Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft__exp_rpt_stack-bash-withtests_glm_4-7_traces_jupiter__Qwen3-8B
+  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. -->
+
+# sft__exp_rpt_stack-bash-withtests_glm_4-7_traces_jupiter__Qwen3-8B
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp_rpt_stack-bash-withtests_glm_4.7_traces_jupiter/snapshots/82b5d32a246ba8ef7438586e6e27da58d585345f_thinking_preprocessed 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- gradient_accumulation_steps: 3
+- total_train_batch_size: 96
+- total_eval_batch_size: 256
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.9.1+cu130
+- Datasets 4.4.1
+- Tokenizers 0.22.2

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,16 @@
+{
+    "achieved_tflops_per_gpu": 42526.70396900443,
+    "achieved_tflops_per_gpu_theoretical": 1871630.9362088453,
+    "epoch": 7.0,
+    "loss_nan_ranks": 0,
+    "loss_rank_avg": 0.09868818521499634,
+    "mfu_percent": 3005.4207751946597,
+    "mfu_percent_theoretical": 132270.73754126116,
+    "total_flos": 1.9140418922369516e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.4065,
+    "train_samples_per_second": 53019.754,
+    "train_steps_per_second": 552.445,
+    "valid_targets_mean": 4527.2,
+    "valid_targets_min": 593
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8690d3233df422290e9039a1a7739315992fa528b84cbe87e9839608ba4d69e3
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:100423744d6201792ad80bea1a62ff19f4722a8ea4b2fa32aa60fb55267f7526
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c52c0ec1251c41a8c9c30e2993e426fe847600a029f0a58df35794be7a493682
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0a8f1801a6dac42ca14507f648b4e4584da6273485f3bfae03afa4704677a8c
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 308224,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": "82b5d32a246ba8ef7438586e6e27da58d585345f_thinking_preprocessed",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "/e/data1/datasets/playground/ot/hf_hub/datasets--DCAgent--exp_rpt_stack-bash-withtests_glm_4.7_traces_jupiter/snapshots/82b5d32a246ba8ef7438586e6e27da58d585345f_thinking_preprocessed",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/exp_rpt_stack-bash-withtests_glm_4_7_traces_jupiter/blob/main/config.json",
+  "wandb_link": null,
+  "traces_location_s3": null
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,12 @@
+{
+    "achieved_tflops_per_gpu": 42526.70396900443,
+    "achieved_tflops_per_gpu_theoretical": 1871630.9362088453,
+    "epoch": 7.0,
+    "mfu_percent": 3005.4207751946597,
+    "mfu_percent_theoretical": 132270.73754126116,
+    "total_flos": 1.9140418922369516e+18,
+    "train_loss": 0.0,
+    "train_runtime": 1.4065,
+    "train_samples_per_second": 53019.754,
+    "train_steps_per_second": 552.445
+}

trainer_log.jsonl

@@ -0,0 +1,160 @@
+{"current_steps": 5, "total_steps": 777, "loss": 0.6951, "lr": 2.0512820512820513e-06, "epoch": 0.04504504504504504, "percentage": 0.64, "elapsed_time": "0:02:02", "remaining_time": "5:16:16"}
+{"current_steps": 10, "total_steps": 777, "loss": 0.6634, "lr": 4.615384615384616e-06, "epoch": 0.09009009009009009, "percentage": 1.29, "elapsed_time": "0:04:07", "remaining_time": "5:16:18"}
+{"current_steps": 15, "total_steps": 777, "loss": 0.5718, "lr": 7.17948717948718e-06, "epoch": 0.13513513513513514, "percentage": 1.93, "elapsed_time": "0:06:10", "remaining_time": "5:13:28"}
+{"current_steps": 20, "total_steps": 777, "loss": 0.5115, "lr": 9.743589743589744e-06, "epoch": 0.18018018018018017, "percentage": 2.57, "elapsed_time": "0:08:05", "remaining_time": "5:06:17"}
+{"current_steps": 25, "total_steps": 777, "loss": 0.4871, "lr": 1.230769230769231e-05, "epoch": 0.22522522522522523, "percentage": 3.22, "elapsed_time": "0:10:04", "remaining_time": "5:03:00"}
+{"current_steps": 30, "total_steps": 777, "loss": 0.4791, "lr": 1.4871794871794874e-05, "epoch": 0.2702702702702703, "percentage": 3.86, "elapsed_time": "0:12:02", "remaining_time": "4:59:57"}
+{"current_steps": 35, "total_steps": 777, "loss": 0.4542, "lr": 1.7435897435897438e-05, "epoch": 0.3153153153153153, "percentage": 4.5, "elapsed_time": "0:14:05", "remaining_time": "4:58:36"}
+{"current_steps": 40, "total_steps": 777, "loss": 0.4362, "lr": 2e-05, "epoch": 0.36036036036036034, "percentage": 5.15, "elapsed_time": "0:16:00", "remaining_time": "4:54:53"}
+{"current_steps": 45, "total_steps": 777, "loss": 0.4108, "lr": 2.2564102564102566e-05, "epoch": 0.40540540540540543, "percentage": 5.79, "elapsed_time": "0:18:05", "remaining_time": "4:54:11"}
+{"current_steps": 50, "total_steps": 777, "loss": 0.4218, "lr": 2.512820512820513e-05, "epoch": 0.45045045045045046, "percentage": 6.44, "elapsed_time": "0:19:56", "remaining_time": "4:50:02"}
+{"current_steps": 55, "total_steps": 777, "loss": 0.4003, "lr": 2.7692307692307694e-05, "epoch": 0.4954954954954955, "percentage": 7.08, "elapsed_time": "0:22:01", "remaining_time": "4:49:04"}
+{"current_steps": 60, "total_steps": 777, "loss": 0.3955, "lr": 3.0256410256410257e-05, "epoch": 0.5405405405405406, "percentage": 7.72, "elapsed_time": "0:24:00", "remaining_time": "4:46:53"}
+{"current_steps": 65, "total_steps": 777, "loss": 0.3757, "lr": 3.282051282051282e-05, "epoch": 0.5855855855855856, "percentage": 8.37, "elapsed_time": "0:26:04", "remaining_time": "4:45:36"}
+{"current_steps": 70, "total_steps": 777, "loss": 0.3825, "lr": 3.538461538461539e-05, "epoch": 0.6306306306306306, "percentage": 9.01, "elapsed_time": "0:28:00", "remaining_time": "4:42:56"}
+{"current_steps": 75, "total_steps": 777, "loss": 0.3694, "lr": 3.794871794871795e-05, "epoch": 0.6756756756756757, "percentage": 9.65, "elapsed_time": "0:30:04", "remaining_time": "4:41:30"}
