "loss": 0.9815, "learning_rate": 1.739933032333863e-05, "epoch": 0.2348537668342446, "percentage": 23.49, "elapsed_time": "1:34:22", "remaining_time": "5:07:25"}
+{"current_steps": 810, "total_steps": 3406, "loss": 1.0191, "learning_rate": 1.733696856659599e-05, "epoch": 0.23778943891967266, "percentage": 23.78, "elapsed_time": "1:35:35", "remaining_time": "5:06:23"}
+{"current_steps": 820, "total_steps": 3406, "loss": 1.0314, "learning_rate": 1.7273982572806303e-05, "epoch": 0.24072511100510072, "percentage": 24.08, "elapsed_time": "1:36:46", "remaining_time": "5:05:12"}
+{"current_steps": 830, "total_steps": 3406, "loss": 0.958, "learning_rate": 1.721037770088455e-05, "epoch": 0.2436607830905288, "percentage": 24.37, "elapsed_time": "1:37:53", "remaining_time": "5:03:50"}
+{"current_steps": 840, "total_steps": 3406, "loss": 1.0272, "learning_rate": 1.7146159362400515e-05, "epoch": 0.24659645517595685, "percentage": 24.66, "elapsed_time": "1:39:01", "remaining_time": "5:02:30"}
+{"current_steps": 850, "total_steps": 3406, "loss": 1.0437, "learning_rate": 1.708133302111837e-05, "epoch": 0.2495321272613849, "percentage": 24.96, "elapsed_time": "1:40:07", "remaining_time": "5:01:04"}
+{"current_steps": 860, "total_steps": 3406, "loss": 1.0393, "learning_rate": 1.7015904192531814e-05, "epoch": 0.25246779934681296, "percentage": 25.25, "elapsed_time": "1:41:16", "remaining_time": "4:59:49"}
+{"current_steps": 870, "total_steps": 3406, "loss": 1.0602, "learning_rate": 1.694987844339479e-05, "epoch": 0.255403471432241, "percentage": 25.54, "elapsed_time": "1:42:30", "remaining_time": "4:58:49"}
+{"current_steps": 880, "total_steps": 3406, "loss": 0.9515, "learning_rate": 1.6883261391247888e-05, "epoch": 0.25833914351766907, "percentage": 25.84, "elapsed_time": "1:43:44", "remaining_time": "4:57:47"}
+{"current_steps": 890, "total_steps": 3406, "loss": 0.9961, "learning_rate": 1.6816058703940366e-05, "epoch": 0.2612748156030971, "percentage": 26.13, "elapsed_time": "1:44:53", "remaining_time": "4:56:32"}
+{"current_steps": 900, "total_steps": 3406, "loss": 1.0066, "learning_rate": 1.6748276099147952e-05, "epoch": 0.2642104876885252, "percentage": 26.42, "elapsed_time": "1:46:07", "remaining_time": "4:55:29"}
+{"current_steps": 910, "total_steps": 3406, "loss": 0.9714, "learning_rate": 1.6679919343886376e-05, "epoch": 0.26714615977395323, "percentage": 26.72, "elapsed_time": "1:47:21", "remaining_time": "4:54:27"}
+{"current_steps": 920, "total_steps": 3406, "loss": 0.9689, "learning_rate": 1.661099425402067e-05, "epoch": 0.2700818318593813, "percentage": 27.01, "elapsed_time": "1:48:32", "remaining_time": "4:53:17"}
+{"current_steps": 930, "total_steps": 3406, "loss": 0.9867, "learning_rate": 1.6541506693770403e-05, "epoch": 0.2730175039448094, "percentage": 27.3, "elapsed_time": "1:49:40", "remaining_time": "4:51:58"}
+{"current_steps": 940, "total_steps": 3406, "loss": 1.0281, "learning_rate": 1.647146257521071e-05, "epoch": 0.27595317603023745, "percentage": 27.6, "elapsed_time": "1:50:52", "remaining_time": "4:50:51"}
+{"current_steps": 950, "total_steps": 3406, "loss": 0.975, "learning_rate": 1.6400867857769287e-05, "epoch": 0.2788888481156655, "percentage": 27.89, "elapsed_time": "1:52:05", "remaining_time": "4:49:46"}
+{"current_steps": 960, "total_steps": 3406, "loss": 0.9373, "learning_rate": 1.6329728547719375e-05, "epoch": 0.28182452020109355, "percentage": 28.19, "elapsed_time": "1:53:13", "remaining_time": "4:48:27"}
+{"current_steps": 970, "total_steps": 3406, "loss": 0.9651, "learning_rate": 1.625805069766873e-05, "epoch": 0.2847601922865216, "percentage": 28.48, "elapsed_time": "1:54:18", "remaining_time": "4:47:03"}
+{"current_steps": 980, "total_steps": 3406, "loss": 0.9262, "learning_rate": 1.6185840406044657e-05, "epoch": 0.28769586437194966, "percentage": 28.77, "elapsed_time": "1:55:24", "remaining_time": "4:45:40"}
+{"current_steps": 990, "total_steps": 3406, "loss": 0.9972, "learning_rate": 1.611310381657515e-05, "epoch": 0.2906315364573777, "percentage": 29.07, "elapsed_time": "1:56:37", "remaining_time": "4:44:37"}
+{"current_steps": 1000, "total_steps": 3406, "loss": 0.9331, "learning_rate": 1.60398471177662e-05, "epoch": 0.29356720854280577, "percentage": 29.36, "elapsed_time": "1:57:49", "remaining_time": "4:43:28"}
+{"current_steps": 1010, "total_steps": 3406, "loss": 0.9592, "learning_rate": 1.596607654237522e-05, "epoch": 0.2965028806282338, "percentage": 29.65, "elapsed_time": "1:58:59", "remaining_time": "4:42:17"}
+{"current_steps": 1020, "total_steps": 3406, "loss": 0.9568, "learning_rate": 1.589179836688081e-05, "epoch": 0.2994385527136619, "percentage": 29.95, "elapsed_time": "2:00:08", "remaining_time": "4:41:03"}
+{"current_steps": 1030, "total_steps": 3406, "loss": 0.9928, "learning_rate": 1.5817018910948712e-05, "epoch": 0.30237422479908993, "percentage": 30.24, "elapsed_time": "2:01:22", "remaining_time": "4:40:00"}
+{"current_steps": 1040, "total_steps": 3406, "loss": 0.9387, "learning_rate": 1.574174453689415e-05, "epoch": 0.305309896884518, "percentage": 30.53, "elapsed_time": "2:02:31", "remaining_time": "4:38:43"}
+{"current_steps": 1050, "total_steps": 3406, "loss": 0.8925, "learning_rate": 1.566598164914049e-05, "epoch": 0.30824556896994604, "percentage": 30.83, "elapsed_time": "2:03:48", "remaining_time": "4:37:47"}
+{"current_steps": 1060, "total_steps": 3406, "loss": 1.0153, "learning_rate": 1.5589736693674372e-05, "epoch": 0.3111812410553741, "percentage": 31.12, "elapsed_time": "2:04:58", "remaining_time": "4:36:35"}
+{"current_steps": 1070, "total_steps": 3406, "loss": 0.9323, "learning_rate": 1.551301615749726e-05, "epoch": 0.31411691314080215, "percentage": 31.42, "elapsed_time": "2:06:03", "remaining_time": "4:35:13"}
+{"current_steps": 1080, "total_steps": 3406, "loss": 0.8901, "learning_rate": 1.5435826568073532e-05, "epoch": 0.31705258522623025, "percentage": 31.71, "elapsed_time": "2:07:15", "remaining_time": "4:34:05"}
+{"current_steps": 1090, "total_steps": 3406, "loss": 0.9118, "learning_rate": 1.535817449277511e-05, "epoch": 0.3199882573116583, "percentage": 32.0, "elapsed_time": "2:08:26", "remaining_time": "4:32:54"}
+{"current_steps": 1100, "total_steps": 3406, "loss": 0.8655, "learning_rate": 1.5280066538322703e-05, "epoch": 0.32292392939708636, "percentage": 32.3, "elapsed_time": "2:09:40", "remaining_time": "4:31:51"}
+{"current_steps": 1110, "total_steps": 3406, "loss": 0.9217, "learning_rate": 1.5201509350223708e-05, "epoch": 0.3258596014825144, "percentage": 32.59, "elapsed_time": "2:10:51", "remaining_time": "4:30:40"}
+{"current_steps": 1120, "total_steps": 3406, "loss": 0.9362, "learning_rate": 1.5122509612206785e-05, "epoch": 0.32879527356794247, "percentage": 32.88, "elapsed_time": "2:12:01", "remaining_time": "4:29:27"}
+{"current_steps": 1130, "total_steps": 3406, "loss": 0.9262, "learning_rate": 1.5043074045653215e-05, "epoch": 0.3317309456533705, "percentage": 33.18, "elapsed_time": "2:13:13", "remaining_time": "4:28:19"}
+{"current_steps": 1140, "total_steps": 3406, "loss": 0.8891, "learning_rate": 1.496320940902503e-05, "epoch": 0.3346666177387986, "percentage": 33.47, "elapsed_time": "2:14:21", "remaining_time": "4:27:04"}
+{"current_steps": 1150, "total_steps": 3406, "loss": 0.9281, "learning_rate": 1.4882922497290007e-05, "epoch": 0.33760228982422663, "percentage": 33.76, "elapsed_time": "2:15:31", "remaining_time": "4:25:51"}
+{"current_steps": 1160, "total_steps": 3406, "loss": 0.8949, "learning_rate": 1.4802220141343516e-05, "epoch": 0.3405379619096547, "percentage": 34.06, "elapsed_time": "2:16:37", "remaining_time": "4:24:32"}
+{"current_steps": 1170, "total_steps": 3406, "loss": 0.8889, "learning_rate": 1.472110920742738e-05, "epoch": 0.34347363399508274, "percentage": 34.35, "elapsed_time": "2:17:51", "remaining_time": "4:23:26"}
+{"current_steps": 1180, "total_steps": 3406, "loss": 0.8397, "learning_rate": 1.4639596596545656e-05, "epoch": 0.3464093060805108, "percentage": 34.64, "elapsed_time": "2:18:59", "remaining_time": "4:22:11"}
+{"current_steps": 1190, "total_steps": 3406, "loss": 0.9142, "learning_rate": 1.4557689243877507e-05, "epoch": 0.34934497816593885, "percentage": 34.94, "elapsed_time": "2:20:14", "remaining_time": "4:21:09"}
+{"current_steps": 1200, "total_steps": 3406, "loss": 0.9809, "learning_rate": 1.4475394118187146e-05, "epoch": 0.3522806502513669, "percentage": 35.23, "elapsed_time": "2:21:30", "remaining_time": "4:20:08"}
+{"current_steps": 1210, "total_steps": 3406, "loss": 0.9141, "learning_rate": 1.4392718221230917e-05, "epoch": 0.35521632233679495, "percentage": 35.53, "elapsed_time": "2:22:44", "remaining_time": "4:19:03"}
+{"current_steps": 1220, "total_steps": 3406, "loss": 0.8669, "learning_rate": 1.4309668587161596e-05, "epoch": 0.35815199442222306, "percentage": 35.82, "elapsed_time": "2:23:53", "remaining_time": "4:17:50"}
+{"current_steps": 1230, "total_steps": 3406, "loss": 0.8384, "learning_rate": 1.4226252281929902e-05, "epoch": 0.3610876665076511, "percentage": 36.11, "elapsed_time": "2:25:07", "remaining_time": "4:16:44"}
+{"current_steps": 1240, "total_steps": 3406, "loss": 0.8971, "learning_rate": 1.4142476402683327e-05, "epoch": 0.36402333859307917, "percentage": 36.41, "elapsed_time": "2:26:18", "remaining_time": "4:15:34"}
+{"current_steps": 1250, "total_steps": 3406, "loss": 0.8783, "learning_rate": 1.4058348077162301e-05, "epoch": 0.3669590106785072, "percentage": 36.7, "elapsed_time": "2:27:31", "remaining_time": "4:14:26"}
+{"current_steps": 1260, "total_steps": 3406, "loss": 0.9623, "learning_rate": 1.3973874463093747e-05, "epoch": 0.3698946827639353, "percentage": 36.99, "elapsed_time": "2:28:43", "remaining_time": "4:13:18"}
+{"current_steps": 1270, "total_steps": 3406, "loss": 0.8092, "learning_rate": 1.3889062747582118e-05, "epoch": 0.37283035484936333, "percentage": 37.29, "elapsed_time": "2:29:56", "remaining_time": "4:12:11"}
+{"current_steps": 1280, "total_steps": 3406, "loss": 0.8762, "learning_rate": 1.3803920146497887e-05, "epoch": 0.3757660269347914, "percentage": 37.58, "elapsed_time": "2:31:06", "remaining_time": "4:10:59"}
+{"current_steps": 1290, "total_steps": 3406, "loss": 0.8321, "learning_rate": 1.3718453903863616e-05, "epoch": 0.37870169902021944, "percentage": 37.87, "elapsed_time": "2:32:18", "remaining_time": "4:09:49"}
+{"current_steps": 1300, "total_steps": 3406, "loss": 0.8566, "learning_rate": 1.3632671291237645e-05, "epoch": 0.3816373711056475, "percentage": 38.17, "elapsed_time": "2:33:28", "remaining_time": "4:08:37"}
+{"current_steps": 1310, "total_steps": 3406, "loss": 0.8944, "learning_rate": 1.35465796070954e-05, "epoch": 0.38457304319107555, "percentage": 38.46, "elapsed_time": "2:34:38", "remaining_time": "4:07:25"}
+{"current_steps": 1320, "total_steps": 3406, "loss": 0.7583, "learning_rate": 1.3460186176208439e-05, "epoch": 0.3875087152765036, "percentage": 38.76, "elapsed_time": "2:35:49", "remaining_time": "4:06:15"}
+{"current_steps": 1330, "total_steps": 3406, "loss": 0.814, "learning_rate": 1.337349834902125e-05, "epoch": 0.39044438736193166, "percentage": 39.05, "elapsed_time": "2:37:02", "remaining_time": "4:05:07"}
+{"current_steps": 1340, "total_steps": 3406, "loss": 0.8006, "learning_rate": 1.328652350102588e-05, "epoch": 0.3933800594473597, "percentage": 39.34, "elapsed_time": "2:38:19", "remaining_time": "4:04:06"}
+{"current_steps": 1350, "total_steps": 3406, "loss": 0.8129, "learning_rate": 1.3199269032134395e-05, "epoch": 0.39631573153278776, "percentage": 39.64, "elapsed_time": "2:39:33", "remaining_time": "4:03:00"}
+{"current_steps": 1360, "total_steps": 3406, "loss": 0.8366, "learning_rate": 1.3111742366049317e-05, "epoch": 0.39925140361821587, "percentage": 39.93, "elapsed_time": "2:40:43", "remaining_time": "4:01:47"}
+{"current_steps": 1370, "total_steps": 3406, "loss": 0.8551, "learning_rate": 1.3023950949631979e-05, "epoch": 0.4021870757036439, "percentage": 40.22, "elapsed_time": "2:41:54", "remaining_time": "4:00:36"}
+{"current_steps": 1380, "total_steps": 3406, "loss": 0.8398, "learning_rate": 1.2935902252268965e-05, "epoch": 0.405122747789072, "percentage": 40.52, "elapsed_time": "2:43:04", "remaining_time": "3:59:24"}
+{"current_steps": 1390, "total_steps": 3406, "loss": 0.836, "learning_rate": 1.2847603765236589e-05, "epoch": 0.40805841987450003, "percentage": 40.81, "elapsed_time": "2:44:16", "remaining_time": "3:58:15"}
+{"current_steps": 1400, "total_steps": 3406, "loss": 0.8369, "learning_rate": 1.2759063001063531e-05, "epoch": 0.4109940919599281, "percentage": 41.1, "elapsed_time": "2:45:30", "remaining_time": "3:57:08"}
+{"current_steps": 1410, "total_steps": 3406, "loss": 0.8988, "learning_rate": 1.2670287492891675e-05, "epoch": 0.41392976404535614, "percentage": 41.4, "elapsed_time": "2:46:41", "remaining_time": "3:55:58"}
+{"current_steps": 1420, "total_steps": 3406, "loss": 0.8352, "learning_rate": 1.258128479383516e-05, "epoch": 0.4168654361307842, "percentage": 41.69, "elapsed_time": "2:48:00", "remaining_time": "3:54:57"}
+{"current_steps": 1430, "total_steps": 3406, "loss": 0.8295, "learning_rate": 1.249206247633778e-05, "epoch": 0.41980110821621225, "percentage": 41.98, "elapsed_time": "2:49:09", "remaining_time": "3:53:44"}
+{"current_steps": 1440, "total_steps": 3406, "loss": 0.8103, "learning_rate": 1.2402628131528686e-05, "epoch": 0.4227367803016403, "percentage": 42.28, "elapsed_time": "2:50:24", "remaining_time": "3:52:39"}
+{"current_steps": 1450, "total_steps": 3406, "loss": 0.7757, "learning_rate": 1.2312989368576547e-05, "epoch": 0.42567245238706836, "percentage": 42.57, "elapsed_time": "2:51:37", "remaining_time": "3:51:31"}
+{"current_steps": 1460, "total_steps": 3406, "loss": 0.7871, "learning_rate": 1.2223153814042137e-05, "epoch": 0.4286081244724964, "percentage": 42.87, "elapsed_time": "2:52:51", "remaining_time": "3:50:23"}
+{"current_steps": 1470, "total_steps": 3406, "loss": 0.851, "learning_rate": 1.2133129111229466e-05, "epoch": 0.43154379655792446, "percentage": 43.16, "elapsed_time": "2:54:03", "remaining_time": "3:49:13"}
+{"current_steps": 1480, "total_steps": 3406, "loss": 0.803, "learning_rate": 1.2042922919535484e-05, "epoch": 0.4344794686433525, "percentage": 43.45, "elapsed_time": "2:55:14", "remaining_time": "3:48:02"}
+{"current_steps": 1490, "total_steps": 3406, "loss": 0.761, "learning_rate": 1.1952542913798406e-05, "epoch": 0.43741514072878057, "percentage": 43.75, "elapsed_time": "2:56:17", "remaining_time": "3:46:41"}