+{"current_steps": 80, "total_steps": 777, "loss": 0.356, "lr": 3.999979800311937e-05, "epoch": 0.7207207207207207, "percentage": 10.3, "elapsed_time": "0:32:06", "remaining_time": "4:39:46"}
+{"current_steps": 85, "total_steps": 777, "loss": 0.3409, "lr": 3.999272854071669e-05, "epoch": 0.7657657657657657, "percentage": 10.94, "elapsed_time": "0:34:05", "remaining_time": "4:37:33"}
+{"current_steps": 90, "total_steps": 777, "loss": 0.347, "lr": 3.99755633141858e-05, "epoch": 0.8108108108108109, "percentage": 11.58, "elapsed_time": "0:36:01", "remaining_time": "4:34:59"}
+{"current_steps": 95, "total_steps": 777, "loss": 0.3339, "lr": 3.994831099148205e-05, "epoch": 0.8558558558558559, "percentage": 12.23, "elapsed_time": "0:37:56", "remaining_time": "4:32:20"}
+{"current_steps": 100, "total_steps": 777, "loss": 0.3304, "lr": 3.991098533425988e-05, "epoch": 0.9009009009009009, "percentage": 12.87, "elapsed_time": "0:39:45", "remaining_time": "4:29:10"}
+{"current_steps": 105, "total_steps": 777, "loss": 0.3353, "lr": 3.9863605190923655e-05, "epoch": 0.9459459459459459, "percentage": 13.51, "elapsed_time": "0:41:40", "remaining_time": "4:26:43"}
+{"current_steps": 110, "total_steps": 777, "loss": 0.3293, "lr": 3.9806194487109636e-05, "epoch": 0.990990990990991, "percentage": 14.16, "elapsed_time": "0:43:40", "remaining_time": "4:24:47"}
+{"current_steps": 115, "total_steps": 777, "loss": 0.3461, "lr": 3.9738782213604305e-05, "epoch": 1.0360360360360361, "percentage": 14.8, "elapsed_time": "0:45:42", "remaining_time": "4:23:06"}
+{"current_steps": 120, "total_steps": 777, "loss": 0.3399, "lr": 3.9661402411704794e-05, "epoch": 1.0810810810810811, "percentage": 15.44, "elapsed_time": "0:47:45", "remaining_time": "4:21:27"}
+{"current_steps": 125, "total_steps": 777, "loss": 0.3244, "lr": 3.957409415602899e-05, "epoch": 1.1261261261261262, "percentage": 16.09, "elapsed_time": "0:49:38", "remaining_time": "4:18:56"}
+{"current_steps": 130, "total_steps": 777, "loss": 0.3128, "lr": 3.947690153478396e-05, "epoch": 1.1711711711711712, "percentage": 16.73, "elapsed_time": "0:51:26", "remaining_time": "4:16:03"}
+{"current_steps": 135, "total_steps": 777, "loss": 0.3319, "lr": 3.936987362750266e-05, "epoch": 1.2162162162162162, "percentage": 17.37, "elapsed_time": "0:53:26", "remaining_time": "4:14:06"}
+{"current_steps": 140, "total_steps": 777, "loss": 0.3272, "lr": 3.925306448026011e-05, "epoch": 1.2612612612612613, "percentage": 18.02, "elapsed_time": "0:55:16", "remaining_time": "4:11:31"}
+{"current_steps": 145, "total_steps": 777, "loss": 0.3191, "lr": 3.912653307838173e-05, "epoch": 1.3063063063063063, "percentage": 18.66, "elapsed_time": "0:57:21", "remaining_time": "4:10:01"}
+{"current_steps": 150, "total_steps": 777, "loss": 0.3132, "lr": 3.899034331665733e-05, "epoch": 1.3513513513513513, "percentage": 19.31, "elapsed_time": "0:59:16", "remaining_time": "4:07:47"}
+{"current_steps": 155, "total_steps": 777, "loss": 0.3172, "lr": 3.884456396707611e-05, "epoch": 1.3963963963963963, "percentage": 19.95, "elapsed_time": "1:01:15", "remaining_time": "4:05:50"}
+{"current_steps": 160, "total_steps": 777, "loss": 0.3205, "lr": 3.8689268644098715e-05, "epoch": 1.4414414414414414, "percentage": 20.59, "elapsed_time": "1:03:13", "remaining_time": "4:03:48"}
+{"current_steps": 165, "total_steps": 777, "loss": 0.3006, "lr": 3.852453576748397e-05, "epoch": 1.4864864864864864, "percentage": 21.24, "elapsed_time": "1:05:13", "remaining_time": "4:01:54"}
+{"current_steps": 170, "total_steps": 777, "loss": 0.3053, "lr": 3.835044852268921e-05, "epoch": 1.5315315315315314, "percentage": 21.88, "elapsed_time": "1:07:10", "remaining_time": "3:59:50"}
+{"current_steps": 175, "total_steps": 777, "loss": 0.3197, "lr": 3.816709481886386e-05, "epoch": 1.5765765765765765, "percentage": 22.52, "elapsed_time": "1:09:09", "remaining_time": "3:57:54"}
+{"current_steps": 180, "total_steps": 777, "loss": 0.3112, "lr": 3.7974567244457886e-05, "epoch": 1.6216216216216215, "percentage": 23.17, "elapsed_time": "1:11:09", "remaining_time": "3:56:01"}
+{"current_steps": 185, "total_steps": 777, "loss": 0.3096, "lr": 3.777296302046719e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "1:13:07", "remaining_time": "3:54:01"}
+{"current_steps": 190, "total_steps": 777, "loss": 0.302, "lr": 3.756238395133972e-05, "epoch": 1.7117117117117115, "percentage": 24.45, "elapsed_time": "1:15:02", "remaining_time": "3:51:51"}
+{"current_steps": 195, "total_steps": 777, "loss": 0.3059, "lr": 3.734293637356719e-05, "epoch": 1.7567567567567568, "percentage": 25.1, "elapsed_time": "1:17:02", "remaining_time": "3:49:55"}
+{"current_steps": 200, "total_steps": 777, "loss": 0.3168, "lr": 3.711473110198805e-05, "epoch": 1.8018018018018018, "percentage": 25.74, "elapsed_time": "1:19:06", "remaining_time": "3:48:14"}
+{"current_steps": 205, "total_steps": 777, "loss": 0.2959, "lr": 3.687788337382918e-05, "epoch": 1.8468468468468469, "percentage": 26.38, "elapsed_time": "1:20:59", "remaining_time": "3:45:59"}
+{"current_steps": 210, "total_steps": 777, "loss": 0.2993, "lr": 3.663251279051431e-05, "epoch": 1.8918918918918919, "percentage": 27.03, "elapsed_time": "1:22:51", "remaining_time": "3:43:41"}
+{"current_steps": 215, "total_steps": 777, "loss": 0.2999, "lr": 3.6378743257268696e-05, "epoch": 1.936936936936937, "percentage": 27.67, "elapsed_time": "1:24:48", "remaining_time": "3:41:41"}
+{"current_steps": 220, "total_steps": 777, "loss": 0.3047, "lr": 3.6116702920550445e-05, "epoch": 1.981981981981982, "percentage": 28.31, "elapsed_time": "1:26:40", "remaining_time": "3:39:27"}
+{"current_steps": 225, "total_steps": 777, "loss": 0.2942, "lr": 3.58465241033402e-05, "epoch": 2.027027027027027, "percentage": 28.96, "elapsed_time": "1:28:32", "remaining_time": "3:37:13"}
+{"current_steps": 230, "total_steps": 777, "loss": 0.2942, "lr": 3.556834323832174e-05, "epoch": 2.0720720720720722, "percentage": 29.6, "elapsed_time": "1:30:31", "remaining_time": "3:35:18"}
+{"current_steps": 235, "total_steps": 777, "loss": 0.2918, "lr": 3.528230079898734e-05, "epoch": 2.1171171171171173, "percentage": 30.24, "elapsed_time": "1:32:31", "remaining_time": "3:33:23"}
+{"current_steps": 240, "total_steps": 777, "loss": 0.2903, "lr": 3.498854122870263e-05, "epoch": 2.1621621621621623, "percentage": 30.89, "elapsed_time": "1:34:30", "remaining_time": "3:31:27"}
+{"current_steps": 245, "total_steps": 777, "loss": 0.2968, "lr": 3.4687212867766696e-05, "epoch": 2.2072072072072073, "percentage": 31.53, "elapsed_time": "1:36:30", "remaining_time": "3:29:33"}
+{"current_steps": 250, "total_steps": 777, "loss": 0.3055, "lr": 3.437846787850454e-05, "epoch": 2.2522522522522523, "percentage": 32.18, "elapsed_time": "1:38:28", "remaining_time": "3:27:35"}
+{"current_steps": 255, "total_steps": 777, "loss": 0.2857, "lr": 3.4062462168429267e-05, "epoch": 2.2972972972972974, "percentage": 32.82, "elapsed_time": "1:40:17", "remaining_time": "3:25:17"}
+{"current_steps": 260, "total_steps": 777, "loss": 0.2905, "lr": 3.373935531151326e-05, "epoch": 2.3423423423423424, "percentage": 33.46, "elapsed_time": "1:42:18", "remaining_time": "3:23:25"}
+{"current_steps": 265, "total_steps": 777, "loss": 0.2858, "lr": 3.3409310467607824e-05, "epoch": 2.3873873873873874, "percentage": 34.11, "elapsed_time": "1:44:13", "remaining_time": "3:21:23"}
+{"current_steps": 270, "total_steps": 777, "loss": 0.2982, "lr": 3.307249430005203e-05, "epoch": 2.4324324324324325, "percentage": 34.75, "elapsed_time": "1:46:10", "remaining_time": "3:19:23"}
+{"current_steps": 275, "total_steps": 777, "loss": 0.3072, "lr": 3.272907689151245e-05, "epoch": 2.4774774774774775, "percentage": 35.39, "elapsed_time": "1:48:06", "remaining_time": "3:17:20"}
+{"current_steps": 280, "total_steps": 777, "loss": 0.2958, "lr": 3.237923165809619e-05, "epoch": 2.5225225225225225, "percentage": 36.04, "elapsed_time": "1:50:06", "remaining_time": "3:15:26"}
+{"current_steps": 285, "total_steps": 777, "loss": 0.2995, "lr": 3.202313526178067e-05, "epoch": 2.5675675675675675, "percentage": 36.68, "elapsed_time": "1:52:03", "remaining_time": "3:13:26"}
+{"current_steps": 290, "total_steps": 777, "loss": 0.2818, "lr": 3.16609675212043e-05, "epoch": 2.6126126126126126, "percentage": 37.32, "elapsed_time": "1:53:52", "remaining_time": "3:11:14"}
+{"current_steps": 295, "total_steps": 777, "loss": 0.2959, "lr": 3.1292911320863104e-05, "epoch": 2.6576576576576576, "percentage": 37.97, "elapsed_time": "1:55:43", "remaining_time": "3:09:05"}
+{"current_steps": 300, "total_steps": 777, "loss": 0.2936, "lr": 3.091915251875928e-05, "epoch": 2.7027027027027026, "percentage": 38.61, "elapsed_time": "1:57:47", "remaining_time": "3:07:16"}
+{"current_steps": 305, "total_steps": 777, "loss": 0.2841, "lr": 3.053987985254806e-05, "epoch": 2.7477477477477477, "percentage": 39.25, "elapsed_time": "1:59:48", "remaining_time": "3:05:24"}
+{"current_steps": 310, "total_steps": 777, "loss": 0.2828, "lr": 3.015528484423059e-05, "epoch": 2.7927927927927927, "percentage": 39.9, "elapsed_time": "2:01:42", "remaining_time": "3:03:21"}
+{"current_steps": 315, "total_steps": 777, "loss": 0.293, "lr": 2.9765561703440688e-05, "epoch": 2.8378378378378377, "percentage": 40.54, "elapsed_time": "2:03:45", "remaining_time": "3:01:31"}
+{"current_steps": 320, "total_steps": 777, "loss": 0.2753, "lr": 2.937090722937446e-05, "epoch": 2.8828828828828827, "percentage": 41.18, "elapsed_time": "2:05:42", "remaining_time": "2:59:31"}
+{"current_steps": 325, "total_steps": 777, "loss": 0.2873, "lr": 2.897152071141225e-05, "epoch": 2.9279279279279278, "percentage": 41.83, "elapsed_time": "2:07:33", "remaining_time": "2:57:24"}
+{"current_steps": 330, "total_steps": 777, "loss": 0.2975, "lr": 2.8567603828483125e-05, "epoch": 2.972972972972973, "percentage": 42.47, "elapsed_time": "2:09:38", "remaining_time": "2:55:35"}
+{"current_steps": 335, "total_steps": 777, "loss": 0.2851, "lr": 2.8159360547222716e-05, "epoch": 3.018018018018018, "percentage": 43.11, "elapsed_time": "2:11:34", "remaining_time": "2:53:36"}
+{"current_steps": 340, "total_steps": 777, "loss": 0.2825, "lr": 2.7746997018975804e-05, "epoch": 3.063063063063063, "percentage": 43.76, "elapsed_time": "2:13:40", "remaining_time": "2:51:48"}
+{"current_steps": 345, "total_steps": 777, "loss": 0.2749, "lr": 2.733072147569572e-05, "epoch": 3.108108108108108, "percentage": 44.4, "elapsed_time": "2:15:35", "remaining_time": "2:49:47"}
+{"current_steps": 350, "total_steps": 777, "loss": 0.2788, "lr": 2.6910744124793046e-05, "epoch": 3.153153153153153, "percentage": 45.05, "elapsed_time": "2:17:30", "remaining_time": "2:47:45"}
+{"current_steps": 355, "total_steps": 777, "loss": 0.2794, "lr": 2.648727704298685e-05, "epoch": 3.1981981981981984, "percentage": 45.69, "elapsed_time": "2:19:27", "remaining_time": "2:45:46"}
+{"current_steps": 360, "total_steps": 777, "loss": 0.2876, "lr": 2.6060534069211877e-05, "epoch": 3.2432432432432434, "percentage": 46.33, "elapsed_time": "2:21:24", "remaining_time": "2:43:47"}
+{"current_steps": 365, "total_steps": 777, "loss": 0.2773, "lr": 2.5630730696635953e-05, "epoch": 3.2882882882882885, "percentage": 46.98, "elapsed_time": "2:23:18", "remaining_time": "2:41:45"}