+{"current_steps": 1500, "total_steps": 3406, "loss": 0.8086, "learning_rate": 1.1861996783644727e-05, "epoch": 0.4403508128142086, "percentage": 44.04, "elapsed_time": "2:57:23", "remaining_time": "3:45:24"}
+{"current_steps": 1510, "total_steps": 3406, "loss": 0.8483, "learning_rate": 1.1771292232834983e-05, "epoch": 0.44328648489963673, "percentage": 44.33, "elapsed_time": "2:58:35", "remaining_time": "3:44:14"}
+{"current_steps": 1520, "total_steps": 3406, "loss": 0.738, "learning_rate": 1.1680436978608314e-05, "epoch": 0.4462221569850648, "percentage": 44.63, "elapsed_time": "2:59:44", "remaining_time": "3:43:01"}
+{"current_steps": 1530, "total_steps": 3406, "loss": 0.7462, "learning_rate": 1.1589438751025852e-05, "epoch": 0.44915782907049284, "percentage": 44.92, "elapsed_time": "3:00:59", "remaining_time": "3:41:55"}
+{"current_steps": 1540, "total_steps": 3406, "loss": 0.7707, "learning_rate": 1.149830529231307e-05, "epoch": 0.4520935011559209, "percentage": 45.21, "elapsed_time": "3:02:07", "remaining_time": "3:40:40"}
+{"current_steps": 1550, "total_steps": 3406, "loss": 0.7832, "learning_rate": 1.140704435620104e-05, "epoch": 0.45502917324134895, "percentage": 45.51, "elapsed_time": "3:03:18", "remaining_time": "3:39:30"}
+{"current_steps": 1560, "total_steps": 3406, "loss": 0.74, "learning_rate": 1.1315663707266742e-05, "epoch": 0.457964845326777, "percentage": 45.8, "elapsed_time": "3:04:30", "remaining_time": "3:38:19"}
+{"current_steps": 1570, "total_steps": 3406, "loss": 0.6698, "learning_rate": 1.1224171120272455e-05, "epoch": 0.46090051741220506, "percentage": 46.1, "elapsed_time": "3:05:38", "remaining_time": "3:37:05"}
+{"current_steps": 1580, "total_steps": 3406, "loss": 0.7604, "learning_rate": 1.1132574379504269e-05, "epoch": 0.4638361894976331, "percentage": 46.39, "elapsed_time": "3:06:48", "remaining_time": "3:35:53"}
+{"current_steps": 1590, "total_steps": 3406, "loss": 0.7466, "learning_rate": 1.1040881278109784e-05, "epoch": 0.46677186158306117, "percentage": 46.68, "elapsed_time": "3:08:05", "remaining_time": "3:34:49"}
+{"current_steps": 1600, "total_steps": 3406, "loss": 0.7452, "learning_rate": 1.0949099617435062e-05, "epoch": 0.4697075336684892, "percentage": 46.98, "elapsed_time": "3:09:19", "remaining_time": "3:33:41"}
+{"current_steps": 1610, "total_steps": 3406, "loss": 0.7637, "learning_rate": 1.0857237206360885e-05, "epoch": 0.4726432057539173, "percentage": 47.27, "elapsed_time": "3:10:28", "remaining_time": "3:32:28"}
+{"current_steps": 1620, "total_steps": 3406, "loss": 0.7364, "learning_rate": 1.0765301860638364e-05, "epoch": 0.4755788778393453, "percentage": 47.56, "elapsed_time": "3:11:36", "remaining_time": "3:31:14"}
+{"current_steps": 1630, "total_steps": 3406, "loss": 0.7356, "learning_rate": 1.0673301402223964e-05, "epoch": 0.4785145499247734, "percentage": 47.86, "elapsed_time": "3:12:40", "remaining_time": "3:29:56"}
+{"current_steps": 1640, "total_steps": 3406, "loss": 0.765, "learning_rate": 1.0581243658614013e-05, "epoch": 0.48145022201020143, "percentage": 48.15, "elapsed_time": "3:13:50", "remaining_time": "3:28:44"}
+{"current_steps": 1650, "total_steps": 3406, "loss": 0.75, "learning_rate": 1.0489136462178718e-05, "epoch": 0.48438589409562954, "percentage": 48.44, "elapsed_time": "3:15:02", "remaining_time": "3:27:34"}
+{"current_steps": 1660, "total_steps": 3406, "loss": 0.7347, "learning_rate": 1.039698764949579e-05, "epoch": 0.4873215661810576, "percentage": 48.74, "elapsed_time": "3:16:09", "remaining_time": "3:26:19"}
+{"current_steps": 1670, "total_steps": 3406, "loss": 0.7887, "learning_rate": 1.0304805060683692e-05, "epoch": 0.49025723826648565, "percentage": 49.03, "elapsed_time": "3:17:26", "remaining_time": "3:25:14"}
+{"current_steps": 1680, "total_steps": 3406, "loss": 0.7492, "learning_rate": 1.021259653873459e-05, "epoch": 0.4931929103519137, "percentage": 49.32, "elapsed_time": "3:18:41", "remaining_time": "3:24:08"}
+{"current_steps": 1690, "total_steps": 3406, "loss": 0.7676, "learning_rate": 1.012036992884708e-05, "epoch": 0.49612858243734176, "percentage": 49.62, "elapsed_time": "3:19:58", "remaining_time": "3:23:02"}
+{"current_steps": 1700, "total_steps": 3406, "loss": 0.7088, "learning_rate": 1.0028133077758688e-05, "epoch": 0.4990642545227698, "percentage": 49.91, "elapsed_time": "3:21:08", "remaining_time": "3:21:51"}
+{"current_steps": 1710, "total_steps": 3406, "loss": 0.7646, "learning_rate": 9.935893833078284e-06, "epoch": 0.5019999266081978, "percentage": 50.21, "elapsed_time": "3:22:20", "remaining_time": "3:20:40"}
+{"current_steps": 1720, "total_steps": 3406, "loss": 0.8147, "learning_rate": 9.843660042618372e-06, "epoch": 0.5049355986936259, "percentage": 50.5, "elapsed_time": "3:23:31", "remaining_time": "3:19:29"}
+{"current_steps": 1730, "total_steps": 3406, "loss": 0.7104, "learning_rate": 9.75143955372742e-06, "epoch": 0.507871270779054, "percentage": 50.79, "elapsed_time": "3:24:39", "remaining_time": "3:18:16"}
+{"current_steps": 1740, "total_steps": 3406, "loss": 0.7367, "learning_rate": 9.659240212622175e-06, "epoch": 0.510806942864482, "percentage": 51.09, "elapsed_time": "3:25:53", "remaining_time": "3:17:08"}
+{"current_steps": 1750, "total_steps": 3406, "loss": 0.7564, "learning_rate": 9.567069863720113e-06, "epoch": 0.5137426149499101, "percentage": 51.38, "elapsed_time": "3:27:07", "remaining_time": "3:16:00"}
+{"current_steps": 1760, "total_steps": 3406, "loss": 0.7735, "learning_rate": 9.474936348972021e-06, "epoch": 0.5166782870353381, "percentage": 51.67, "elapsed_time": "3:28:22", "remaining_time": "3:14:52"}
+{"current_steps": 1770, "total_steps": 3406, "loss": 0.7035, "learning_rate": 9.382847507194797e-06, "epoch": 0.5196139591207662, "percentage": 51.97, "elapsed_time": "3:29:36", "remaining_time": "3:13:44"}
+{"current_steps": 1780, "total_steps": 3406, "loss": 0.6347, "learning_rate": 9.290811173404513e-06, "epoch": 0.5225496312061942, "percentage": 52.26, "elapsed_time": "3:30:47", "remaining_time": "3:12:32"}
+{"current_steps": 1790, "total_steps": 3406, "loss": 0.6359, "learning_rate": 9.198835178149807e-06, "epoch": 0.5254853032916224, "percentage": 52.55, "elapsed_time": "3:31:56", "remaining_time": "3:11:20"}
+{"current_steps": 1800, "total_steps": 3406, "loss": 0.7137, "learning_rate": 9.106927346845663e-06, "epoch": 0.5284209753770504, "percentage": 52.85, "elapsed_time": "3:33:08", "remaining_time": "3:10:09"}
+{"current_steps": 1810, "total_steps": 3406, "loss": 0.7085, "learning_rate": 9.015095499107578e-06, "epoch": 0.5313566474624785, "percentage": 53.14, "elapsed_time": "3:34:21", "remaining_time": "3:09:01"}
+{"current_steps": 1820, "total_steps": 3406, "loss": 0.6501, "learning_rate": 8.923347448086311e-06, "epoch": 0.5342923195479065, "percentage": 53.44, "elapsed_time": "3:35:32", "remaining_time": "3:07:49"}
+{"current_steps": 1830, "total_steps": 3406, "loss": 0.8129, "learning_rate": 8.831690999803101e-06, "epoch": 0.5372279916333346, "percentage": 53.73, "elapsed_time": "3:36:40", "remaining_time": "3:06:35"}
+{"current_steps": 1840, "total_steps": 3406, "loss": 0.6732, "learning_rate": 8.740133952485515e-06, "epoch": 0.5401636637187626, "percentage": 54.02, "elapsed_time": "3:37:47", "remaining_time": "3:05:21"}
+{"current_steps": 1850, "total_steps": 3406, "loss": 0.6872, "learning_rate": 8.648684095904001e-06, "epoch": 0.5430993358041907, "percentage": 54.32, "elapsed_time": "3:38:57", "remaining_time": "3:04:10"}
+{"current_steps": 1860, "total_steps": 3406, "loss": 0.6686, "learning_rate": 8.557349210709098e-06, "epoch": 0.5460350078896188, "percentage": 54.61, "elapsed_time": "3:40:12", "remaining_time": "3:03:02"}
+{"current_steps": 1870, "total_steps": 3406, "loss": 0.6853, "learning_rate": 8.46613706776945e-06, "epoch": 0.5489706799750468, "percentage": 54.9, "elapsed_time": "3:41:23", "remaining_time": "3:01:50"}
+{"current_steps": 1880, "total_steps": 3406, "loss": 0.6923, "learning_rate": 8.375055427510673e-06, "epoch": 0.5519063520604749, "percentage": 55.2, "elapsed_time": "3:42:33", "remaining_time": "3:00:39"}
+{"current_steps": 1890, "total_steps": 3406, "loss": 0.6744, "learning_rate": 8.284112039255071e-06, "epoch": 0.5548420241459029, "percentage": 55.49, "elapsed_time": "3:43:43", "remaining_time": "2:59:27"}
+{"current_steps": 1900, "total_steps": 3406, "loss": 0.627, "learning_rate": 8.193314640562315e-06, "epoch": 0.557777696231331, "percentage": 55.78, "elapsed_time": "3:44:55", "remaining_time": "2:58:16"}
+{"current_steps": 1910, "total_steps": 3406, "loss": 0.6627, "learning_rate": 8.102670956571139e-06, "epoch": 0.560713368316759, "percentage": 56.08, "elapsed_time": "3:46:01", "remaining_time": "2:57:02"}
+{"current_steps": 1920, "total_steps": 3406, "loss": 0.6476, "learning_rate": 8.012188699342072e-06, "epoch": 0.5636490404021871, "percentage": 56.37, "elapsed_time": "3:47:11", "remaining_time": "2:55:49"}
+{"current_steps": 1930, "total_steps": 3406, "loss": 0.6968, "learning_rate": 7.92187556720126e-06, "epoch": 0.5665847124876151, "percentage": 56.66, "elapsed_time": "3:48:23", "remaining_time": "2:54:40"}
+{"current_steps": 1940, "total_steps": 3406, "loss": 0.6811, "learning_rate": 7.831739244085534e-06, "epoch": 0.5695203845730432, "percentage": 56.96, "elapsed_time": "3:49:41", "remaining_time": "2:53:34"}
+{"current_steps": 1950, "total_steps": 3406, "loss": 0.6501, "learning_rate": 7.741787398888617e-06, "epoch": 0.5724560566584712, "percentage": 57.25, "elapsed_time": "3:50:45", "remaining_time": "2:52:18"}
+{"current_steps": 1960, "total_steps": 3406, "loss": 0.6496, "learning_rate": 7.652027684808644e-06, "epoch": 0.5753917287438993, "percentage": 57.55, "elapsed_time": "3:51:57", "remaining_time": "2:51:07"}
+{"current_steps": 1970, "total_steps": 3406, "loss": 0.659, "learning_rate": 7.56246773869705e-06, "epoch": 0.5783274008293273, "percentage": 57.84, "elapsed_time": "3:53:12", "remaining_time": "2:49:59"}
+{"current_steps": 1980, "total_steps": 3406, "loss": 0.6429, "learning_rate": 7.47311518040879e-06, "epoch": 0.5812630729147554, "percentage": 58.13, "elapsed_time": "3:54:19", "remaining_time": "2:48:45"}
+{"current_steps": 1990, "total_steps": 3406, "loss": 0.6845, "learning_rate": 7.3839776121540385e-06, "epoch": 0.5841987450001834, "percentage": 58.43, "elapsed_time": "3:55:32", "remaining_time": "2:47:36"}
+{"current_steps": 2000, "total_steps": 3406, "loss": 0.6536, "learning_rate": 7.2950626178514e-06, "epoch": 0.5871344170856115, "percentage": 58.72, "elapsed_time": "3:56:45", "remaining_time": "2:46:26"}
+{"current_steps": 2010, "total_steps": 3406, "loss": 0.6691, "learning_rate": 7.215235676567183e-06, "epoch": 0.5900700891710396, "percentage": 59.01, "elapsed_time": "3:57:55", "remaining_time": "2:45:14"}
+{"current_steps": 2020, "total_steps": 3406, "loss": 0.6483, "learning_rate": 7.126764398128368e-06, "epoch": 0.5930057612564676, "percentage": 59.31, "elapsed_time": "3:59:08", "remaining_time": "2:44:05"}
+{"current_steps": 2030, "total_steps": 3406, "loss": 0.5965, "learning_rate": 7.038537577614009e-06, "epoch": 0.5959414333418958, "percentage": 59.6, "elapsed_time": "4:00:26", "remaining_time": "2:42:58"}
+{"current_steps": 2040, "total_steps": 3406, "loss": 0.5782, "learning_rate": 6.950562721455325e-06, "epoch": 0.5988771054273238, "percentage": 59.89, "elapsed_time": "4:01:32", "remaining_time": "2:41:44"}
+{"current_steps": 2050, "total_steps": 3406, "loss": 0.6419, "learning_rate": 6.86284731464614e-06, "epoch": 0.6018127775127519, "percentage": 60.19, "elapsed_time": "4:02:47", "remaining_time": "2:40:35"}
+{"current_steps": 2060, "total_steps": 3406, "loss": 0.5942, "learning_rate": 6.775398820106065e-06, "epoch": 0.6047484495981799, "percentage": 60.48, "elapsed_time": "4:03:57", "remaining_time": "2:39:23"}
+{"current_steps": 2070, "total_steps": 3406, "loss": 0.5874, "learning_rate": 6.688224678045507e-06, "epoch": 0.607684121683608, "percentage": 60.78, "elapsed_time": "4:05:02", "remaining_time": "2:38:09"}
+{"current_steps": 2080, "total_steps": 3406, "loss": 0.6178, "learning_rate": 6.6013323053327065e-06, "epoch": 0.610619793769036, "percentage": 61.07, "elapsed_time": "4:06:13", "remaining_time": "2:36:57"}
+{"current_steps": 2090, "total_steps": 3406, "loss": 0.5972, "learning_rate": 6.5147290948626365e-06, "epoch": 0.6135554658544641, "percentage": 61.36, "elapsed_time": "4:07:20", "remaining_time": "2:35:44"}
+{"current_steps": 2100, "total_steps": 3406, "loss": 0.5808, "learning_rate": 6.428422414928066e-06, "epoch": 0.6164911379398921, "percentage": 61.66, "elapsed_time": "4:08:31", "remaining_time": "2:34:33"}
+{"current_steps": 2110, "total_steps": 3406, "loss": 0.6407, "learning_rate": 6.342419608592626e-06, "epoch": 0.6194268100253202, "percentage": 61.95, "elapsed_time": "4:09:39", "remaining_time": "2:33:20"}
+{"current_steps": 2120, "total_steps": 3406, "loss": 0.5792, "learning_rate": 6.25672799306605e-06, "epoch": 0.6223624821107482, "percentage": 62.24, "elapsed_time": "4:10:50", "remaining_time": "2:32:09"}
+{"current_steps": 2130, "total_steps": 3406, "loss": 0.7062, "learning_rate": 6.171354859081639e-06, "epoch": 0.6252981541961763, "percentage": 62.54, "elapsed_time": "4:12:01", "remaining_time": "2:30:58"}
+{"current_steps": 2140, "total_steps": 3406, "loss": 0.6015, "learning_rate": 6.086307470275947e-06, "epoch": 0.6282338262816043, "percentage": 62.83, "elapsed_time": "4:13:10", "remaining_time": "2:29:46"}
+{"current_steps": 2150, "total_steps": 3406, "loss": 0.699, "learning_rate": 6.001593062570776e-06, "epoch": 0.6311694983670324, "percentage": 63.12, "elapsed_time": "4:14:19", "remaining_time": "2:28:34"}
+{"current_steps": 2160, "total_steps": 3406, "loss": 0.5912, "learning_rate": 5.917218843557551e-06, "epoch": 0.6341051704524605, "percentage": 63.42, "elapsed_time": "4:15:32", "remaining_time": "2:27:24"}
+{"current_steps": 2170, "total_steps": 3406, "loss": 0.6029, "learning_rate": 5.8415788415375744e-06, "epoch": 0.6370408425378885, "percentage": 63.71, "elapsed_time": "4:16:46", "remaining_time": "2:26:15"}
+{"current_steps": 2180, "total_steps": 3406, "loss": 0.6054, "learning_rate": 5.757870733799642e-06, "epoch": 0.6399765146233166, "percentage": 64.0, "elapsed_time": "4:17:55", "remaining_time": "2:25:02"}
+{"current_steps": 2190, "total_steps": 3406, "loss": 0.5703, "learning_rate": 5.6745235509072135e-06, "epoch": 0.6429121867087446, "percentage": 64.3, "elapsed_time": "4:19:02", "remaining_time": "2:23:50"}
+{"current_steps": 2200, "total_steps": 3406, "loss": 0.6101, "learning_rate": 5.591544384126769e-06, "epoch": 0.6458478587941727, "percentage": 64.59, "elapsed_time": "4:20:09", "remaining_time": "2:22:36"}
+{"current_steps": 2210, "total_steps": 3406, "loss": 0.6131, "learning_rate": 5.508940293413603e-06, "epoch": 0.6487835308796007, "percentage": 64.89, "elapsed_time": "4:21:13", "remaining_time": "2:21:22"}
+{"current_steps": 2220, "total_steps": 3406, "loss": 0.5761, "learning_rate": 5.426718306811134e-06, "epoch": 0.6517192029650288, "percentage": 65.18, "elapsed_time": "4:22:19", "remaining_time": "2:20:08"}
+{"current_steps": 2230, "total_steps": 3406, "loss": 0.6456, "learning_rate": 5.344885419852961e-06, "epoch": 0.6546548750504568, "percentage": 65.47, "elapsed_time": "4:23:37", "remaining_time": "2:19:01"}
+{"current_steps": 2240, "total_steps": 3406, "loss": 0.657, "learning_rate": 5.263448594967673e-06, "epoch": 0.6575905471358849, "percentage": 65.77, "elapsed_time": "4:24:47", "remaining_time": "2:17:50"}
+{"current_steps": 2250, "total_steps": 3406, "loss": 0.6083, "learning_rate": 5.182414760886484e-06, "epoch": 0.6605262192213129, "percentage": 66.06, "elapsed_time": "4:25:55", "remaining_time": "2:16:37"}
+{"current_steps": 2260, "total_steps": 3406, "loss": 0.5721, "learning_rate": 5.1017908120537105e-06, "epoch": 0.663461891306741, "percentage": 66.35, "elapsed_time": "4:27:03", "remaining_time": "2:15:25"}
+{"current_steps": 2270, "total_steps": 3406, "loss": 0.5952, "learning_rate": 5.021583608040208e-06, "epoch": 0.666397563392169, "percentage": 66.65, "elapsed_time": "4:28:18", "remaining_time": "2:14:16"}
+{"current_steps": 2280, "total_steps": 3406, "loss": 0.5074, "learning_rate": 4.941799972959752e-06, "epoch": 0.6693332354775972, "percentage": 66.94, "elapsed_time": "4:29:29", "remaining_time": "2:13:05"}
+{"current_steps": 2290, "total_steps": 3406, "loss": 0.5274, "learning_rate": 4.862446694888403e-06, "epoch": 0.6722689075630253, "percentage": 67.23, "elapsed_time": "4:30:42", "remaining_time": "2:11:55"}
+{"current_steps": 2300, "total_steps": 3406, "loss": 0.5694, "learning_rate": 4.783530525287006e-06, "epoch": 0.6752045796484533, "percentage": 67.53, "elapsed_time": "4:31:50", "remaining_time": "2:10:43"}
+{"current_steps": 2310, "total_steps": 3406, "loss": 0.55, "learning_rate": 4.705058178426753e-06, "epoch": 0.6781402517338814, "percentage": 67.82, "elapsed_time": "4:32:59", "remaining_time": "2:09:31"}
+{"current_steps": 2320, "total_steps": 3406, "loss": 0.5432, "learning_rate": 4.627036330817926e-06, "epoch": 0.6810759238193094, "percentage": 68.12, "elapsed_time": "4:34:09", "remaining_time": "2:08:19"}
+{"current_steps": 2330, "total_steps": 3406, "loss": 0.5332, "learning_rate": 4.5494716206418555e-06, "epoch": 0.6840115959047375, "percentage": 68.41, "elapsed_time": "4:35:19", "remaining_time": "2:07:08"}
+{"current_steps": 2340, "total_steps": 3406, "loss": 0.5744, "learning_rate": 4.4723706471861385e-06, "epoch": 0.6869472679901655, "percentage": 68.7, "elapsed_time": "4:36:30", "remaining_time": "2:05:57"}
+{"current_steps": 2350, "total_steps": 3406, "loss": 0.5314, "learning_rate": 4.3957399702831505e-06, "epoch": 0.6898829400755936, "percentage": 69.0, "elapsed_time": "4:37:39", "remaining_time": "2:04:46"}
+{"current_steps": 2360, "total_steps": 3406, "loss": 0.554, "learning_rate": 4.31958610975195e-06, "epoch": 0.6928186121610216, "percentage": 69.29, "elapsed_time": "4:38:53", "remaining_time": "2:03:36"}
+{"current_steps": 2370, "total_steps": 3406, "loss": 0.4857, "learning_rate": 4.243915544843549e-06, "epoch": 0.6957542842464497, "percentage": 69.58, "elapsed_time": "4:40:07", "remaining_time": "2:02:27"}
+{"current_steps": 2380, "total_steps": 3406, "loss": 0.5484, "learning_rate": 4.168734713689658e-06, "epoch": 0.6986899563318777, "percentage": 69.88, "elapsed_time": "4:41:14", "remaining_time": "2:01:14"}
+{"current_steps": 2390, "total_steps": 3406, "loss": 0.4888, "learning_rate": 4.094050012754925e-06, "epoch": 0.7016256284173058, "percentage": 70.17, "elapsed_time": "4:42:25", "remaining_time": "2:00:03"}
+{"current_steps": 2400, "total_steps": 3406, "loss": 0.5125, "learning_rate": 4.019867796292709e-06, "epoch": 0.7045613005027338, "percentage": 70.46, "elapsed_time": "4:43:30", "remaining_time": "1:58:50"}
+{"current_steps": 2410, "total_steps": 3406, "loss": 0.5262, "learning_rate": 3.946194375804452e-06, "epoch": 0.7074969725881619, "percentage": 70.76, "elapsed_time": "4:44:43", "remaining_time": "1:57:40"}
+{"current_steps": 2420, "total_steps": 3406, "loss": 0.5581, "learning_rate": 3.873036019502716e-06, "epoch": 0.7104326446735899, "percentage": 71.05, "elapsed_time": "4:45:52", "remaining_time": "1:56:28"}
+{"current_steps": 2430, "total_steps": 3406, "loss": 0.5687, "learning_rate": 3.800398951777845e-06, "epoch": 0.713368316759018, "percentage": 71.34, "elapsed_time": "4:47:02", "remaining_time": "1:55:17"}
+{"current_steps": 2440, "total_steps": 3406, "loss": 0.5136, "learning_rate": 3.7282893526683914e-06, "epoch": 0.7163039888444461, "percentage": 71.64, "elapsed_time": "4:48:12", "remaining_time": "1:54:06"}
+{"current_steps": 2450, "total_steps": 3406, "loss": 0.5358, "learning_rate": 3.656713357335334e-06, "epoch": 0.7192396609298741, "percentage": 71.93, "elapsed_time": "4:49:27", "remaining_time": "1:52:56"}
+{"current_steps": 2460, "total_steps": 3406, "loss": 0.5214, "learning_rate": 3.585677055540072e-06, "epoch": 0.7221753330153022, "percentage": 72.23, "elapsed_time": "4:50:41", "remaining_time": "1:51:47"}
+{"current_steps": 2470, "total_steps": 3406, "loss": 0.5048, "learning_rate": 3.5151864911263066e-06, "epoch": 0.7251110051007302, "percentage": 72.52, "elapsed_time": "4:51:57", "remaining_time": "1:50:38"}
+{"current_steps": 2480, "total_steps": 3406, "loss": 0.509, "learning_rate": 3.4452476615058316e-06, "epoch": 0.7280466771861583, "percentage": 72.81, "elapsed_time": "4:53:18", "remaining_time": "1:49:31"}
+{"current_steps": 2490, "total_steps": 3406, "loss": 0.5361, "learning_rate": 3.3758665171482474e-06, "epoch": 0.7309823492715863, "percentage": 73.11, "elapsed_time": "4:54:34", "remaining_time": "1:48:21"}
+{"current_steps": 2500, "total_steps": 3406, "loss": 0.5033, "learning_rate": 3.3070489610747146e-06, "epoch": 0.7339180213570144, "percentage": 73.4, "elapsed_time": "4:55:50", "remaining_time": "1:47:12"}
+{"current_steps": 2510, "total_steps": 3406, "loss": 0.526, "learning_rate": 3.238800848355702e-06, "epoch": 0.7368536934424424, "percentage": 73.69, "elapsed_time": "4:56:59", "remaining_time": "1:46:01"}
+{"current_steps": 2520, "total_steps": 3406, "loss": 0.5014, "learning_rate": 3.1711279856128387e-06, "epoch": 0.7397893655278706, "percentage": 73.99, "elapsed_time": "4:58:04", "remaining_time": "1:44:48"}
+{"current_steps": 2530, "total_steps": 3406, "loss": 0.4514, "learning_rate": 3.10403613052487e-06, "epoch": 0.7427250376132986, "percentage": 74.28, "elapsed_time": "4:59:16", "remaining_time": "1:43:37"}
+{"current_steps": 2540, "total_steps": 3406, "loss": 0.5645, "learning_rate": 3.037530991337807e-06, "epoch": 0.7456607096987267, "percentage": 74.57, "elapsed_time": "5:00:28", "remaining_time": "1:42:26"}
+{"current_steps": 2550, "total_steps": 3406, "loss": 0.5026, "learning_rate": 2.9716182263792314e-06, "epoch": 0.7485963817841547, "percentage": 74.87, "elapsed_time": "5:01:31", "remaining_time": "1:41:13"}
+{"current_steps": 2560, "total_steps": 3406, "loss": 0.5318, "learning_rate": 2.9063034435769242e-06, "epoch": 0.7515320538695828, "percentage": 75.16, "elapsed_time": "5:02:44", "remaining_time": "1:40:02"}
+{"current_steps": 2570, "total_steps": 3406, "loss": 0.5106, "learning_rate": 2.8415921999816966e-06, "epoch": 0.7544677259550108, "percentage": 75.46, "elapsed_time": "5:03:57", "remaining_time": "1:38:52"}
+{"current_steps": 2580, "total_steps": 3406, "loss": 0.5299, "learning_rate": 2.7774900012946037e-06, "epoch": 0.7574033980404389, "percentage": 75.75, "elapsed_time": "5:05:10", "remaining_time": "1:37:42"}
+{"current_steps": 2590, "total_steps": 3406, "loss": 0.5211, "learning_rate": 2.714002301398524e-06, "epoch": 0.760339070125867, "percentage": 76.04, "elapsed_time": "5:06:18", "remaining_time": "1:36:30"}
+{"current_steps": 2600, "total_steps": 3406, "loss": 0.5071, "learning_rate": 2.6511345018941225e-06, "epoch": 0.763274742211295, "percentage": 76.34, "elapsed_time": "5:07:28", "remaining_time": "1:35:19"}
+{"current_steps": 2610, "total_steps": 3406, "loss": 0.5199, "learning_rate": 2.588891951640288e-06, "epoch": 0.7662104142967231, "percentage": 76.63, "elapsed_time": "5:08:38", "remaining_time": "1:34:07"}
+{"current_steps": 2620, "total_steps": 3406, "loss": 0.4537, "learning_rate": 2.527279946299037e-06, "epoch": 0.7691460863821511, "percentage": 76.92, "elapsed_time": "5:09:47", "remaining_time": "1:32:56"}
+{"current_steps": 2630, "total_steps": 3406, "loss": 0.4993, "learning_rate": 2.4663037278849665e-06, "epoch": 0.7720817584675792, "percentage": 77.22, "elapsed_time": "5:10:58", "remaining_time": "1:31:45"}
+{"current_steps": 2640, "total_steps": 3406, "loss": 0.4596, "learning_rate": 2.405968484319231e-06, "epoch": 0.7750174305530072, "percentage": 77.51, "elapsed_time": "5:12:08", "remaining_time": "1:30:34"}
+{"current_steps": 2650, "total_steps": 3406, "loss": 0.5141, "learning_rate": 2.3462793489881884e-06, "epoch": 0.7779531026384353, "percentage": 77.8, "elapsed_time": "5:13:22", "remaining_time": "1:29:23"}
+{"current_steps": 2660, "total_steps": 3406, "loss": 0.4483, "learning_rate": 2.2872414003066146e-06, "epoch": 0.7808887747238633, "percentage": 78.1, "elapsed_time": "5:14:32", "remaining_time": "1:28:12"}
+{"current_steps": 2670, "total_steps": 3406, "loss": 0.4834, "learning_rate": 2.2288596612856306e-06, "epoch": 0.7838244468092914, "percentage": 78.39, "elapsed_time": "5:15:46", "remaining_time": "1:27:02"}
+{"current_steps": 2680, "total_steps": 3406, "loss": 0.4913, "learning_rate": 2.1711390991053547e-06, "epoch": 0.7867601188947194, "percentage": 78.68, "elapsed_time": "5:16:57", "remaining_time": "1:25:51"}
+{"current_steps": 2690, "total_steps": 3406, "loss": 0.4748, "learning_rate": 2.1140846246922774e-06, "epoch": 0.7896957909801475, "percentage": 78.98, "elapsed_time": "5:18:09", "remaining_time": "1:24:41"}
+{"current_steps": 2700, "total_steps": 3406, "loss": 0.5014, "learning_rate": 2.0577010923014353e-06, "epoch": 0.7926314630655755, "percentage": 79.27, "elapsed_time": "5:19:21", "remaining_time": "1:23:30"}
+{"current_steps": 2710, "total_steps": 3406, "loss": 0.4524, "learning_rate": 2.001993299103411e-06, "epoch": 0.7955671351510036, "percentage": 79.57, "elapsed_time": "5:20:32", "remaining_time": "1:22:19"}
+{"current_steps": 2720, "total_steps": 3406, "loss": 0.486, "learning_rate": 1.946965984776181e-06, "epoch": 0.7985028072364317, "percentage": 79.86, "elapsed_time": "5:21:45", "remaining_time": "1:21:08"}
+{"current_steps": 2730, "total_steps": 3406, "loss": 0.4112, "learning_rate": 1.8926238311018551e-06, "epoch": 0.8014384793218597, "percentage": 80.15, "elapsed_time": "5:23:04", "remaining_time": "1:20:00"}
+{"current_steps": 2740, "total_steps": 3406, "loss": 0.4758, "learning_rate": 1.8443055276768218e-06, "epoch": 0.8043741514072879, "percentage": 80.45, "elapsed_time": "5:24:20", "remaining_time": "1:18:50"}
+{"current_steps": 2750, "total_steps": 3406, "loss": 0.4209, "learning_rate": 1.7912778684550137e-06, "epoch": 0.8073098234927159, "percentage": 80.74, "elapsed_time": "5:25:30", "remaining_time": "1:17:38"}
+{"current_steps": 2760, "total_steps": 3406, "loss": 0.4913, "learning_rate": 1.7389486159957436e-06, "epoch": 0.810245495578144, "percentage": 81.03, "elapsed_time": "5:26:41", "remaining_time": "1:16:27"}
+{"current_steps": 2770, "total_steps": 3406, "loss": 0.4523, "learning_rate": 1.6873222225271656e-06, "epoch": 0.813181167663572, "percentage": 81.33, "elapsed_time": "5:27:49", "remaining_time": "1:15:16"}
+{"current_steps": 2780, "total_steps": 3406, "loss": 0.4545, "learning_rate": 1.63640308047745e-06, "epoch": 0.8161168397490001, "percentage": 81.62, "elapsed_time": "5:29:03", "remaining_time": "1:14:05"}
+{"current_steps": 2790, "total_steps": 3406, "loss": 0.5272, "learning_rate": 1.5861955221010671e-06, "epoch": 0.8190525118344281, "percentage": 81.91, "elapsed_time": "5:30:19", "remaining_time": "1:12:55"}
+{"current_steps": 2800, "total_steps": 3406, "loss": 0.4166, "learning_rate": 1.536703819110198e-06, "epoch": 0.8219881839198562, "percentage": 82.21, "elapsed_time": "5:31:29", "remaining_time": "1:11:44"}
+{"current_steps": 2810, "total_steps": 3406, "loss": 0.5194, "learning_rate": 1.4879321823112802e-06, "epoch": 0.8249238560052842, "percentage": 82.5, "elapsed_time": "5:32:39", "remaining_time": "1:10:33"}
+{"current_steps": 2820, "total_steps": 3406, "loss": 0.4626, "learning_rate": 1.4398847612467736e-06, "epoch": 0.8278595280907123, "percentage": 82.8, "elapsed_time": "5:33:45", "remaining_time": "1:09:21"}
+{"current_steps": 2830, "total_steps": 3406, "loss": 0.4246, "learning_rate": 1.3925656438420876e-06, "epoch": 0.8307952001761403, "percentage": 83.09, "elapsed_time": "5:34:50", "remaining_time": "1:08:09"}
+{"current_steps": 2840, "total_steps": 3406, "loss": 0.431, "learning_rate": 1.3459788560577847e-06, "epoch": 0.8337308722615684, "percentage": 83.38, "elapsed_time": "5:35:58", "remaining_time": "1:06:57"}
+{"current_steps": 2850, "total_steps": 3406, "loss": 0.4478, "learning_rate": 1.3001283615470517e-06, "epoch": 0.8366665443469964, "percentage": 83.68, "elapsed_time": "5:37:08", "remaining_time": "1:05:46"}
+{"current_steps": 2860, "total_steps": 3406, "loss": 0.4432, "learning_rate": 1.255018061318467e-06, "epoch": 0.8396022164324245, "percentage": 83.97, "elapsed_time": "5:38:17", "remaining_time": "1:04:34"}
+{"current_steps": 2870, "total_steps": 3406, "loss": 0.4598, "learning_rate": 1.2106517934040917e-06, "epoch": 0.8425378885178526, "percentage": 84.26, "elapsed_time": "5:39:22", "remaining_time": "1:03:22"}
+{"current_steps": 2880, "total_steps": 3406, "loss": 0.4908, "learning_rate": 1.1670333325329353e-06, "epoch": 0.8454735606032806, "percentage": 84.56, "elapsed_time": "5:40:34", "remaining_time": "1:02:12"}
+{"current_steps": 2890, "total_steps": 3406, "loss": 0.4239, "learning_rate": 1.1241663898097865e-06, "epoch": 0.8484092326887087, "percentage": 84.85, "elapsed_time": "5:41:42", "remaining_time": "1:01:00"}