+{"current_steps": 370, "total_steps": 777, "loss": 0.2824, "lr": 2.5198083963841988e-05, "epoch": 3.3333333333333335, "percentage": 47.62, "elapsed_time": "2:25:15", "remaining_time": "2:39:47"}
+{"current_steps": 375, "total_steps": 777, "loss": 0.2846, "lr": 2.4762812345229622e-05, "epoch": 3.3783783783783785, "percentage": 48.26, "elapsed_time": "2:27:10", "remaining_time": "2:37:46"}
+{"current_steps": 380, "total_steps": 777, "loss": 0.2821, "lr": 2.4325135640691823e-05, "epoch": 3.4234234234234235, "percentage": 48.91, "elapsed_time": "2:29:06", "remaining_time": "2:35:46"}
+{"current_steps": 385, "total_steps": 777, "loss": 0.2693, "lr": 2.388527486462212e-05, "epoch": 3.4684684684684686, "percentage": 49.55, "elapsed_time": "2:31:00", "remaining_time": "2:33:45"}
+{"current_steps": 390, "total_steps": 777, "loss": 0.2775, "lr": 2.3443452134308565e-05, "epoch": 3.5135135135135136, "percentage": 50.19, "elapsed_time": "2:32:59", "remaining_time": "2:31:49"}
+{"current_steps": 395, "total_steps": 777, "loss": 0.276, "lr": 2.299989055777079e-05, "epoch": 3.5585585585585586, "percentage": 50.84, "elapsed_time": "2:34:56", "remaining_time": "2:29:50"}
+{"current_steps": 400, "total_steps": 777, "loss": 0.2924, "lr": 2.2554814121096748e-05, "epoch": 3.6036036036036037, "percentage": 51.48, "elapsed_time": "2:36:50", "remaining_time": "2:27:49"}
+{"current_steps": 405, "total_steps": 777, "loss": 0.2783, "lr": 2.2108447575336015e-05, "epoch": 3.6486486486486487, "percentage": 52.12, "elapsed_time": "2:38:41", "remaining_time": "2:25:46"}
+{"current_steps": 410, "total_steps": 777, "loss": 0.2841, "lr": 2.16610163230069e-05, "epoch": 3.6936936936936937, "percentage": 52.77, "elapsed_time": "2:40:38", "remaining_time": "2:23:47"}
+{"current_steps": 415, "total_steps": 777, "loss": 0.2709, "lr": 2.1212746304274482e-05, "epoch": 3.7387387387387387, "percentage": 53.41, "elapsed_time": "2:42:38", "remaining_time": "2:21:52"}
+{"current_steps": 420, "total_steps": 777, "loss": 0.2802, "lr": 2.0763863882857242e-05, "epoch": 3.7837837837837838, "percentage": 54.05, "elapsed_time": "2:44:37", "remaining_time": "2:19:55"}
+{"current_steps": 425, "total_steps": 777, "loss": 0.2764, "lr": 2.031459573171973e-05, "epoch": 3.828828828828829, "percentage": 54.7, "elapsed_time": "2:46:33", "remaining_time": "2:17:56"}
+{"current_steps": 430, "total_steps": 777, "loss": 0.2753, "lr": 1.9865168718609142e-05, "epoch": 3.873873873873874, "percentage": 55.34, "elapsed_time": "2:48:30", "remaining_time": "2:15:58"}
+{"current_steps": 435, "total_steps": 777, "loss": 0.2599, "lr": 1.9415809791493484e-05, "epoch": 3.918918918918919, "percentage": 55.98, "elapsed_time": "2:50:25", "remaining_time": "2:13:59"}
+{"current_steps": 440, "total_steps": 777, "loss": 0.29, "lr": 1.8966745863959256e-05, "epoch": 3.963963963963964, "percentage": 56.63, "elapsed_time": "2:52:10", "remaining_time": "2:11:51"}
+{"current_steps": 445, "total_steps": 777, "loss": 0.2694, "lr": 1.851820370062648e-05, "epoch": 4.009009009009009, "percentage": 57.27, "elapsed_time": "2:54:05", "remaining_time": "2:09:53"}
+{"current_steps": 450, "total_steps": 777, "loss": 0.2819, "lr": 1.8070409802638985e-05, "epoch": 4.054054054054054, "percentage": 57.92, "elapsed_time": "2:55:57", "remaining_time": "2:07:52"}
+{"current_steps": 455, "total_steps": 777, "loss": 0.2679, "lr": 1.762359029328768e-05, "epoch": 4.099099099099099, "percentage": 58.56, "elapsed_time": "2:57:47", "remaining_time": "2:05:49"}
+{"current_steps": 460, "total_steps": 777, "loss": 0.2655, "lr": 1.7177970803824714e-05, "epoch": 4.1441441441441444, "percentage": 59.2, "elapsed_time": "2:59:43", "remaining_time": "2:03:50"}
+{"current_steps": 465, "total_steps": 777, "loss": 0.273, "lr": 1.6733776359526024e-05, "epoch": 4.1891891891891895, "percentage": 59.85, "elapsed_time": "3:01:34", "remaining_time": "2:01:49"}
+{"current_steps": 470, "total_steps": 777, "loss": 0.2758, "lr": 1.6291231266059912e-05, "epoch": 4.2342342342342345, "percentage": 60.49, "elapsed_time": "3:03:34", "remaining_time": "1:59:54"}
+{"current_steps": 475, "total_steps": 777, "loss": 0.2771, "lr": 1.585055899621904e-05, "epoch": 4.2792792792792795, "percentage": 61.13, "elapsed_time": "3:05:32", "remaining_time": "1:57:57"}
+{"current_steps": 480, "total_steps": 777, "loss": 0.2736, "lr": 1.5411982077072925e-05, "epoch": 4.324324324324325, "percentage": 61.78, "elapsed_time": "3:07:30", "remaining_time": "1:56:01"}
+{"current_steps": 485, "total_steps": 777, "loss": 0.2636, "lr": 1.497572197759811e-05, "epoch": 4.36936936936937, "percentage": 62.42, "elapsed_time": "3:09:32", "remaining_time": "1:54:06"}
+{"current_steps": 490, "total_steps": 777, "loss": 0.2721, "lr": 1.4541998996842503e-05, "epoch": 4.414414414414415, "percentage": 63.06, "elapsed_time": "3:11:27", "remaining_time": "1:52:08"}
+{"current_steps": 495, "total_steps": 777, "loss": 0.2669, "lr": 1.4111032152680621e-05, "epoch": 4.45945945945946, "percentage": 63.71, "elapsed_time": "3:13:24", "remaining_time": "1:50:10"}
+{"current_steps": 500, "total_steps": 777, "loss": 0.2704, "lr": 1.3683039071215717e-05, "epoch": 4.504504504504505, "percentage": 64.35, "elapsed_time": "3:15:23", "remaining_time": "1:48:14"}
+{"current_steps": 505, "total_steps": 777, "loss": 0.2746, "lr": 1.3258235876884735e-05, "epoch": 4.54954954954955, "percentage": 64.99, "elapsed_time": "3:17:25", "remaining_time": "1:46:20"}
+{"current_steps": 510, "total_steps": 777, "loss": 0.2572, "lr": 1.283683708332159e-05, "epoch": 4.594594594594595, "percentage": 65.64, "elapsed_time": "3:19:12", "remaining_time": "1:44:17"}
+{"current_steps": 515, "total_steps": 777, "loss": 0.2538, "lr": 1.2419055485033788e-05, "epoch": 4.63963963963964, "percentage": 66.28, "elapsed_time": "3:21:04", "remaining_time": "1:42:17"}