+{"current_steps": 2900, "total_steps": 3406, "loss": 0.4636, "learning_rate": 1.08205461239948e-06, "epoch": 0.8513449047741367, "percentage": 85.14, "elapsed_time": "5:43:00", "remaining_time": "0:59:50"}
+{"current_steps": 2910, "total_steps": 3406, "loss": 0.4595, "learning_rate": 1.04070158321659e-06, "epoch": 0.8542805768595648, "percentage": 85.44, "elapsed_time": "5:44:13", "remaining_time": "0:58:40"}
+{"current_steps": 2920, "total_steps": 3406, "loss": 0.4699, "learning_rate": 1.00011082062058e-06, "epoch": 0.8572162489449928, "percentage": 85.73, "elapsed_time": "5:45:29", "remaining_time": "0:57:30"}
+{"current_steps": 2930, "total_steps": 3406, "loss": 0.4599, "learning_rate": 9.602857781164721e-07, "epoch": 0.8601519210304209, "percentage": 86.02, "elapsed_time": "5:46:43", "remaining_time": "0:56:19"}
+{"current_steps": 2940, "total_steps": 3406, "loss": 0.4601, "learning_rate": 9.212298440610101e-07, "epoch": 0.8630875931158489, "percentage": 86.32, "elapsed_time": "5:47:54", "remaining_time": "0:55:08"}
+{"current_steps": 2950, "total_steps": 3406, "loss": 0.453, "learning_rate": 8.829463413743811e-07, "epoch": 0.866023265201277, "percentage": 86.61, "elapsed_time": "5:49:05", "remaining_time": "0:53:57"}
+{"current_steps": 2960, "total_steps": 3406, "loss": 0.4298, "learning_rate": 8.454385272574906e-07, "epoch": 0.868958937286705, "percentage": 86.91, "elapsed_time": "5:50:14", "remaining_time": "0:52:46"}
+{"current_steps": 2970, "total_steps": 3406, "loss": 0.457, "learning_rate": 8.087095929148436e-07, "epoch": 0.8718946093721331, "percentage": 87.2, "elapsed_time": "5:51:19", "remaining_time": "0:51:34"}
+{"current_steps": 2980, "total_steps": 3406, "loss": 0.4194, "learning_rate": 7.727626632830221e-07, "epoch": 0.8748302814575611, "percentage": 87.49, "elapsed_time": "5:52:32", "remaining_time": "0:50:23"}
+{"current_steps": 2990, "total_steps": 3406, "loss": 0.4457, "learning_rate": 7.376007967648302e-07, "epoch": 0.8777659535429893, "percentage": 87.79, "elapsed_time": "5:53:45", "remaining_time": "0:49:13"}
+{"current_steps": 3000, "total_steps": 3406, "loss": 0.4532, "learning_rate": 7.032269849690654e-07, "epoch": 0.8807016256284173, "percentage": 88.08, "elapsed_time": "5:54:57", "remaining_time": "0:48:02"}
+{"current_steps": 3010, "total_steps": 3406, "loss": 0.4772, "learning_rate": 6.696441524559983e-07, "epoch": 0.8836372977138454, "percentage": 88.37, "elapsed_time": "5:56:11", "remaining_time": "0:46:51"}
+{"current_steps": 3020, "total_steps": 3406, "loss": 0.4239, "learning_rate": 6.368551564885439e-07, "epoch": 0.8865729697992735, "percentage": 88.67, "elapsed_time": "5:57:24", "remaining_time": "0:45:40"}
+{"current_steps": 3030, "total_steps": 3406, "loss": 0.4564, "learning_rate": 6.048627867891665e-07, "epoch": 0.8895086418847015, "percentage": 88.96, "elapsed_time": "5:58:40", "remaining_time": "0:44:30"}
+{"current_steps": 3040, "total_steps": 3406, "loss": 0.4206, "learning_rate": 5.736697653025192e-07, "epoch": 0.8924443139701296, "percentage": 89.25, "elapsed_time": "5:59:48", "remaining_time": "0:43:19"}
+{"current_steps": 3050, "total_steps": 3406, "loss": 0.4751, "learning_rate": 5.432787459638722e-07, "epoch": 0.8953799860555576, "percentage": 89.55, "elapsed_time": "6:00:58", "remaining_time": "0:42:08"}
+{"current_steps": 3060, "total_steps": 3406, "loss": 0.4273, "learning_rate": 5.136923144732997e-07, "epoch": 0.8983156581409857, "percentage": 89.84, "elapsed_time": "6:02:08", "remaining_time": "0:40:56"}
+{"current_steps": 3070, "total_steps": 3406, "loss": 0.472, "learning_rate": 4.849129880756886e-07, "epoch": 0.9012513302264137, "percentage": 90.14, "elapsed_time": "6:03:19", "remaining_time": "0:39:45"}
+{"current_steps": 3080, "total_steps": 3406, "loss": 0.5233, "learning_rate": 4.569432153465736e-07, "epoch": 0.9041870023118418, "percentage": 90.43, "elapsed_time": "6:04:29", "remaining_time": "0:38:34"}
+{"current_steps": 3090, "total_steps": 3406, "loss": 0.4543, "learning_rate": 4.297853759838055e-07, "epoch": 0.9071226743972698, "percentage": 90.72, "elapsed_time": "6:05:43", "remaining_time": "0:37:24"}
+{"current_steps": 3100, "total_steps": 3406, "loss": 0.4383, "learning_rate": 4.034417806050872e-07, "epoch": 0.9100583464826979, "percentage": 91.02, "elapsed_time": "6:06:57", "remaining_time": "0:36:13"}
+{"current_steps": 3110, "total_steps": 3406, "loss": 0.4644, "learning_rate": 3.779146705513814e-07, "epoch": 0.9129940185681259, "percentage": 91.31, "elapsed_time": "6:08:09", "remaining_time": "0:35:02"}
+{"current_steps": 3120, "total_steps": 3406, "loss": 0.4591, "learning_rate": 3.532062176962159e-07, "epoch": 0.915929690653554, "percentage": 91.6, "elapsed_time": "6:09:27", "remaining_time": "0:33:52"}
+{"current_steps": 3130, "total_steps": 3406, "loss": 0.4354, "learning_rate": 3.293185242608954e-07, "epoch": 0.918865362738982, "percentage": 91.9, "elapsed_time": "6:10:48", "remaining_time": "0:32:41"}
+{"current_steps": 3140, "total_steps": 3406, "loss": 0.4466, "learning_rate": 3.062536226356472e-07, "epoch": 0.9218010348244101, "percentage": 92.19, "elapsed_time": "6:11:57", "remaining_time": "0:31:30"}
+{"current_steps": 3150, "total_steps": 3406, "loss": 0.4629, "learning_rate": 2.8401347520670253e-07, "epoch": 0.9247367069098382, "percentage": 92.48, "elapsed_time": "6:13:11", "remaining_time": "0:30:19"}
+{"current_steps": 3160, "total_steps": 3406, "loss": 0.5156, "learning_rate": 2.625999741893304e-07, "epoch": 0.9276723789952662, "percentage": 92.78, "elapsed_time": "6:14:33", "remaining_time": "0:29:09"}
+{"current_steps": 3170, "total_steps": 3406, "loss": 0.42, "learning_rate": 2.420149414668493e-07, "epoch": 0.9306080510806943, "percentage": 93.07, "elapsed_time": "6:15:48", "remaining_time": "0:27:58"}
+{"current_steps": 3180, "total_steps": 3406, "loss": 0.4408, "learning_rate": 2.222601284356185e-07, "epoch": 0.9335437231661223, "percentage": 93.36, "elapsed_time": "6:17:01", "remaining_time": "0:26:47"}
+{"current_steps": 3190, "total_steps": 3406, "loss": 0.4558, "learning_rate": 2.0333721585602984e-07, "epoch": 0.9364793952515504, "percentage": 93.66, "elapsed_time": "6:18:11", "remaining_time": "0:25:36"}
+{"current_steps": 3200, "total_steps": 3406, "loss": 0.4475, "learning_rate": 1.8524781370950262e-07, "epoch": 0.9394150673369784, "percentage": 93.95, "elapsed_time": "6:19:22", "remaining_time": "0:24:25"}
+{"current_steps": 3210, "total_steps": 3406, "loss": 0.4351, "learning_rate": 1.679934610615064e-07, "epoch": 0.9423507394224065, "percentage": 94.25, "elapsed_time": "6:20:36", "remaining_time": "0:23:14"}
+{"current_steps": 3220, "total_steps": 3406, "loss": 0.4431, "learning_rate": 1.515756259306178e-07, "epoch": 0.9452864115078345, "percentage": 94.54, "elapsed_time": "6:21:50", "remaining_time": "0:22:03"}
+{"current_steps": 3230, "total_steps": 3406, "loss": 0.4256, "learning_rate": 1.3599570516361737e-07, "epoch": 0.9482220835932627, "percentage": 94.83, "elapsed_time": "6:23:10", "remaining_time": "0:20:52"}
+{"current_steps": 3240, "total_steps": 3406, "loss": 0.4811, "learning_rate": 1.212550243166455e-07, "epoch": 0.9511577556786907, "percentage": 95.13, "elapsed_time": "6:24:24", "remaining_time": "0:19:41"}
+{"current_steps": 3250, "total_steps": 3406, "loss": 0.4435, "learning_rate": 1.0735483754242049e-07, "epoch": 0.9540934277641188, "percentage": 95.42, "elapsed_time": "6:25:42", "remaining_time": "0:18:30"}
+{"current_steps": 3260, "total_steps": 3406, "loss": 0.4152, "learning_rate": 9.429632748354068e-08, "epoch": 0.9570290998495468, "percentage": 95.71, "elapsed_time": "6:26:56", "remaining_time": "0:17:19"}
+{"current_steps": 3270, "total_steps": 3406, "loss": 0.4579, "learning_rate": 8.208060517185146e-08, "epoch": 0.9599647719349749, "percentage": 96.01, "elapsed_time": "6:28:04", "remaining_time": "0:16:08"}
+{"current_steps": 3280, "total_steps": 3406, "loss": 0.4531, "learning_rate": 7.070870993393209e-08, "epoch": 0.9629004440204029, "percentage": 96.3, "elapsed_time": "6:29:14", "remaining_time": "0:14:57"}
+{"current_steps": 3290, "total_steps": 3406, "loss": 0.4384, "learning_rate": 6.01816093026586e-08, "epoch": 0.965836116105831, "percentage": 96.59, "elapsed_time": "6:30:26", "remaining_time": "0:13:45"}
+{"current_steps": 3300, "total_steps": 3406, "loss": 0.4028, "learning_rate": 5.0500198934889665e-08, "epoch": 0.9687717881912591, "percentage": 96.89, "elapsed_time": "6:31:31", "remaining_time": "0:12:34"}
+{"current_steps": 3310, "total_steps": 3406, "loss": 0.4894, "learning_rate": 4.16653025352598e-08, "epoch": 0.9717074602766871, "percentage": 97.18, "elapsed_time": "6:32:37", "remaining_time": "0:11:23"}
+{"current_steps": 3320, "total_steps": 3406, "loss": 0.4403, "learning_rate": 3.367767178609982e-08, "epoch": 0.9746431323621152, "percentage": 97.48, "elapsed_time": "6:33:46", "remaining_time": "0:10:12"}
+{"current_steps": 3330, "total_steps": 3406, "loss": 0.4123, "learning_rate": 2.6537986283485805e-08, "epoch": 0.9775788044475432, "percentage": 97.77, "elapsed_time": "6:34:55", "remaining_time": "0:09:00"}
+{"current_steps": 3340, "total_steps": 3406, "loss": 0.4456, "learning_rate": 2.024685347941202e-08, "epoch": 0.9805144765329713, "percentage": 98.06, "elapsed_time": "6:36:03", "remaining_time": "0:07:49"}
+{"current_steps": 3350, "total_steps": 3406, "loss": 0.4383, "learning_rate": 1.4804808630112244e-08, "epoch": 0.9834501486183993, "percentage": 98.36, "elapsed_time": "6:37:14", "remaining_time": "0:06:38"}
+{"current_steps": 3360, "total_steps": 3406, "loss": 0.4368, "learning_rate": 1.0212314750518426e-08, "epoch": 0.9863858207038274, "percentage": 98.65, "elapsed_time": "6:38:22", "remaining_time": "0:05:27"}
+{"current_steps": 3370, "total_steps": 3406, "loss": 0.4769, "learning_rate": 6.469762574868866e-09, "epoch": 0.9893214927892554, "percentage": 98.94, "elapsed_time": "6:39:25", "remaining_time": "0:04:16"}
+{"current_steps": 3380, "total_steps": 3406, "loss": 0.4412, "learning_rate": 3.5774705234625783e-09, "epoch": 0.9922571648746835, "percentage": 99.24, "elapsed_time": "6:40:37", "remaining_time": "0:03:04"}
+{"current_steps": 3390, "total_steps": 3406, "loss": 0.5059, "learning_rate": 1.5356846755654187e-09, "epoch": 0.9951928369601115, "percentage": 99.53, "elapsed_time": "6:41:46", "remaining_time": "0:01:53"}
+{"current_steps": 3400, "total_steps": 3406, "loss": 0.4697, "learning_rate": 3.4457874847793063e-10, "epoch": 0.9981285090455396, "percentage": 99.82, "elapsed_time": "6:43:05", "remaining_time": "0:00:42"}
+{"current_steps": 3406, "total_steps": 3406, "epoch": 0.9998899122967965, "percentage": 100.0, "elapsed_time": "6:43:48", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2422 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9998899122967965,
+  "eval_steps": 500,
+  "global_step": 3406,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0029356720854280577,
+      "grad_norm": 2.3989222049713135,
+      "learning_rate": 1.9999583060217186e-05,
+      "loss": 1.4046,
+      "step": 10
+    },
+    {
+      "epoch": 0.005871344170856115,
+      "grad_norm": 2.4013407230377197,
+      "learning_rate": 1.9998315387870395e-05,
+      "loss": 1.2805,
+      "step": 20
+    },
+    {
+      "epoch": 0.008807016256284174,
+      "grad_norm": 2.5987584590911865,
+      "learning_rate": 1.9996197048273697e-05,
+      "loss": 1.2627,
+      "step": 30
+    },
+    {
+      "epoch": 0.01174268834171223,
+      "grad_norm": 2.5626957416534424,
+      "learning_rate": 1.999322822165767e-05,
+      "loss": 1.34,
+      "step": 40
+    },
+    {
+      "epoch": 0.014678360427140288,
+      "grad_norm": 2.4768199920654297,
+      "learning_rate": 1.998940916061322e-05,
+      "loss": 1.2963,
+      "step": 50
+    },
+    {
+      "epoch": 0.017614032512568347,
+      "grad_norm": 2.1327669620513916,
+      "learning_rate": 1.9984740190070102e-05,
+      "loss": 1.3513,
+      "step": 60
+    },
+    {
+      "epoch": 0.020549704597996404,
+      "grad_norm": 2.7165908813476562,
+      "learning_rate": 1.9979221707269273e-05,
+      "loss": 1.2629,
+      "step": 70
+    },
+    {
+      "epoch": 0.02348537668342446,
+      "grad_norm": 2.5773496627807617,
+      "learning_rate": 1.997285418172908e-05,
+      "loss": 1.2504,
+      "step": 80
+    },
+    {
+      "epoch": 0.02642104876885252,
+      "grad_norm": 2.7524304389953613,
+      "learning_rate": 1.9965638155205335e-05,
+      "loss": 1.2854,
+      "step": 90
+    },
+    {
+      "epoch": 0.029356720854280576,
+      "grad_norm": 2.542572498321533,
+      "learning_rate": 1.995757424164521e-05,
+      "loss": 1.2583,
+      "step": 100
+    },
+    {
+      "epoch": 0.03229239293970863,
+      "grad_norm": 3.595125198364258,
+      "learning_rate": 1.9948663127135003e-05,
+      "loss": 1.2612,
+      "step": 110
+    },
+    {
+      "epoch": 0.035228065025136694,
+      "grad_norm": 2.8669538497924805,
+      "learning_rate": 1.9938905569841754e-05,
+      "loss": 1.237,
+      "step": 120
+    },
+    {
+      "epoch": 0.03816373711056475,
+      "grad_norm": 3.1492984294891357,
+      "learning_rate": 1.9928302399948767e-05,
+      "loss": 1.2394,
+      "step": 130
+    },
+    {
+      "epoch": 0.04109940919599281,
+      "grad_norm": 3.0048630237579346,
+      "learning_rate": 1.991685451958495e-05,
+      "loss": 1.1899,
+      "step": 140
+    },
+    {
+      "epoch": 0.04403508128142086,
+      "grad_norm": 2.9907774925231934,
+      "learning_rate": 1.990456290274808e-05,
+      "loss": 1.1939,
+      "step": 150
+    },
+    {
+      "epoch": 0.04697075336684892,
+      "grad_norm": 3.010820150375366,
+      "learning_rate": 1.9891428595221914e-05,
+      "loss": 1.2212,
+      "step": 160
+    },
+    {
+      "epoch": 0.049906425452276984,
+      "grad_norm": 2.486607551574707,
+      "learning_rate": 1.9877452714487232e-05,
+      "loss": 1.1824,
+      "step": 170
+    },
+    {
+      "epoch": 0.05284209753770504,
+      "grad_norm": 2.491534471511841,
+      "learning_rate": 1.9862636449626752e-05,
+      "loss": 1.2118,
+      "step": 180
+    },
+    {
+      "epoch": 0.0557777696231331,
+      "grad_norm": 2.5148768424987793,
+      "learning_rate": 1.9846981061223958e-05,
+      "loss": 1.2377,
+      "step": 190
+    },
+    {
+      "epoch": 0.05871344170856115,
+      "grad_norm": 2.640007734298706,
+      "learning_rate": 1.9830487881255864e-05,
+      "loss": 1.1995,