+{"current_steps": 520, "total_steps": 777, "loss": 0.2671, "lr": 1.200510204994724e-05, "epoch": 4.684684684684685, "percentage": 66.92, "elapsed_time": "3:22:58", "remaining_time": "1:40:18"}
+{"current_steps": 525, "total_steps": 777, "loss": 0.283, "lr": 1.1595185812873382e-05, "epoch": 4.72972972972973, "percentage": 67.57, "elapsed_time": "3:24:57", "remaining_time": "1:38:23"}
+{"current_steps": 530, "total_steps": 777, "loss": 0.269, "lr": 1.118951376995251e-05, "epoch": 4.774774774774775, "percentage": 68.21, "elapsed_time": "3:26:57", "remaining_time": "1:36:27"}
+{"current_steps": 535, "total_steps": 777, "loss": 0.2757, "lr": 1.0788290774126549e-05, "epoch": 4.81981981981982, "percentage": 68.85, "elapsed_time": "3:28:55", "remaining_time": "1:34:30"}
+{"current_steps": 540, "total_steps": 777, "loss": 0.2697, "lr": 1.039171943169411e-05, "epoch": 4.864864864864865, "percentage": 69.5, "elapsed_time": "3:30:45", "remaining_time": "1:32:30"}
+{"current_steps": 545, "total_steps": 777, "loss": 0.2582, "lr": 1.0000000000000006e-05, "epoch": 4.90990990990991, "percentage": 70.14, "elapsed_time": "3:32:39", "remaining_time": "1:30:31"}
+{"current_steps": 550, "total_steps": 777, "loss": 0.2702, "lr": 9.613330286310952e-06, "epoch": 4.954954954954955, "percentage": 70.79, "elapsed_time": "3:34:35", "remaining_time": "1:28:34"}
+{"current_steps": 555, "total_steps": 777, "loss": 0.2727, "lr": 9.23190554792847e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "3:36:33", "remaining_time": "1:26:37"}
+{"current_steps": 560, "total_steps": 777, "loss": 0.2649, "lr": 8.855918393589462e-06, "epoch": 5.045045045045045, "percentage": 72.07, "elapsed_time": "3:38:24", "remaining_time": "1:24:37"}
+{"current_steps": 565, "total_steps": 777, "loss": 0.2687, "lr": 8.485558686204215e-06, "epoch": 5.09009009009009, "percentage": 72.72, "elapsed_time": "3:40:13", "remaining_time": "1:22:37"}
+{"current_steps": 570, "total_steps": 777, "loss": 0.2547, "lr": 8.121013446981004e-06, "epoch": 5.135135135135135, "percentage": 73.36, "elapsed_time": "3:42:16", "remaining_time": "1:20:43"}
+{"current_steps": 575, "total_steps": 777, "loss": 0.2613, "lr": 7.762466760985651e-06, "epoch": 5.18018018018018, "percentage": 74.0, "elapsed_time": "3:44:06", "remaining_time": "1:18:43"}
+{"current_steps": 580, "total_steps": 777, "loss": 0.2692, "lr": 7.410099684183738e-06, "epoch": 5.225225225225225, "percentage": 74.65, "elapsed_time": "3:46:09", "remaining_time": "1:16:49"}
+{"current_steps": 585, "total_steps": 777, "loss": 0.2625, "lr": 7.064090152012488e-06, "epoch": 5.27027027027027, "percentage": 75.29, "elapsed_time": "3:48:05", "remaining_time": "1:14:51"}
+{"current_steps": 590, "total_steps": 777, "loss": 0.2592, "lr": 6.72461288952835e-06, "epoch": 5.315315315315315, "percentage": 75.93, "elapsed_time": "3:50:02", "remaining_time": "1:12:54"}
+{"current_steps": 595, "total_steps": 777, "loss": 0.263, "lr": 6.391839323175788e-06, "epoch": 5.36036036036036, "percentage": 76.58, "elapsed_time": "3:51:59", "remaining_time": "1:10:57"}
+{"current_steps": 600, "total_steps": 777, "loss": 0.277, "lr": 6.065937494221763e-06, "epoch": 5.405405405405405, "percentage": 77.22, "elapsed_time": "3:53:56", "remaining_time": "1:09:00"}
+{"current_steps": 605, "total_steps": 777, "loss": 0.2712, "lr": 5.747071973899634e-06, "epoch": 5.45045045045045, "percentage": 77.86, "elapsed_time": "3:55:59", "remaining_time": "1:07:05"}
+{"current_steps": 610, "total_steps": 777, "loss": 0.2633, "lr": 5.4354037803053124e-06, "epoch": 5.495495495495495, "percentage": 78.51, "elapsed_time": "3:57:52", "remaining_time": "1:05:07"}
+{"current_steps": 615, "total_steps": 777, "loss": 0.2467, "lr": 5.131090297087682e-06, "epoch": 5.54054054054054, "percentage": 79.15, "elapsed_time": "3:59:46", "remaining_time": "1:03:09"}
+{"current_steps": 620, "total_steps": 777, "loss": 0.2828, "lr": 4.834285193974277e-06, "epoch": 5.585585585585585, "percentage": 79.79, "elapsed_time": "4:01:36", "remaining_time": "1:01:10"}
+{"current_steps": 625, "total_steps": 777, "loss": 0.267, "lr": 4.545138349172418e-06, "epoch": 5.63063063063063, "percentage": 80.44, "elapsed_time": "4:03:22", "remaining_time": "0:59:11"}
+{"current_steps": 630, "total_steps": 777, "loss": 0.2685, "lr": 4.263795773684929e-06, "epoch": 5.675675675675675, "percentage": 81.08, "elapsed_time": "4:05:18", "remaining_time": "0:57:14"}
+{"current_steps": 635, "total_steps": 777, "loss": 0.2682, "lr": 3.9903995375787245e-06, "epoch": 5.7207207207207205, "percentage": 81.72, "elapsed_time": "4:07:10", "remaining_time": "0:55:16"}
+{"current_steps": 640, "total_steps": 777, "loss": 0.2712, "lr": 3.7250876982433947e-06, "epoch": 5.7657657657657655, "percentage": 82.37, "elapsed_time": "4:09:06", "remaining_time": "0:53:19"}
+{"current_steps": 645, "total_steps": 777, "loss": 0.2673, "lr": 3.4679942306761484e-06, "epoch": 5.8108108108108105, "percentage": 83.01, "elapsed_time": "4:10:58", "remaining_time": "0:51:21"}
+{"current_steps": 650, "total_steps": 777, "loss": 0.2626, "lr": 3.219248959828196e-06, "epoch": 5.8558558558558556, "percentage": 83.66, "elapsed_time": "4:13:03", "remaining_time": "0:49:26"}
+{"current_steps": 655, "total_steps": 777, "loss": 0.2614, "lr": 2.9789774950468265e-06, "epoch": 5.900900900900901, "percentage": 84.3, "elapsed_time": "4:14:49", "remaining_time": "0:47:27"}
+{"current_steps": 660, "total_steps": 777, "loss": 0.2732, "lr": 2.747301166646221e-06, "epoch": 5.945945945945946, "percentage": 84.94, "elapsed_time": "4:16:48", "remaining_time": "0:45:31"}