+      "step": 200
+    },
+    {
+      "epoch": 0.06164911379398921,
+      "grad_norm": 2.6175191402435303,
+      "learning_rate": 1.981315831297966e-05,
+      "loss": 1.1114,
+      "step": 210
+    },
+    {
+      "epoch": 0.06458478587941727,
+      "grad_norm": 2.8480780124664307,
+      "learning_rate": 1.9794993830813358e-05,
+      "loss": 1.1897,
+      "step": 220
+    },
+    {
+      "epoch": 0.06752045796484532,
+      "grad_norm": 2.635657787322998,
+      "learning_rate": 1.9775995980210306e-05,
+      "loss": 1.1592,
+      "step": 230
+    },
+    {
+      "epoch": 0.07045613005027339,
+      "grad_norm": 2.8263065814971924,
+      "learning_rate": 1.9756166377527734e-05,
+      "loss": 1.1712,
+      "step": 240
+    },
+    {
+      "epoch": 0.07339180213570144,
+      "grad_norm": 3.2777886390686035,
+      "learning_rate": 1.9735506709889213e-05,
+      "loss": 1.1724,
+      "step": 250
+    },
+    {
+      "epoch": 0.0763274742211295,
+      "grad_norm": 2.587409019470215,
+      "learning_rate": 1.9714018735041125e-05,
+      "loss": 1.1767,
+      "step": 260
+    },
+    {
+      "epoch": 0.07926314630655756,
+      "grad_norm": 2.9432199001312256,
+      "learning_rate": 1.9691704281203098e-05,
+      "loss": 1.1553,
+      "step": 270
+    },
+    {
+      "epoch": 0.08219881839198562,
+      "grad_norm": 3.1995699405670166,
+      "learning_rate": 1.966856524691247e-05,
+      "loss": 1.1577,
+      "step": 280
+    },
+    {
+      "epoch": 0.08513449047741367,
+      "grad_norm": 2.805522918701172,
+      "learning_rate": 1.9644603600862753e-05,
+      "loss": 1.1627,
+      "step": 290
+    },
+    {
+      "epoch": 0.08807016256284173,
+      "grad_norm": 2.6327457427978516,
+      "learning_rate": 1.961982138173615e-05,
+      "loss": 1.1483,
+      "step": 300
+    },
+    {
+      "epoch": 0.09100583464826979,
+      "grad_norm": 4.197879314422607,
+      "learning_rate": 1.959422069803007e-05,
+      "loss": 1.2015,
+      "step": 310
+    },
+    {
+      "epoch": 0.09394150673369785,
+      "grad_norm": 3.2353358268737793,
+      "learning_rate": 1.956780372787777e-05,
+      "loss": 1.1068,
+      "step": 320
+    },
+    {
+      "epoch": 0.0968771788191259,
+      "grad_norm": 2.8246076107025146,
+      "learning_rate": 1.9540572718863012e-05,
+      "loss": 1.1424,
+      "step": 330
+    },
+    {
+      "epoch": 0.09981285090455397,
+      "grad_norm": 4.32204532623291,
+      "learning_rate": 1.9512529987828853e-05,
+      "loss": 1.1508,
+      "step": 340
+    },
+    {
+      "epoch": 0.10274852298998202,
+      "grad_norm": 2.8142335414886475,
+      "learning_rate": 1.9483677920680512e-05,
+      "loss": 1.1623,
+      "step": 350
+    },
+    {
+      "epoch": 0.10568419507541008,
+      "grad_norm": 2.9336957931518555,
+      "learning_rate": 1.9454018972182383e-05,
+      "loss": 1.161,
+      "step": 360
+    },
+    {
+      "epoch": 0.10861986716083813,
+      "grad_norm": 2.9903533458709717,
+      "learning_rate": 1.9423555665749182e-05,
+      "loss": 1.1444,
+      "step": 370
+    },
+    {
+      "epoch": 0.1115555392462662,
+      "grad_norm": 2.8897149562835693,
+      "learning_rate": 1.939229059323124e-05,
+      "loss": 1.171,
+      "step": 380
+    },
+    {
+      "epoch": 0.11449121133169425,
+      "grad_norm": 3.222294807434082,
+      "learning_rate": 1.9360226414694008e-05,
+      "loss": 1.1365,
+      "step": 390
+    },
+    {
+      "epoch": 0.1174268834171223,
+      "grad_norm": 2.9000742435455322,
+      "learning_rate": 1.932736585819171e-05,
+      "loss": 1.1342,
+      "step": 400
+    },
+    {
+      "epoch": 0.12036255550255036,
+      "grad_norm": 2.682969093322754,
+      "learning_rate": 1.929371171953526e-05,
+      "loss": 1.0428,
+      "step": 410
+    },
+    {
+      "epoch": 0.12329822758797843,
+      "grad_norm": 2.8611629009246826,
+      "learning_rate": 1.9259266862054366e-05,
+      "loss": 1.1135,
+      "step": 420
+    },
+    {
+      "epoch": 0.12623389967340648,
+      "grad_norm": 2.9910166263580322,
+      "learning_rate": 1.9224034216353947e-05,
+      "loss": 1.1154,
+      "step": 430
+    },
+    {
+      "epoch": 0.12916957175883453,
+      "grad_norm": 3.245227336883545,
+      "learning_rate": 1.9188016780064768e-05,
+      "loss": 1.2029,
+      "step": 440
+    },
+    {
+      "epoch": 0.1321052438442626,
+      "grad_norm": 3.2252321243286133,
+      "learning_rate": 1.9151217617588412e-05,
+      "loss": 1.1272,
+      "step": 450
+    },
+    {
+      "epoch": 0.13504091592969064,
+      "grad_norm": 3.23498272895813,
+      "learning_rate": 1.9113639859836544e-05,
+      "loss": 1.1421,
+      "step": 460
+    },
+    {
+      "epoch": 0.13797658801511872,
+      "grad_norm": 3.0721843242645264,
+      "learning_rate": 1.9075286703964554e-05,
+      "loss": 1.14,
+      "step": 470
+    },
+    {
+      "epoch": 0.14091226010054678,
+      "grad_norm": 3.130610704421997,
+      "learning_rate": 1.9036161413099512e-05,
+      "loss": 1.1699,
+      "step": 480
+    },
+    {
+      "epoch": 0.14384793218597483,
+      "grad_norm": 3.054914712905884,
+      "learning_rate": 1.899626731606255e-05,
+      "loss": 1.0919,
+      "step": 490
+    },
+    {
+      "epoch": 0.14678360427140288,
+      "grad_norm": 3.3167009353637695,
+      "learning_rate": 1.895560780708565e-05,
+      "loss": 1.0625,
+      "step": 500
+    },
+    {
+      "epoch": 0.14971927635683094,
+      "grad_norm": 3.075392484664917,
+      "learning_rate": 1.8914186345522846e-05,
+      "loss": 1.0899,
+      "step": 510
+    },
+    {
+      "epoch": 0.152654948442259,
+      "grad_norm": 3.1269266605377197,
+      "learning_rate": 1.8872006455555906e-05,
+      "loss": 1.1148,
+      "step": 520
+    },
+    {
+      "epoch": 0.15559062052768705,
+      "grad_norm": 3.867361068725586,
+      "learning_rate": 1.8829071725894483e-05,
+      "loss": 1.02,
+      "step": 530
+    },
+    {
+      "epoch": 0.15852629261311513,
+      "grad_norm": 3.529639720916748,
+      "learning_rate": 1.87853858094708e-05,
+      "loss": 1.1167,
+      "step": 540
+    },
+    {
+      "epoch": 0.16146196469854318,
+      "grad_norm": 3.098249673843384,
+      "learning_rate": 1.8740952423128842e-05,
+      "loss": 1.0181,
+      "step": 550
+    },
+    {
+      "epoch": 0.16439763678397123,
+      "grad_norm": 3.1614904403686523,
+      "learning_rate": 1.869577534730812e-05,
+      "loss": 1.1118,
+      "step": 560
+    },
+    {
+      "epoch": 0.1673333088693993,
+      "grad_norm": 3.054616928100586,
+      "learning_rate": 1.8649858425722033e-05,
+      "loss": 1.0666,
+      "step": 570
+    },
+    {
+      "epoch": 0.17026898095482734,
+      "grad_norm": 3.479527711868286,
+      "learning_rate": 1.8603205565030846e-05,
+      "loss": 1.108,
+      "step": 580
+    },
+    {
+      "epoch": 0.1732046530402554,
+      "grad_norm": 2.9523024559020996,
+      "learning_rate": 1.8555820734509297e-05,
+      "loss": 1.0833,
+      "step": 590
+    },
+    {
+      "epoch": 0.17614032512568345,
+      "grad_norm": 2.9907584190368652,
+      "learning_rate": 1.8507707965708892e-05,
+      "loss": 1.0283,
+      "step": 600
+    },
+    {
+      "epoch": 0.17907599721111153,
+      "grad_norm": 3.2911376953125,
+      "learning_rate": 1.8458871352114894e-05,
+      "loss": 1.0747,
+      "step": 610
+    },
+    {
+      "epoch": 0.18201166929653959,
+      "grad_norm": 3.1361849308013916,
+      "learning_rate": 1.840931504879806e-05,
+      "loss": 1.11,
+      "step": 620
+    },
+    {
+      "epoch": 0.18494734138196764,
+      "grad_norm": 3.527332067489624,
+      "learning_rate": 1.8359043272061086e-05,
+      "loss": 1.0424,
+      "step": 630
+    },
+    {
+      "epoch": 0.1878830134673957,
+      "grad_norm": 3.5494275093078613,
+      "learning_rate": 1.8308060299079926e-05,
+      "loss": 1.0818,
+      "step": 640
+    },
+    {
+      "epoch": 0.19081868555282375,
+      "grad_norm": 3.4427106380462646,
+      "learning_rate": 1.8256370467539847e-05,
+      "loss": 1.0883,
+      "step": 650
+    },
+    {
+      "epoch": 0.1937543576382518,
+      "grad_norm": 3.092515230178833,
+      "learning_rate": 1.82039781752664e-05,
+      "loss": 1.0285,
+      "step": 660
+    },
+    {
+      "epoch": 0.19669002972367985,
+      "grad_norm": 2.667904853820801,
+      "learning_rate": 1.815088787985124e-05,
+      "loss": 0.9751,
+      "step": 670
+    },
+    {
+      "epoch": 0.19962570180910794,
+      "grad_norm": 3.5892174243927,
+      "learning_rate": 1.809710409827285e-05,
+      "loss": 1.0603,
+      "step": 680
+    },
+    {
+      "epoch": 0.202561373894536,
+      "grad_norm": 3.122434616088867,
+      "learning_rate": 1.804263140651227e-05,
+      "loss": 1.0919,
+      "step": 690
+    },
+    {
+      "epoch": 0.20549704597996404,
+      "grad_norm": 2.9182698726654053,
+      "learning_rate": 1.798747443916374e-05,
+      "loss": 1.0553,
+      "step": 700
+    },
+    {
+      "epoch": 0.2084327180653921,
+      "grad_norm": 3.260917901992798,
+      "learning_rate": 1.793163788904038e-05,
+      "loss": 1.0711,
+      "step": 710
+    },
+    {
+      "epoch": 0.21136839015082015,
+      "grad_norm": 3.4142649173736572,
+      "learning_rate": 1.7875126506774956e-05,
+      "loss": 1.0423,
+      "step": 720
+    },
+    {
+      "epoch": 0.2143040622362482,
+      "grad_norm": 3.0127294063568115,
+      "learning_rate": 1.781794510041564e-05,
+      "loss": 1.0679,
+      "step": 730
+    },
+    {
+      "epoch": 0.21723973432167626,
+      "grad_norm": 3.398015022277832,
+      "learning_rate": 1.776009853501698e-05,
+      "loss": 1.0558,
+      "step": 740
+    },
+    {
+      "epoch": 0.2201754064071043,
+      "grad_norm": 3.6017568111419678,
+      "learning_rate": 1.770159173222595e-05,
+      "loss": 1.0198,
+      "step": 750
+    },
+    {
+      "epoch": 0.2231110784925324,
+      "grad_norm": 3.5204339027404785,
+      "learning_rate": 1.7642429669863225e-05,
+      "loss": 0.9951,
+      "step": 760
+    },
+    {
+      "epoch": 0.22604675057796045,
+      "grad_norm": 3.3134777545928955,
+      "learning_rate": 1.7582617381499655e-05,
+      "loss": 0.9906,
+      "step": 770
+    },
+    {
+      "epoch": 0.2289824226633885,
+      "grad_norm": 3.5017244815826416,
+      "learning_rate": 1.7522159956028003e-05,
+      "loss": 1.0711,
+      "step": 780
+    },
+    {
+      "epoch": 0.23191809474881656,
+      "grad_norm": 3.1634137630462646,
+      "learning_rate": 1.7461062537229987e-05,
+      "loss": 0.9909,
+      "step": 790
+    },
+    {
+      "epoch": 0.2348537668342446,
+      "grad_norm": 3.368623971939087,
+      "learning_rate": 1.739933032333863e-05,
+      "loss": 0.9815,
+      "step": 800
+    },
+    {
+      "epoch": 0.23778943891967266,
+      "grad_norm": 3.1064817905426025,
+      "learning_rate": 1.733696856659599e-05,
+      "loss": 1.0191,
+      "step": 810
+    },
+    {
+      "epoch": 0.24072511100510072,
+      "grad_norm": 3.2074899673461914,
+      "learning_rate": 1.7273982572806303e-05,
+      "loss": 1.0314,
+      "step": 820
+    },
+    {
+      "epoch": 0.2436607830905288,
+      "grad_norm": 2.5882649421691895,
+      "learning_rate": 1.721037770088455e-05,
+      "loss": 0.958,
+      "step": 830
+    },
+    {
+      "epoch": 0.24659645517595685,
+      "grad_norm": 3.730363130569458,
+      "learning_rate": 1.7146159362400515e-05,
+      "loss": 1.0272,
+      "step": 840
+    },
+    {
+      "epoch": 0.2495321272613849,
+      "grad_norm": 2.940425395965576,
+      "learning_rate": 1.708133302111837e-05,
+      "loss": 1.0437,
+      "step": 850
+    },
+    {
+      "epoch": 0.25246779934681296,
+      "grad_norm": 4.833681106567383,
+      "learning_rate": 1.7015904192531814e-05,
+      "loss": 1.0393,
+      "step": 860
+    },
+    {
+      "epoch": 0.255403471432241,
+      "grad_norm": 3.417707681655884,
+      "learning_rate": 1.694987844339479e-05,
+      "loss": 1.0602,
+      "step": 870
+    },
+    {
+      "epoch": 0.25833914351766907,
+      "grad_norm": 3.239388942718506,
+      "learning_rate": 1.6883261391247888e-05,
+      "loss": 0.9515,
+      "step": 880
+    },
+    {
+      "epoch": 0.2612748156030971,
+      "grad_norm": 3.1867291927337646,
+      "learning_rate": 1.6816058703940366e-05,
+      "loss": 0.9961,
+      "step": 890
+    },
+    {
+      "epoch": 0.2642104876885252,
+      "grad_norm": 3.193343162536621,
+      "learning_rate": 1.6748276099147952e-05,
+      "loss": 1.0066,
+      "step": 900
+    },
+    {
+      "epoch": 0.26714615977395323,
+      "grad_norm": 3.1413753032684326,
+      "learning_rate": 1.6679919343886376e-05,
+      "loss": 0.9714,
+      "step": 910
+    },
+    {
+      "epoch": 0.2700818318593813,
+      "grad_norm": 3.0826566219329834,
+      "learning_rate": 1.661099425402067e-05,
+      "loss": 0.9689,
+      "step": 920
+    },
+    {
+      "epoch": 0.2730175039448094,
+      "grad_norm": 3.5959160327911377,
+      "learning_rate": 1.6541506693770403e-05,
+      "loss": 0.9867,
+      "step": 930
+    },
+    {
+      "epoch": 0.27595317603023745,
+      "grad_norm": 3.8435122966766357,
+      "learning_rate": 1.647146257521071e-05,
+      "loss": 1.0281,
+      "step": 940
+    },
+    {
+      "epoch": 0.2788888481156655,
+      "grad_norm": 3.396488904953003,
+      "learning_rate": 1.6400867857769287e-05,
+      "loss": 0.975,
+      "step": 950
+    },
+    {
+      "epoch": 0.28182452020109355,
+      "grad_norm": 3.2766590118408203,
+      "learning_rate": 1.6329728547719375e-05,
+      "loss": 0.9373,
+      "step": 960
+    },
+    {
+      "epoch": 0.2847601922865216,
+      "grad_norm": 3.673755645751953,
+      "learning_rate": 1.625805069766873e-05,
+      "loss": 0.9651,
+      "step": 970
+    },
+    {
+      "epoch": 0.28769586437194966,
+      "grad_norm": 3.8751864433288574,
+      "learning_rate": 1.6185840406044657e-05,
+      "loss": 0.9262,
+      "step": 980
+    },
+    {
+      "epoch": 0.2906315364573777,
+      "grad_norm": 3.708500623703003,
+      "learning_rate": 1.611310381657515e-05,
+      "loss": 0.9972,
+      "step": 990
+    },
+    {
+      "epoch": 0.29356720854280577,
+      "grad_norm": 3.4258711338043213,
+      "learning_rate": 1.60398471177662e-05,
+      "loss": 0.9331,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2965028806282338,
+      "grad_norm": 3.4662258625030518,