+{"current_steps": 665, "total_steps": 777, "loss": 0.2579, "lr": 2.524336964639067e-06, "epoch": 5.990990990990991, "percentage": 85.59, "elapsed_time": "4:18:42", "remaining_time": "0:43:34"}
+{"current_steps": 670, "total_steps": 777, "loss": 0.2628, "lr": 2.3101974796599015e-06, "epoch": 6.036036036036036, "percentage": 86.23, "elapsed_time": "4:20:34", "remaining_time": "0:41:36"}
+{"current_steps": 675, "total_steps": 777, "loss": 0.2705, "lr": 2.1049908461100086e-06, "epoch": 6.081081081081081, "percentage": 86.87, "elapsed_time": "4:22:36", "remaining_time": "0:39:40"}
+{"current_steps": 680, "total_steps": 777, "loss": 0.2652, "lr": 1.9088206875526128e-06, "epoch": 6.126126126126126, "percentage": 87.52, "elapsed_time": "4:24:39", "remaining_time": "0:37:45"}
+{"current_steps": 685, "total_steps": 777, "loss": 0.2655, "lr": 1.7217860643858797e-06, "epoch": 6.171171171171171, "percentage": 88.16, "elapsed_time": "4:26:35", "remaining_time": "0:35:48"}
+{"current_steps": 690, "total_steps": 777, "loss": 0.2625, "lr": 1.5439814238202356e-06, "epoch": 6.216216216216216, "percentage": 88.8, "elapsed_time": "4:28:20", "remaining_time": "0:33:50"}
+{"current_steps": 695, "total_steps": 777, "loss": 0.2657, "lr": 1.3754965521851582e-06, "epoch": 6.261261261261261, "percentage": 89.45, "elapsed_time": "4:30:13", "remaining_time": "0:31:52"}
+{"current_steps": 700, "total_steps": 777, "loss": 0.2658, "lr": 1.2164165295896392e-06, "epoch": 6.306306306306306, "percentage": 90.09, "elapsed_time": "4:32:12", "remaining_time": "0:29:56"}
+{"current_steps": 705, "total_steps": 777, "loss": 0.268, "lr": 1.0668216869591098e-06, "epoch": 6.351351351351352, "percentage": 90.73, "elapsed_time": "4:34:06", "remaining_time": "0:27:59"}
+{"current_steps": 710, "total_steps": 777, "loss": 0.2607, "lr": 9.267875654706015e-07, "epoch": 6.396396396396397, "percentage": 91.38, "elapsed_time": "4:35:55", "remaining_time": "0:26:02"}
+{"current_steps": 715, "total_steps": 777, "loss": 0.2523, "lr": 7.963848784065753e-07, "epoch": 6.441441441441442, "percentage": 92.02, "elapsed_time": "4:37:56", "remaining_time": "0:24:06"}
+{"current_steps": 720, "total_steps": 777, "loss": 0.2642, "lr": 6.756794754467045e-07, "epoch": 6.486486486486487, "percentage": 92.66, "elapsed_time": "4:39:52", "remaining_time": "0:22:09"}
+{"current_steps": 725, "total_steps": 777, "loss": 0.2579, "lr": 5.647323094156565e-07, "epoch": 6.531531531531532, "percentage": 93.31, "elapsed_time": "4:41:42", "remaining_time": "0:20:12"}
+{"current_steps": 730, "total_steps": 777, "loss": 0.2618, "lr": 4.635994055036208e-07, "epoch": 6.576576576576577, "percentage": 93.95, "elapsed_time": "4:43:37", "remaining_time": "0:18:15"}
+{"current_steps": 735, "total_steps": 777, "loss": 0.264, "lr": 3.723318329751746e-07, "epoch": 6.621621621621622, "percentage": 94.59, "elapsed_time": "4:45:30", "remaining_time": "0:16:18"}
+{"current_steps": 740, "total_steps": 777, "loss": 0.2668, "lr": 2.9097567938074943e-07, "epoch": 6.666666666666667, "percentage": 95.24, "elapsed_time": "4:47:22", "remaining_time": "0:14:22"}
+{"current_steps": 745, "total_steps": 777, "loss": 0.2649, "lr": 2.1957202728370542e-07, "epoch": 6.711711711711712, "percentage": 95.88, "elapsed_time": "4:49:13", "remaining_time": "0:12:25"}
+{"current_steps": 750, "total_steps": 777, "loss": 0.2483, "lr": 1.5815693351480587e-07, "epoch": 6.756756756756757, "percentage": 96.53, "elapsed_time": "4:51:06", "remaining_time": "0:10:28"}
+{"current_steps": 755, "total_steps": 777, "loss": 0.2714, "lr": 1.0676141096453097e-07, "epoch": 6.801801801801802, "percentage": 97.17, "elapsed_time": "4:52:56", "remaining_time": "0:08:32"}
+{"current_steps": 760, "total_steps": 777, "loss": 0.269, "lr": 6.541141292243814e-08, "epoch": 6.846846846846847, "percentage": 97.81, "elapsed_time": "4:54:48", "remaining_time": "0:06:35"}
+{"current_steps": 765, "total_steps": 777, "loss": 0.2628, "lr": 3.412781997148784e-08, "epoch": 6.891891891891892, "percentage": 98.46, "elapsed_time": "4:56:45", "remaining_time": "0:04:39"}
+{"current_steps": 770, "total_steps": 777, "loss": 0.2532, "lr": 1.29264294439424e-08, "epoch": 6.936936936936937, "percentage": 99.1, "elapsed_time": "4:58:36", "remaining_time": "0:02:42"}
+{"current_steps": 775, "total_steps": 777, "loss": 0.2576, "lr": 1.817947444149315e-09, "epoch": 6.981981981981982, "percentage": 99.74, "elapsed_time": "5:00:40", "remaining_time": "0:00:46"}
+{"current_steps": 777, "total_steps": 777, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "5:01:37", "remaining_time": "0:00:00"}
+{"current_steps": 777, "total_steps": 777, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 777, "total_steps": 777, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 777, "total_steps": 777, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
+{"current_steps": 777, "total_steps": 777, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1748 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 777,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04504504504504504,
+      "grad_norm": 12.213179482888265,
+      "learning_rate": 2.0512820512820513e-06,
+      "loss": 0.6951,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.21766051650047302,
+      "step": 5,
+      "valid_targets_mean": 3509.5,
+      "valid_targets_min": 811
+    },
+    {
+      "epoch": 0.09009009009009009,
+      "grad_norm": 7.570539034885599,
+      "learning_rate": 4.615384615384616e-06,
+      "loss": 0.6634,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1856536865234375,
+      "step": 10,
+      "valid_targets_mean": 3624.1,
+      "valid_targets_min": 292
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 2.6810961238620084,
+      "learning_rate": 7.17948717948718e-06,
+      "loss": 0.5718,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1723824441432953,
+      "step": 15,
+      "valid_targets_mean": 3464.6,
+      "valid_targets_min": 483
+    },
+    {
+      "epoch": 0.18018018018018017,
+      "grad_norm": 1.2227064393103297,
+      "learning_rate": 9.743589743589744e-06,
+      "loss": 0.5115,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.17001838982105255,
+      "step": 20,
+      "valid_targets_mean": 3984.6,
+      "valid_targets_min": 488
+    },
+    {
+      "epoch": 0.22522522522522523,
+      "grad_norm": 0.8898938226580776,
+      "learning_rate": 1.230769230769231e-05,
+      "loss": 0.4871,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.17259931564331055,
+      "step": 25,
+      "valid_targets_mean": 4314.8,
+      "valid_targets_min": 456
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.6432303488130432,
+      "learning_rate": 1.4871794871794874e-05,
+      "loss": 0.4791,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.2156098484992981,
+      "step": 30,
+      "valid_targets_mean": 5139.6,
+      "valid_targets_min": 285
+    },
+    {
+      "epoch": 0.3153153153153153,
+      "grad_norm": 0.420063730489216,
+      "learning_rate": 1.7435897435897438e-05,
+      "loss": 0.4542,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.14423362910747528,
+      "step": 35,
+      "valid_targets_mean": 4965.8,
+      "valid_targets_min": 610
+    },
+    {
+      "epoch": 0.36036036036036034,
+      "grad_norm": 0.4108255376992912,
+      "learning_rate": 2e-05,
+      "loss": 0.4362,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1998554766178131,
+      "step": 40,
+      "valid_targets_mean": 5446.5,
+      "valid_targets_min": 626
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.3763657695313296,
+      "learning_rate": 2.2564102564102566e-05,
+      "loss": 0.4108,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1512545347213745,
+      "step": 45,
+      "valid_targets_mean": 4206.4,
+      "valid_targets_min": 484
+    },
+    {
+      "epoch": 0.45045045045045046,
+      "grad_norm": 0.3362402566929759,
+      "learning_rate": 2.512820512820513e-05,
+      "loss": 0.4218,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.13444261252880096,
+      "step": 50,
+      "valid_targets_mean": 3656.3,
+      "valid_targets_min": 398
+    },
+    {
+      "epoch": 0.4954954954954955,
+      "grad_norm": 0.29451984543253784,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 0.4003,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11262520402669907,
+      "step": 55,
+      "valid_targets_mean": 4485.2,
+      "valid_targets_min": 606
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.29803110540835986,
+      "learning_rate": 3.0256410256410257e-05,
+      "loss": 0.3955,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.14588972926139832,
+      "step": 60,
+      "valid_targets_mean": 4701.9,
+      "valid_targets_min": 470
+    },
+    {
+      "epoch": 0.5855855855855856,
+      "grad_norm": 0.8391493968662852,
+      "learning_rate": 3.282051282051282e-05,
+      "loss": 0.3757,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09588639438152313,
+      "step": 65,
+      "valid_targets_mean": 4384.8,
+      "valid_targets_min": 664
+    },
+    {
+      "epoch": 0.6306306306306306,
+      "grad_norm": 0.2886198856062646,
+      "learning_rate": 3.538461538461539e-05,
+      "loss": 0.3825,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11931118369102478,
+      "step": 70,
+      "valid_targets_mean": 3792.6,
+      "valid_targets_min": 529
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.26848114245238813,
+      "learning_rate": 3.794871794871795e-05,
+      "loss": 0.3694,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11248503625392914,
+      "step": 75,
+      "valid_targets_mean": 4532.7,
+      "valid_targets_min": 536
+    },
+    {
+      "epoch": 0.7207207207207207,
+      "grad_norm": 0.2710447890224146,
+      "learning_rate": 3.999979800311937e-05,
+      "loss": 0.356,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10272569209337234,
+      "step": 80,
+      "valid_targets_mean": 3715.0,
+      "valid_targets_min": 404
+    },
+    {
+      "epoch": 0.7657657657657657,
+      "grad_norm": 0.26845203304003346,
+      "learning_rate": 3.999272854071669e-05,
+      "loss": 0.3409,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08947348594665527,
+      "step": 85,
+      "valid_targets_mean": 4057.3,
+      "valid_targets_min": 562
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.28500381948167564,
+      "learning_rate": 3.99755633141858e-05,
+      "loss": 0.347,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11878690123558044,
+      "step": 90,
+      "valid_targets_mean": 3781.4,
+      "valid_targets_min": 513
+    },
+    {
+      "epoch": 0.8558558558558559,
+      "grad_norm": 0.2897579470253114,
+      "learning_rate": 3.994831099148205e-05,
+      "loss": 0.3339,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09589523077011108,
+      "step": 95,
+      "valid_targets_mean": 3537.8,
+      "valid_targets_min": 410
+    },
+    {
+      "epoch": 0.9009009009009009,
+      "grad_norm": 0.37166782552169725,
+      "learning_rate": 3.991098533425988e-05,
+      "loss": 0.3304,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.12742844223976135,
+      "step": 100,
+      "valid_targets_mean": 4120.6,
+      "valid_targets_min": 625
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.2721758202080061,
+      "learning_rate": 3.9863605190923655e-05,