+      "learning_rate": 1.596607654237522e-05,
+      "loss": 0.9592,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2994385527136619,
+      "grad_norm": 2.938396453857422,
+      "learning_rate": 1.589179836688081e-05,
+      "loss": 0.9568,
+      "step": 1020
+    },
+    {
+      "epoch": 0.30237422479908993,
+      "grad_norm": 3.248762845993042,
+      "learning_rate": 1.5817018910948712e-05,
+      "loss": 0.9928,
+      "step": 1030
+    },
+    {
+      "epoch": 0.305309896884518,
+      "grad_norm": 3.423213243484497,
+      "learning_rate": 1.574174453689415e-05,
+      "loss": 0.9387,
+      "step": 1040
+    },
+    {
+      "epoch": 0.30824556896994604,
+      "grad_norm": 3.249216318130493,
+      "learning_rate": 1.566598164914049e-05,
+      "loss": 0.8925,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3111812410553741,
+      "grad_norm": 3.6318016052246094,
+      "learning_rate": 1.5589736693674372e-05,
+      "loss": 1.0153,
+      "step": 1060
+    },
+    {
+      "epoch": 0.31411691314080215,
+      "grad_norm": 3.9752533435821533,
+      "learning_rate": 1.551301615749726e-05,
+      "loss": 0.9323,
+      "step": 1070
+    },
+    {
+      "epoch": 0.31705258522623025,
+      "grad_norm": 3.46864914894104,
+      "learning_rate": 1.5435826568073532e-05,
+      "loss": 0.8901,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3199882573116583,
+      "grad_norm": 4.399304389953613,
+      "learning_rate": 1.535817449277511e-05,
+      "loss": 0.9118,
+      "step": 1090
+    },
+    {
+      "epoch": 0.32292392939708636,
+      "grad_norm": 3.2890026569366455,
+      "learning_rate": 1.5280066538322703e-05,
+      "loss": 0.8655,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3258596014825144,
+      "grad_norm": 3.491983652114868,
+      "learning_rate": 1.5201509350223708e-05,
+      "loss": 0.9217,
+      "step": 1110
+    },
+    {
+      "epoch": 0.32879527356794247,
+      "grad_norm": 5.0014824867248535,
+      "learning_rate": 1.5122509612206785e-05,
+      "loss": 0.9362,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3317309456533705,
+      "grad_norm": 4.092339038848877,
+      "learning_rate": 1.5043074045653215e-05,
+      "loss": 0.9262,
+      "step": 1130
+    },
+    {
+      "epoch": 0.3346666177387986,
+      "grad_norm": 3.286433219909668,
+      "learning_rate": 1.496320940902503e-05,
+      "loss": 0.8891,
+      "step": 1140
+    },
+    {
+      "epoch": 0.33760228982422663,
+      "grad_norm": 3.6521873474121094,
+      "learning_rate": 1.4882922497290007e-05,
+      "loss": 0.9281,
+      "step": 1150
+    },
+    {
+      "epoch": 0.3405379619096547,
+      "grad_norm": 3.8015809059143066,
+      "learning_rate": 1.4802220141343516e-05,
+      "loss": 0.8949,
+      "step": 1160
+    },
+    {
+      "epoch": 0.34347363399508274,
+      "grad_norm": 4.149661064147949,
+      "learning_rate": 1.472110920742738e-05,
+      "loss": 0.8889,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3464093060805108,
+      "grad_norm": 3.5252785682678223,
+      "learning_rate": 1.4639596596545656e-05,
+      "loss": 0.8397,
+      "step": 1180
+    },
+    {
+      "epoch": 0.34934497816593885,
+      "grad_norm": 3.6884541511535645,
+      "learning_rate": 1.4557689243877507e-05,
+      "loss": 0.9142,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3522806502513669,
+      "grad_norm": 3.9577550888061523,
+      "learning_rate": 1.4475394118187146e-05,
+      "loss": 0.9809,
+      "step": 1200
+    },
+    {
+      "epoch": 0.35521632233679495,
+      "grad_norm": 3.6897339820861816,
+      "learning_rate": 1.4392718221230917e-05,
+      "loss": 0.9141,
+      "step": 1210
+    },
+    {
+      "epoch": 0.35815199442222306,
+      "grad_norm": 3.061516046524048,
+      "learning_rate": 1.4309668587161596e-05,
+      "loss": 0.8669,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3610876665076511,
+      "grad_norm": 3.1191623210906982,
+      "learning_rate": 1.4226252281929902e-05,
+      "loss": 0.8384,
+      "step": 1230
+    },
+    {
+      "epoch": 0.36402333859307917,
+      "grad_norm": 4.198310852050781,
+      "learning_rate": 1.4142476402683327e-05,
+      "loss": 0.8971,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3669590106785072,
+      "grad_norm": 3.8184337615966797,
+      "learning_rate": 1.4058348077162301e-05,
+      "loss": 0.8783,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3698946827639353,
+      "grad_norm": 3.842637777328491,
+      "learning_rate": 1.3973874463093747e-05,
+      "loss": 0.9623,
+      "step": 1260
+    },
+    {
+      "epoch": 0.37283035484936333,
+      "grad_norm": 3.5173559188842773,
+      "learning_rate": 1.3889062747582118e-05,
+      "loss": 0.8092,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3757660269347914,
+      "grad_norm": 3.8953890800476074,
+      "learning_rate": 1.3803920146497887e-05,
+      "loss": 0.8762,
+      "step": 1280
+    },
+    {
+      "epoch": 0.37870169902021944,
+      "grad_norm": 3.0550928115844727,
+      "learning_rate": 1.3718453903863616e-05,
+      "loss": 0.8321,
+      "step": 1290
+    },
+    {
+      "epoch": 0.3816373711056475,
+      "grad_norm": 3.9677445888519287,
+      "learning_rate": 1.3632671291237645e-05,
+      "loss": 0.8566,
+      "step": 1300
+    },
+    {
+      "epoch": 0.38457304319107555,
+      "grad_norm": 3.887268304824829,
+      "learning_rate": 1.35465796070954e-05,
+      "loss": 0.8944,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3875087152765036,
+      "grad_norm": 3.1006393432617188,
+      "learning_rate": 1.3460186176208439e-05,
+      "loss": 0.7583,
+      "step": 1320
+    },
+    {
+      "epoch": 0.39044438736193166,
+      "grad_norm": 3.7594895362854004,
+      "learning_rate": 1.337349834902125e-05,
+      "loss": 0.814,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3933800594473597,
+      "grad_norm": 4.34951114654541,
+      "learning_rate": 1.328652350102588e-05,
+      "loss": 0.8006,
+      "step": 1340
+    },
+    {
+      "epoch": 0.39631573153278776,
+      "grad_norm": 2.9645636081695557,
+      "learning_rate": 1.3199269032134395e-05,
+      "loss": 0.8129,
+      "step": 1350
+    },
+    {
+      "epoch": 0.39925140361821587,
+      "grad_norm": 3.858602285385132,
+      "learning_rate": 1.3111742366049317e-05,
+      "loss": 0.8366,
+      "step": 1360
+    },
+    {
+      "epoch": 0.4021870757036439,
+      "grad_norm": 3.2778103351593018,
+      "learning_rate": 1.3023950949631979e-05,
+      "loss": 0.8551,
+      "step": 1370
+    },
+    {
+      "epoch": 0.405122747789072,
+      "grad_norm": 3.2402875423431396,
+      "learning_rate": 1.2935902252268965e-05,
+      "loss": 0.8398,
+      "step": 1380
+    },
+    {
+      "epoch": 0.40805841987450003,
+      "grad_norm": 4.325957775115967,
+      "learning_rate": 1.2847603765236589e-05,
+      "loss": 0.836,
+      "step": 1390
+    },
+    {
+      "epoch": 0.4109940919599281,
+      "grad_norm": 3.5310022830963135,
+      "learning_rate": 1.2759063001063531e-05,
+      "loss": 0.8369,
+      "step": 1400
+    },
+    {
+      "epoch": 0.41392976404535614,
+      "grad_norm": 3.5352087020874023,
+      "learning_rate": 1.2670287492891675e-05,
+      "loss": 0.8988,
+      "step": 1410
+    },
+    {
+      "epoch": 0.4168654361307842,
+      "grad_norm": 3.190788745880127,
+      "learning_rate": 1.258128479383516e-05,
+      "loss": 0.8352,
+      "step": 1420
+    },
+    {
+      "epoch": 0.41980110821621225,
+      "grad_norm": 3.459728240966797,
+      "learning_rate": 1.249206247633778e-05,
+      "loss": 0.8295,
+      "step": 1430
+    },
+    {
+      "epoch": 0.4227367803016403,
+      "grad_norm": 3.5794529914855957,
+      "learning_rate": 1.2402628131528686e-05,
+      "loss": 0.8103,
+      "step": 1440
+    },
+    {
+      "epoch": 0.42567245238706836,
+      "grad_norm": 4.169612407684326,
+      "learning_rate": 1.2312989368576547e-05,
+      "loss": 0.7757,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4286081244724964,
+      "grad_norm": 3.301011562347412,
+      "learning_rate": 1.2223153814042137e-05,
+      "loss": 0.7871,
+      "step": 1460
+    },
+    {
+      "epoch": 0.43154379655792446,
+      "grad_norm": 4.524185657501221,
+      "learning_rate": 1.2133129111229466e-05,
+      "loss": 0.851,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4344794686433525,
+      "grad_norm": 3.72041392326355,
+      "learning_rate": 1.2042922919535484e-05,
+      "loss": 0.803,
+      "step": 1480
+    },
+    {
+      "epoch": 0.43741514072878057,
+      "grad_norm": 3.926424503326416,
+      "learning_rate": 1.1952542913798406e-05,
+      "loss": 0.761,
+      "step": 1490
+    },
+    {
+      "epoch": 0.4403508128142086,
+      "grad_norm": 3.5725414752960205,
+      "learning_rate": 1.1861996783644727e-05,
+      "loss": 0.8086,
+      "step": 1500
+    },
+    {
+      "epoch": 0.44328648489963673,
+      "grad_norm": 4.109748363494873,
+      "learning_rate": 1.1771292232834983e-05,
+      "loss": 0.8483,
+      "step": 1510
+    },
+    {
+      "epoch": 0.4462221569850648,
+      "grad_norm": 3.673794984817505,
+      "learning_rate": 1.1680436978608314e-05,
+      "loss": 0.738,
+      "step": 1520
+    },
+    {
+      "epoch": 0.44915782907049284,
+      "grad_norm": 3.831571102142334,
+      "learning_rate": 1.1589438751025852e-05,
+      "loss": 0.7462,
+      "step": 1530
+    },
+    {
+      "epoch": 0.4520935011559209,
+      "grad_norm": 4.181507587432861,
+      "learning_rate": 1.149830529231307e-05,
+      "loss": 0.7707,
+      "step": 1540
+    },
+    {
+      "epoch": 0.45502917324134895,
+      "grad_norm": 3.3295936584472656,
+      "learning_rate": 1.140704435620104e-05,
+      "loss": 0.7832,
+      "step": 1550
+    },
+    {
+      "epoch": 0.457964845326777,
+      "grad_norm": 4.025683403015137,
+      "learning_rate": 1.1315663707266742e-05,
+      "loss": 0.74,
+      "step": 1560
+    },
+    {
+      "epoch": 0.46090051741220506,
+      "grad_norm": 3.792701244354248,
+      "learning_rate": 1.1224171120272455e-05,
+      "loss": 0.6698,
+      "step": 1570
+    },
+    {
+      "epoch": 0.4638361894976331,
+      "grad_norm": 3.7220959663391113,
+      "learning_rate": 1.1132574379504269e-05,
+      "loss": 0.7604,
+      "step": 1580
+    },
+    {
+      "epoch": 0.46677186158306117,
+      "grad_norm": 4.423033714294434,
+      "learning_rate": 1.1040881278109784e-05,
+      "loss": 0.7466,
+      "step": 1590
+    },
+    {
+      "epoch": 0.4697075336684892,
+      "grad_norm": 3.633347272872925,
+      "learning_rate": 1.0949099617435062e-05,
+      "loss": 0.7452,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4726432057539173,
+      "grad_norm": 3.661238431930542,
+      "learning_rate": 1.0857237206360885e-05,
+      "loss": 0.7637,
+      "step": 1610
+    },
+    {
+      "epoch": 0.4755788778393453,
+      "grad_norm": 4.33590030670166,
+      "learning_rate": 1.0765301860638364e-05,
+      "loss": 0.7364,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4785145499247734,
+      "grad_norm": 3.7030036449432373,
+      "learning_rate": 1.0673301402223964e-05,
+      "loss": 0.7356,
+      "step": 1630
+    },
+    {
+      "epoch": 0.48145022201020143,
+      "grad_norm": 4.784999847412109,
+      "learning_rate": 1.0581243658614013e-05,
+      "loss": 0.765,
+      "step": 1640
+    },
+    {
+      "epoch": 0.48438589409562954,
+      "grad_norm": 3.2158679962158203,
+      "learning_rate": 1.0489136462178718e-05,
+      "loss": 0.75,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4873215661810576,
+      "grad_norm": 4.584315299987793,
+      "learning_rate": 1.039698764949579e-05,
+      "loss": 0.7347,
+      "step": 1660
+    },
+    {
+      "epoch": 0.49025723826648565,
+      "grad_norm": 3.4453585147857666,
+      "learning_rate": 1.0304805060683692e-05,
+      "loss": 0.7887,
+      "step": 1670
+    },
+    {
+      "epoch": 0.4931929103519137,
+      "grad_norm": 3.9263744354248047,
+      "learning_rate": 1.021259653873459e-05,
+      "loss": 0.7492,
+      "step": 1680
+    },
+    {
+      "epoch": 0.49612858243734176,
+      "grad_norm": 4.6535539627075195,
+      "learning_rate": 1.012036992884708e-05,
+      "loss": 0.7676,
+      "step": 1690
+    },
+    {
+      "epoch": 0.4990642545227698,
+      "grad_norm": 4.22018575668335,
+      "learning_rate": 1.0028133077758688e-05,
+      "loss": 0.7088,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5019999266081978,
+      "grad_norm": 4.408539295196533,
+      "learning_rate": 9.935893833078284e-06,
+      "loss": 0.7646,
+      "step": 1710
+    },
+    {
+      "epoch": 0.5049355986936259,
+      "grad_norm": 5.264422416687012,
+      "learning_rate": 9.843660042618372e-06,
+      "loss": 0.8147,
+      "step": 1720
+    },
+    {
+      "epoch": 0.507871270779054,
+      "grad_norm": 4.2693047523498535,
+      "learning_rate": 9.75143955372742e-06,
+      "loss": 0.7104,
+      "step": 1730
+    },
+    {
+      "epoch": 0.510806942864482,
+      "grad_norm": 4.856871128082275,
+      "learning_rate": 9.659240212622175e-06,
+      "loss": 0.7367,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5137426149499101,
+      "grad_norm": 2.8976457118988037,
+      "learning_rate": 9.567069863720113e-06,
+      "loss": 0.7564,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5166782870353381,
+      "grad_norm": 5.992892742156982,
+      "learning_rate": 9.474936348972021e-06,
+      "loss": 0.7735,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5196139591207662,
+      "grad_norm": 3.6526339054107666,
+      "learning_rate": 9.382847507194797e-06,
+      "loss": 0.7035,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5225496312061942,
+      "grad_norm": 4.040701389312744,
+      "learning_rate": 9.290811173404513e-06,
+      "loss": 0.6347,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5254853032916224,
+      "grad_norm": 3.848483085632324,
+      "learning_rate": 9.198835178149807e-06,
+      "loss": 0.6359,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5284209753770504,
+      "grad_norm": 3.2821764945983887,
+      "learning_rate": 9.106927346845663e-06,
+      "loss": 0.7137,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5313566474624785,
+      "grad_norm": 4.672881603240967,
+      "learning_rate": 9.015095499107578e-06,
+      "loss": 0.7085,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5342923195479065,
+      "grad_norm": 3.976231098175049,
+      "learning_rate": 8.923347448086311e-06,
+      "loss": 0.6501,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5372279916333346,
+      "grad_norm": 4.726049423217773,
+      "learning_rate": 8.831690999803101e-06,
+      "loss": 0.8129,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5401636637187626,
+      "grad_norm": 6.278385162353516,
+      "learning_rate": 8.740133952485515e-06,
+      "loss": 0.6732,
+      "step": 1840
+    },
+    {
+      "epoch": 0.5430993358041907,
+      "grad_norm": 4.620763301849365,
+      "learning_rate": 8.648684095904001e-06,
+      "loss": 0.6872,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5460350078896188,
+      "grad_norm": 4.494777679443359,
+      "learning_rate": 8.557349210709098e-06,
+      "loss": 0.6686,
+      "step": 1860
+    },
+    {
+      "epoch": 0.5489706799750468,
+      "grad_norm": 4.2295637130737305,
+      "learning_rate": 8.46613706776945e-06,
+      "loss": 0.6853,
+      "step": 1870
+    },
+    {
+      "epoch": 0.5519063520604749,
+      "grad_norm": 3.5783040523529053,
+      "learning_rate": 8.375055427510673e-06,
+      "loss": 0.6923,
+      "step": 1880
+    },
+    {
+      "epoch": 0.5548420241459029,
+      "grad_norm": 3.5585546493530273,
+      "learning_rate": 8.284112039255071e-06,
+      "loss": 0.6744,
+      "step": 1890
+    },
+    {
+      "epoch": 0.557777696231331,
+      "grad_norm": 3.939253330230713,
+      "learning_rate": 8.193314640562315e-06,
+      "loss": 0.627,
+      "step": 1900
+    },
+    {
+      "epoch": 0.560713368316759,
+      "grad_norm": 3.630519390106201,
+      "learning_rate": 8.102670956571139e-06,
+      "loss": 0.6627,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5636490404021871,
+      "grad_norm": 11.943046569824219,
+      "learning_rate": 8.012188699342072e-06,
+      "loss": 0.6476,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5665847124876151,
+      "grad_norm": 5.358550071716309,
+      "learning_rate": 7.92187556720126e-06,
+      "loss": 0.6968,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5695203845730432,
+      "grad_norm": 3.8031585216522217,
+      "learning_rate": 7.831739244085534e-06,
+      "loss": 0.6811,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5724560566584712,
+      "grad_norm": 3.1659951210021973,
+      "learning_rate": 7.741787398888617e-06,
+      "loss": 0.6501,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5753917287438993,
+      "grad_norm": 3.7877001762390137,
+      "learning_rate": 7.652027684808644e-06,
+      "loss": 0.6496,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5783274008293273,
+      "grad_norm": 4.701345920562744,
+      "learning_rate": 7.56246773869705e-06,
+      "loss": 0.659,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5812630729147554,
+      "grad_norm": 4.617175579071045,
+      "learning_rate": 7.47311518040879e-06,
+      "loss": 0.6429,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5841987450001834,
+      "grad_norm": 5.269269943237305,
+      "learning_rate": 7.3839776121540385e-06,
+      "loss": 0.6845,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5871344170856115,
+      "grad_norm": 3.911558151245117,
+      "learning_rate": 7.2950626178514e-06,
+      "loss": 0.6536,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5900700891710396,
+      "grad_norm": NaN,
+      "learning_rate": 7.215235676567183e-06,
+      "loss": 0.6691,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5930057612564676,
+      "grad_norm": 5.29760217666626,
+      "learning_rate": 7.126764398128368e-06,
+      "loss": 0.6483,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5959414333418958,
+      "grad_norm": 3.4294636249542236,
+      "learning_rate": 7.038537577614009e-06,
+      "loss": 0.5965,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5988771054273238,
+      "grad_norm": 3.6569931507110596,
+      "learning_rate": 6.950562721455325e-06,
+      "loss": 0.5782,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6018127775127519,
+      "grad_norm": 3.845431089401245,
+      "learning_rate": 6.86284731464614e-06,
+      "loss": 0.6419,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6047484495981799,
+      "grad_norm": 3.8947107791900635,
+      "learning_rate": 6.775398820106065e-06,
+      "loss": 0.5942,
+      "step": 2060
+    },
+    {
+      "epoch": 0.607684121683608,
+      "grad_norm": 5.501591682434082,
+      "learning_rate": 6.688224678045507e-06,
+      "loss": 0.5874,
+      "step": 2070
+    },
+    {
+      "epoch": 0.610619793769036,
+      "grad_norm": 4.684408187866211,
+      "learning_rate": 6.6013323053327065e-06,
+      "loss": 0.6178,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6135554658544641,
+      "grad_norm": 4.132544040679932,
+      "learning_rate": 6.5147290948626365e-06,
+      "loss": 0.5972,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6164911379398921,
+      "grad_norm": 3.2844135761260986,
+      "learning_rate": 6.428422414928066e-06,
+      "loss": 0.5808,
+      "step": 2100
+    },
+    {
+      "epoch": 0.6194268100253202,
+      "grad_norm": 4.8152289390563965,
+      "learning_rate": 6.342419608592626e-06,
+      "loss": 0.6407,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6223624821107482,
+      "grad_norm": 4.975841999053955,
+      "learning_rate": 6.25672799306605e-06,
+      "loss": 0.5792,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6252981541961763,
+      "grad_norm": 3.772268772125244,
+      "learning_rate": 6.171354859081639e-06,
+      "loss": 0.7062,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6282338262816043,
+      "grad_norm": 3.6091275215148926,
+      "learning_rate": 6.086307470275947e-06,
+      "loss": 0.6015,
+      "step": 2140
+    },
+    {
+      "epoch": 0.6311694983670324,
+      "grad_norm": 3.9650683403015137,
+      "learning_rate": 6.001593062570776e-06,
+      "loss": 0.699,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6341051704524605,
+      "grad_norm": 3.4142041206359863,
+      "learning_rate": 5.917218843557551e-06,
+      "loss": 0.5912,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6370408425378885,
+      "grad_norm": 3.6262595653533936,
+      "learning_rate": 5.8415788415375744e-06,
+      "loss": 0.6029,
+      "step": 2170
+    },
+    {
+      "epoch": 0.6399765146233166,
+      "grad_norm": 3.612025737762451,
+      "learning_rate": 5.757870733799642e-06,
+      "loss": 0.6054,
+      "step": 2180
+    },
+    {
+      "epoch": 0.6429121867087446,
+      "grad_norm": 3.7721731662750244,
+      "learning_rate": 5.6745235509072135e-06,
+      "loss": 0.5703,
+      "step": 2190
+    },
+    {
+      "epoch": 0.6458478587941727,
+      "grad_norm": 4.44386100769043,
+      "learning_rate": 5.591544384126769e-06,
+      "loss": 0.6101,
+      "step": 2200
+    },
+    {
+      "epoch": 0.6487835308796007,
+      "grad_norm": 3.6553893089294434,
+      "learning_rate": 5.508940293413603e-06,
+      "loss": 0.6131,
+      "step": 2210
+    },
+    {
+      "epoch": 0.6517192029650288,
+      "grad_norm": 4.550465106964111,
+      "learning_rate": 5.426718306811134e-06,
+      "loss": 0.5761,
+      "step": 2220
+    },
+    {
+      "epoch": 0.6546548750504568,
+      "grad_norm": 3.433598279953003,
+      "learning_rate": 5.344885419852961e-06,
+      "loss": 0.6456,
+      "step": 2230
+    },
+    {
+      "epoch": 0.6575905471358849,
+      "grad_norm": 5.087676048278809,
+      "learning_rate": 5.263448594967673e-06,
+      "loss": 0.657,
+      "step": 2240
+    },
+    {
+      "epoch": 0.6605262192213129,
+      "grad_norm": 4.578396797180176,
+      "learning_rate": 5.182414760886484e-06,
+      "loss": 0.6083,
+      "step": 2250
+    },
+    {
+      "epoch": 0.663461891306741,
+      "grad_norm": 6.043960094451904,
+      "learning_rate": 5.1017908120537105e-06,
+      "loss": 0.5721,
+      "step": 2260
+    },
+    {
+      "epoch": 0.666397563392169,
+      "grad_norm": 3.624394178390503,
+      "learning_rate": 5.021583608040208e-06,
+      "loss": 0.5952,
+      "step": 2270
+    },
+    {
+      "epoch": 0.6693332354775972,
+      "grad_norm": 2.965820074081421,
+      "learning_rate": 4.941799972959752e-06,
+      "loss": 0.5074,
+      "step": 2280
+    },
+    {
+      "epoch": 0.6722689075630253,
+      "grad_norm": 5.590756416320801,
+      "learning_rate": 4.862446694888403e-06,
+      "loss": 0.5274,
+      "step": 2290
+    },
+    {
+      "epoch": 0.6752045796484533,
+      "grad_norm": 4.188043594360352,
+      "learning_rate": 4.783530525287006e-06,
+      "loss": 0.5694,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6781402517338814,
+      "grad_norm": 3.925184488296509,
+      "learning_rate": 4.705058178426753e-06,
+      "loss": 0.55,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6810759238193094,
+      "grad_norm": 4.226954936981201,
+      "learning_rate": 4.627036330817926e-06,
+      "loss": 0.5432,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6840115959047375,
+      "grad_norm": 3.9109609127044678,
+      "learning_rate": 4.5494716206418555e-06,
+      "loss": 0.5332,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6869472679901655,
+      "grad_norm": 4.698592662811279,
+      "learning_rate": 4.4723706471861385e-06,
+      "loss": 0.5744,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6898829400755936,
+      "grad_norm": 4.461889266967773,
+      "learning_rate": 4.3957399702831505e-06,
+      "loss": 0.5314,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6928186121610216,
+      "grad_norm": 4.412221908569336,
+      "learning_rate": 4.31958610975195e-06,
+      "loss": 0.554,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6957542842464497,
+      "grad_norm": 3.776421308517456,
+      "learning_rate": 4.243915544843549e-06,
+      "loss": 0.4857,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "grad_norm": 4.851159572601318,
+      "learning_rate": 4.168734713689658e-06,
+      "loss": 0.5484,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7016256284173058,
+      "grad_norm": 3.8917558193206787,
+      "learning_rate": 4.094050012754925e-06,
+      "loss": 0.4888,
+      "step": 2390
+    },
+    {
+      "epoch": 0.7045613005027338,
+      "grad_norm": 4.396358966827393,
+      "learning_rate": 4.019867796292709e-06,
+      "loss": 0.5125,
+      "step": 2400
+    },
+    {
+      "epoch": 0.7074969725881619,
+      "grad_norm": 4.374291896820068,
+      "learning_rate": 3.946194375804452e-06,
+      "loss": 0.5262,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7104326446735899,
+      "grad_norm": 4.330350875854492,
+      "learning_rate": 3.873036019502716e-06,
+      "loss": 0.5581,
+      "step": 2420
+    },
+    {
+      "epoch": 0.713368316759018,
+      "grad_norm": 4.86287784576416,
+      "learning_rate": 3.800398951777845e-06,
+      "loss": 0.5687,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7163039888444461,
+      "grad_norm": 5.004453659057617,
+      "learning_rate": 3.7282893526683914e-06,
+      "loss": 0.5136,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7192396609298741,
+      "grad_norm": 3.035261631011963,
+      "learning_rate": 3.656713357335334e-06,
+      "loss": 0.5358,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7221753330153022,
+      "grad_norm": 3.3477425575256348,
+      "learning_rate": 3.585677055540072e-06,
+      "loss": 0.5214,
+      "step": 2460
+    },
+    {
+      "epoch": 0.7251110051007302,
+      "grad_norm": 3.495814323425293,
+      "learning_rate": 3.5151864911263066e-06,
+      "loss": 0.5048,
+      "step": 2470
+    },
+    {
+      "epoch": 0.7280466771861583,
+      "grad_norm": 3.35532283782959,
+      "learning_rate": 3.4452476615058316e-06,
+      "loss": 0.509,
+      "step": 2480
+    },
+    {
+      "epoch": 0.7309823492715863,
+      "grad_norm": 3.0357613563537598,
+      "learning_rate": 3.3758665171482474e-06,
+      "loss": 0.5361,
+      "step": 2490
+    },
+    {
+      "epoch": 0.7339180213570144,
+      "grad_norm": 4.02761173248291,
+      "learning_rate": 3.3070489610747146e-06,
+      "loss": 0.5033,
+      "step": 2500
+    },
+    {
+      "epoch": 0.7368536934424424,
+      "grad_norm": 4.085331916809082,
+      "learning_rate": 3.238800848355702e-06,
+      "loss": 0.526,
+      "step": 2510
+    },
+    {
+      "epoch": 0.7397893655278706,
+      "grad_norm": 4.161253929138184,
+      "learning_rate": 3.1711279856128387e-06,
+      "loss": 0.5014,
+      "step": 2520
+    },
+    {
+      "epoch": 0.7427250376132986,
+      "grad_norm": 3.7220897674560547,
+      "learning_rate": 3.10403613052487e-06,
+      "loss": 0.4514,
+      "step": 2530
+    },
+    {
+      "epoch": 0.7456607096987267,
+      "grad_norm": 4.337230682373047,
+      "learning_rate": 3.037530991337807e-06,
+      "loss": 0.5645,
+      "step": 2540
+    },
+    {
+      "epoch": 0.7485963817841547,
+      "grad_norm": 4.30481481552124,
+      "learning_rate": 2.9716182263792314e-06,
+      "loss": 0.5026,
+      "step": 2550
+    },
+    {
+      "epoch": 0.7515320538695828,
+      "grad_norm": 3.3447349071502686,
+      "learning_rate": 2.9063034435769242e-06,
+      "loss": 0.5318,
+      "step": 2560
+    },
+    {
+      "epoch": 0.7544677259550108,
+      "grad_norm": 3.936032295227051,
+      "learning_rate": 2.8415921999816966e-06,
+      "loss": 0.5106,
+      "step": 2570
+    },
+    {
+      "epoch": 0.7574033980404389,
+      "grad_norm": 3.9542150497436523,
+      "learning_rate": 2.7774900012946037e-06,
+      "loss": 0.5299,
+      "step": 2580
+    },
+    {
+      "epoch": 0.760339070125867,
+      "grad_norm": 4.351448059082031,
+      "learning_rate": 2.714002301398524e-06,
+      "loss": 0.5211,
+      "step": 2590
+    },
+    {
+      "epoch": 0.763274742211295,
+      "grad_norm": 4.167295932769775,
+      "learning_rate": 2.6511345018941225e-06,
+      "loss": 0.5071,
+      "step": 2600
+    },
+    {
+      "epoch": 0.7662104142967231,
+      "grad_norm": 5.125722408294678,
+      "learning_rate": 2.588891951640288e-06,
+      "loss": 0.5199,
+      "step": 2610
+    },
+    {
+      "epoch": 0.7691460863821511,
+      "grad_norm": 4.25960111618042,
+      "learning_rate": 2.527279946299037e-06,
+      "loss": 0.4537,
+      "step": 2620
+    },
+    {
+      "epoch": 0.7720817584675792,
+      "grad_norm": 3.875459909439087,
+      "learning_rate": 2.4663037278849665e-06,
+      "loss": 0.4993,
+      "step": 2630
+    },
+    {
+      "epoch": 0.7750174305530072,
+      "grad_norm": 4.285188674926758,
+      "learning_rate": 2.405968484319231e-06,
+      "loss": 0.4596,
+      "step": 2640
+    },
+    {
+      "epoch": 0.7779531026384353,
+      "grad_norm": 3.827913284301758,
+      "learning_rate": 2.3462793489881884e-06,
+      "loss": 0.5141,
+      "step": 2650
+    },
+    {
+      "epoch": 0.7808887747238633,
+      "grad_norm": 4.174901485443115,
+      "learning_rate": 2.2872414003066146e-06,
+      "loss": 0.4483,
+      "step": 2660
+    },
+    {
+      "epoch": 0.7838244468092914,
+      "grad_norm": 3.4712812900543213,
+      "learning_rate": 2.2288596612856306e-06,
+      "loss": 0.4834,
+      "step": 2670
+    },
+    {
+      "epoch": 0.7867601188947194,
+      "grad_norm": 4.7577972412109375,
+      "learning_rate": 2.1711390991053547e-06,
+      "loss": 0.4913,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7896957909801475,
+      "grad_norm": 3.8983209133148193,
+      "learning_rate": 2.1140846246922774e-06,
+      "loss": 0.4748,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7926314630655755,
+      "grad_norm": 3.3365228176116943,
+      "learning_rate": 2.0577010923014353e-06,
+      "loss": 0.5014,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7955671351510036,
+      "grad_norm": 3.7394635677337646,
+      "learning_rate": 2.001993299103411e-06,
+      "loss": 0.4524,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7985028072364317,
+      "grad_norm": 3.325190544128418,
+      "learning_rate": 1.946965984776181e-06,
+      "loss": 0.486,
+      "step": 2720
+    },
+    {
+      "epoch": 0.8014384793218597,
+      "grad_norm": 3.337636947631836,
+      "learning_rate": 1.8926238311018551e-06,
+      "loss": 0.4112,
+      "step": 2730
+    },
+    {
+      "epoch": 0.8043741514072879,
+      "grad_norm": 4.279343128204346,
+      "learning_rate": 1.8443055276768218e-06,
+      "loss": 0.4758,
+      "step": 2740
+    },
+    {
+      "epoch": 0.8073098234927159,
+      "grad_norm": 3.3319621086120605,
+      "learning_rate": 1.7912778684550137e-06,
+      "loss": 0.4209,
+      "step": 2750
+    },
+    {
+      "epoch": 0.810245495578144,
+      "grad_norm": 4.332451343536377,
+      "learning_rate": 1.7389486159957436e-06,
+      "loss": 0.4913,
+      "step": 2760
+    },
+    {
+      "epoch": 0.813181167663572,
+      "grad_norm": 5.22000789642334,
+      "learning_rate": 1.6873222225271656e-06,
+      "loss": 0.4523,
+      "step": 2770
+    },
+    {
+      "epoch": 0.8161168397490001,
+      "grad_norm": 4.080671787261963,
+      "learning_rate": 1.63640308047745e-06,
+      "loss": 0.4545,
+      "step": 2780
+    },
+    {
+      "epoch": 0.8190525118344281,
+      "grad_norm": 5.591613292694092,
+      "learning_rate": 1.5861955221010671e-06,
+      "loss": 0.5272,
+      "step": 2790
+    },
+    {
+      "epoch": 0.8219881839198562,
+      "grad_norm": 3.4515106678009033,
+      "learning_rate": 1.536703819110198e-06,
+      "loss": 0.4166,
+      "step": 2800
+    },
+    {
+      "epoch": 0.8249238560052842,
+      "grad_norm": 3.1613569259643555,
+      "learning_rate": 1.4879321823112802e-06,
+      "loss": 0.5194,
+      "step": 2810
+    },
+    {
+      "epoch": 0.8278595280907123,
+      "grad_norm": 4.931222915649414,
+      "learning_rate": 1.4398847612467736e-06,
+      "loss": 0.4626,
+      "step": 2820
+    },
+    {
+      "epoch": 0.8307952001761403,
+      "grad_norm": 3.088315963745117,
+      "learning_rate": 1.3925656438420876e-06,
+      "loss": 0.4246,
+      "step": 2830
+    },
+    {
+      "epoch": 0.8337308722615684,
+      "grad_norm": 3.7036452293395996,
+      "learning_rate": 1.3459788560577847e-06,
+      "loss": 0.431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.8366665443469964,
+      "grad_norm": 4.452617168426514,
+      "learning_rate": 1.3001283615470517e-06,
+      "loss": 0.4478,
+      "step": 2850
+    },
+    {
+      "epoch": 0.8396022164324245,
+      "grad_norm": 3.2161977291107178,
+      "learning_rate": 1.255018061318467e-06,
+      "loss": 0.4432,
+      "step": 2860
+    },
+    {
+      "epoch": 0.8425378885178526,
+      "grad_norm": 4.302596092224121,
+      "learning_rate": 1.2106517934040917e-06,
+      "loss": 0.4598,
+      "step": 2870
+    },
+    {
+      "epoch": 0.8454735606032806,
+      "grad_norm": 4.297342300415039,
+      "learning_rate": 1.1670333325329353e-06,
+      "loss": 0.4908,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8484092326887087,
+      "grad_norm": 3.9199209213256836,
+      "learning_rate": 1.1241663898097865e-06,
+      "loss": 0.4239,
+      "step": 2890
+    },
+    {
+      "epoch": 0.8513449047741367,
+      "grad_norm": 4.693470001220703,
+      "learning_rate": 1.08205461239948e-06,
+      "loss": 0.4636,
+      "step": 2900
+    },
+    {
+      "epoch": 0.8542805768595648,
+      "grad_norm": 4.2040510177612305,
+      "learning_rate": 1.04070158321659e-06,
+      "loss": 0.4595,
+      "step": 2910
+    },
+    {
+      "epoch": 0.8572162489449928,
+      "grad_norm": 4.8676252365112305,
+      "learning_rate": 1.00011082062058e-06,
+      "loss": 0.4699,
+      "step": 2920
+    },
+    {
+      "epoch": 0.8601519210304209,
+      "grad_norm": 3.176576852798462,
+      "learning_rate": 9.602857781164721e-07,
+      "loss": 0.4599,
+      "step": 2930
+    },
+    {
+      "epoch": 0.8630875931158489,
+      "grad_norm": 4.111423969268799,
+      "learning_rate": 9.212298440610101e-07,
+      "loss": 0.4601,
+      "step": 2940
+    },
+    {
+      "epoch": 0.866023265201277,
+      "grad_norm": 3.106792449951172,
+      "learning_rate": 8.829463413743811e-07,
+      "loss": 0.453,
+      "step": 2950
+    },
+    {
+      "epoch": 0.868958937286705,
+      "grad_norm": 4.940300941467285,
+      "learning_rate": 8.454385272574906e-07,
+      "loss": 0.4298,
+      "step": 2960
+    },
+    {
+      "epoch": 0.8718946093721331,
+      "grad_norm": 4.7473249435424805,
+      "learning_rate": 8.087095929148436e-07,
+      "loss": 0.457,
+      "step": 2970
+    },
+    {
+      "epoch": 0.8748302814575611,
+      "grad_norm": 4.263439655303955,
+      "learning_rate": 7.727626632830221e-07,
+      "loss": 0.4194,
+      "step": 2980
+    },
+    {
+      "epoch": 0.8777659535429893,
+      "grad_norm": 4.69775390625,
+      "learning_rate": 7.376007967648302e-07,
+      "loss": 0.4457,
+      "step": 2990
+    },
+    {
+      "epoch": 0.8807016256284173,
+      "grad_norm": 4.177097320556641,
+      "learning_rate": 7.032269849690654e-07,
+      "loss": 0.4532,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8836372977138454,
+      "grad_norm": 4.312076568603516,
+      "learning_rate": 6.696441524559983e-07,
+      "loss": 0.4772,
+      "step": 3010
+    },
+    {
+      "epoch": 0.8865729697992735,
+      "grad_norm": 4.328220367431641,
+      "learning_rate": 6.368551564885439e-07,
+      "loss": 0.4239,
+      "step": 3020
+    },
+    {
+      "epoch": 0.8895086418847015,
+      "grad_norm": 3.3847310543060303,
+      "learning_rate": 6.048627867891665e-07,
+      "loss": 0.4564,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8924443139701296,
+      "grad_norm": 3.408613681793213,
+      "learning_rate": 5.736697653025192e-07,
+      "loss": 0.4206,
+      "step": 3040
+    },
+    {
+      "epoch": 0.8953799860555576,
+      "grad_norm": 4.045165061950684,
+      "learning_rate": 5.432787459638722e-07,
+      "loss": 0.4751,
+      "step": 3050
+    },
+    {
+      "epoch": 0.8983156581409857,
+      "grad_norm": 3.965830087661743,
+      "learning_rate": 5.136923144732997e-07,
+      "loss": 0.4273,
+      "step": 3060
+    },
+    {
+      "epoch": 0.9012513302264137,
+      "grad_norm": 3.462986707687378,
+      "learning_rate": 4.849129880756886e-07,
+      "loss": 0.472,
+      "step": 3070
+    },
+    {
+      "epoch": 0.9041870023118418,
+      "grad_norm": 5.114270210266113,
+      "learning_rate": 4.569432153465736e-07,
+      "loss": 0.5233,
+      "step": 3080
+    },
+    {
+      "epoch": 0.9071226743972698,
+      "grad_norm": 4.655681610107422,
+      "learning_rate": 4.297853759838055e-07,
+      "loss": 0.4543,
+      "step": 3090
+    },
+    {
+      "epoch": 0.9100583464826979,
+      "grad_norm": 4.586308002471924,
+      "learning_rate": 4.034417806050872e-07,
+      "loss": 0.4383,
+      "step": 3100
+    },
+    {
+      "epoch": 0.9129940185681259,
+      "grad_norm": 3.405298948287964,
+      "learning_rate": 3.779146705513814e-07,
+      "loss": 0.4644,
+      "step": 3110
+    },
+    {
+      "epoch": 0.915929690653554,
+      "grad_norm": 3.8995399475097656,
+      "learning_rate": 3.532062176962159e-07,
+      "loss": 0.4591,
+      "step": 3120
+    },
+    {
+      "epoch": 0.918865362738982,
+      "grad_norm": 3.6494014263153076,
+      "learning_rate": 3.293185242608954e-07,
+      "loss": 0.4354,
+      "step": 3130
+    },
+    {
+      "epoch": 0.9218010348244101,
+      "grad_norm": 4.192446708679199,
+      "learning_rate": 3.062536226356472e-07,
+      "loss": 0.4466,
+      "step": 3140
+    },
+    {
+      "epoch": 0.9247367069098382,
+      "grad_norm": 3.4682350158691406,
+      "learning_rate": 2.8401347520670253e-07,
+      "loss": 0.4629,
+      "step": 3150
+    },
+    {
+      "epoch": 0.9276723789952662,
+      "grad_norm": 3.987903594970703,
+      "learning_rate": 2.625999741893304e-07,
+      "loss": 0.5156,
+      "step": 3160
+    },
+    {
+      "epoch": 0.9306080510806943,
+      "grad_norm": 4.3802103996276855,
+      "learning_rate": 2.420149414668493e-07,
+      "loss": 0.42,
+      "step": 3170
+    },
+    {
+      "epoch": 0.9335437231661223,
+      "grad_norm": 4.355963230133057,
+      "learning_rate": 2.222601284356185e-07,
+      "loss": 0.4408,
+      "step": 3180
+    },
+    {
+      "epoch": 0.9364793952515504,
+      "grad_norm": 5.095834255218506,
+      "learning_rate": 2.0333721585602984e-07,
+      "loss": 0.4558,
+      "step": 3190
+    },
+    {
+      "epoch": 0.9394150673369784,
+      "grad_norm": 3.3932993412017822,
+      "learning_rate": 1.8524781370950262e-07,
+      "loss": 0.4475,
+      "step": 3200
+    },
+    {
+      "epoch": 0.9423507394224065,
+      "grad_norm": 5.2142014503479,
+      "learning_rate": 1.679934610615064e-07,
+      "loss": 0.4351,
+      "step": 3210
+    },
+    {
+      "epoch": 0.9452864115078345,
+      "grad_norm": 4.271505832672119,
+      "learning_rate": 1.515756259306178e-07,
+      "loss": 0.4431,
+      "step": 3220
+    },
+    {
+      "epoch": 0.9482220835932627,
+      "grad_norm": 4.888089656829834,
+      "learning_rate": 1.3599570516361737e-07,
+      "loss": 0.4256,
+      "step": 3230
+    },
+    {
+      "epoch": 0.9511577556786907,
+      "grad_norm": 4.216527938842773,
+      "learning_rate": 1.212550243166455e-07,
+      "loss": 0.4811,
+      "step": 3240
+    },
+    {
+      "epoch": 0.9540934277641188,
+      "grad_norm": 4.079187393188477,
+      "learning_rate": 1.0735483754242049e-07,
+      "loss": 0.4435,
+      "step": 3250
+    },
+    {
+      "epoch": 0.9570290998495468,
+      "grad_norm": 4.337707042694092,
+      "learning_rate": 9.429632748354068e-08,
+      "loss": 0.4152,
+      "step": 3260
+    },
+    {
+      "epoch": 0.9599647719349749,
+      "grad_norm": 3.4174439907073975,
+      "learning_rate": 8.208060517185146e-08,
+      "loss": 0.4579,
+      "step": 3270
+    },
+    {
+      "epoch": 0.9629004440204029,
+      "grad_norm": 4.021118640899658,
+      "learning_rate": 7.070870993393209e-08,
+      "loss": 0.4531,
+      "step": 3280
+    },
+    {
+      "epoch": 0.965836116105831,
+      "grad_norm": 3.2883527278900146,
+      "learning_rate": 6.01816093026586e-08,
+      "loss": 0.4384,
+      "step": 3290
+    },
+    {
+      "epoch": 0.9687717881912591,
+      "grad_norm": 3.5450029373168945,
+      "learning_rate": 5.0500198934889665e-08,
+      "loss": 0.4028,
+      "step": 3300
+    },
+    {
+      "epoch": 0.9717074602766871,
+      "grad_norm": 3.9169414043426514,
+      "learning_rate": 4.16653025352598e-08,
+      "loss": 0.4894,
+      "step": 3310
+    },
+    {
+      "epoch": 0.9746431323621152,
+      "grad_norm": 4.527153015136719,
+      "learning_rate": 3.367767178609982e-08,
+      "loss": 0.4403,
+      "step": 3320
+    },
+    {
+      "epoch": 0.9775788044475432,
+      "grad_norm": 4.728188514709473,
+      "learning_rate": 2.6537986283485805e-08,
+      "loss": 0.4123,
+      "step": 3330
+    },
+    {
+      "epoch": 0.9805144765329713,
+      "grad_norm": 4.7194037437438965,
+      "learning_rate": 2.024685347941202e-08,
+      "loss": 0.4456,
+      "step": 3340
+    },
+    {
+      "epoch": 0.9834501486183993,
+      "grad_norm": 4.34934139251709,
+      "learning_rate": 1.4804808630112244e-08,
+      "loss": 0.4383,
+      "step": 3350
+    },
+    {
+      "epoch": 0.9863858207038274,
+      "grad_norm": 4.218658924102783,
+      "learning_rate": 1.0212314750518426e-08,
+      "loss": 0.4368,
+      "step": 3360
+    },
+    {
+      "epoch": 0.9893214927892554,
+      "grad_norm": 4.213326454162598,
+      "learning_rate": 6.469762574868866e-09,
+      "loss": 0.4769,
+      "step": 3370
+    },
+    {
+      "epoch": 0.9922571648746835,
+      "grad_norm": 3.9344699382781982,
+      "learning_rate": 3.5774705234625783e-09,
+      "loss": 0.4412,
+      "step": 3380
+    },
+    {
+      "epoch": 0.9951928369601115,
+      "grad_norm": 3.622770071029663,
+      "learning_rate": 1.5356846755654187e-09,
+      "loss": 0.5059,
+      "step": 3390
+    },
+    {
+      "epoch": 0.9981285090455396,
+      "grad_norm": 5.872491359710693,
+      "learning_rate": 3.4457874847793063e-10,
+      "loss": 0.4697,
+      "step": 3400
+    },
+    {
+      "epoch": 0.9998899122967965,
+      "step": 3406,
+      "total_flos": 3.2891568428128666e+18,
+      "train_loss": 0.7668657067657847,
+      "train_runtime": 24228.5265,
+      "train_samples_per_second": 4.499,
+      "train_steps_per_second": 0.141
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3406,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.2891568428128666e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e21c12aabf1516052edabb8d4bd98ccbd2e1fbd03851dc54004b7ada1a7bb0e
+size 5304