+      "loss": 0.3353,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1229485422372818,
+      "step": 105,
+      "valid_targets_mean": 4571.3,
+      "valid_targets_min": 536
+    },
+    {
+      "epoch": 0.990990990990991,
+      "grad_norm": 0.2716104773435794,
+      "learning_rate": 3.9806194487109636e-05,
+      "loss": 0.3293,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1011948436498642,
+      "step": 110,
+      "valid_targets_mean": 3915.6,
+      "valid_targets_min": 536
+    },
+    {
+      "epoch": 1.0360360360360361,
+      "grad_norm": 0.4113397770099122,
+      "learning_rate": 3.9738782213604305e-05,
+      "loss": 0.3461,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.12486414611339569,
+      "step": 115,
+      "valid_targets_mean": 4712.1,
+      "valid_targets_min": 663
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.2775525865510845,
+      "learning_rate": 3.9661402411704794e-05,
+      "loss": 0.3399,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09220485389232635,
+      "step": 120,
+      "valid_targets_mean": 3749.4,
+      "valid_targets_min": 381
+    },
+    {
+      "epoch": 1.1261261261261262,
+      "grad_norm": 0.26661128827223074,
+      "learning_rate": 3.957409415602899e-05,
+      "loss": 0.3244,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11258970201015472,
+      "step": 125,
+      "valid_targets_mean": 4166.4,
+      "valid_targets_min": 395
+    },
+    {
+      "epoch": 1.1711711711711712,
+      "grad_norm": 0.27815633052261163,
+      "learning_rate": 3.947690153478396e-05,
+      "loss": 0.3128,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1220335066318512,
+      "step": 130,
+      "valid_targets_mean": 4006.0,
+      "valid_targets_min": 525
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.2758450156551077,
+      "learning_rate": 3.936987362750266e-05,
+      "loss": 0.3319,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10510491579771042,
+      "step": 135,
+      "valid_targets_mean": 4167.9,
+      "valid_targets_min": 576
+    },
+    {
+      "epoch": 1.2612612612612613,
+      "grad_norm": 0.251293693452417,
+      "learning_rate": 3.925306448026011e-05,
+      "loss": 0.3272,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0853872001171112,
+      "step": 140,
+      "valid_targets_mean": 2816.8,
+      "valid_targets_min": 627
+    },
+    {
+      "epoch": 1.3063063063063063,
+      "grad_norm": 0.25769295208742854,
+      "learning_rate": 3.912653307838173e-05,
+      "loss": 0.3191,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11158967018127441,
+      "step": 145,
+      "valid_targets_mean": 4418.5,
+      "valid_targets_min": 688
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.28387795710075575,
+      "learning_rate": 3.899034331665733e-05,
+      "loss": 0.3132,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.13492226600646973,
+      "step": 150,
+      "valid_targets_mean": 4884.4,
+      "valid_targets_min": 273
+    },
+    {
+      "epoch": 1.3963963963963963,
+      "grad_norm": 0.25474866914888333,
+      "learning_rate": 3.884456396707611e-05,
+      "loss": 0.3172,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1127757877111435,
+      "step": 155,
+      "valid_targets_mean": 5368.9,
+      "valid_targets_min": 563
+    },
+    {
+      "epoch": 1.4414414414414414,
+      "grad_norm": 0.2801065026702884,
+      "learning_rate": 3.8689268644098715e-05,
+      "loss": 0.3205,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11982893943786621,
+      "step": 160,
+      "valid_targets_mean": 4552.2,
+      "valid_targets_min": 487
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.26487929604501453,
+      "learning_rate": 3.852453576748397e-05,
+      "loss": 0.3006,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09722155332565308,
+      "step": 165,
+      "valid_targets_mean": 4420.7,
+      "valid_targets_min": 489
+    },
+    {
+      "epoch": 1.5315315315315314,
+      "grad_norm": 0.2755186974342944,
+      "learning_rate": 3.835044852268921e-05,
+      "loss": 0.3053,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09628415107727051,
+      "step": 170,
+      "valid_targets_mean": 3981.4,
+      "valid_targets_min": 521
+    },
+    {
+      "epoch": 1.5765765765765765,
+      "grad_norm": 0.2779173348107798,
+      "learning_rate": 3.816709481886386e-05,
+      "loss": 0.3197,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10215558111667633,
+      "step": 175,
+      "valid_targets_mean": 4846.7,
+      "valid_targets_min": 957
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.27126966265543495,
+      "learning_rate": 3.7974567244457886e-05,
+      "loss": 0.3112,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1354570835828781,
+      "step": 180,
+      "valid_targets_mean": 4403.5,
+      "valid_targets_min": 648
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.2880963639114082,
+      "learning_rate": 3.777296302046719e-05,
+      "loss": 0.3096,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08432003855705261,
+      "step": 185,
+      "valid_targets_mean": 3485.8,
+      "valid_targets_min": 367
+    },
+    {
+      "epoch": 1.7117117117117115,
+      "grad_norm": 0.2706373394484155,
+      "learning_rate": 3.756238395133972e-05,
+      "loss": 0.302,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11862757056951523,
+      "step": 190,
+      "valid_targets_mean": 4555.7,
+      "valid_targets_min": 693
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.3075395709355726,
+      "learning_rate": 3.734293637356719e-05,
+      "loss": 0.3059,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.12262945622205734,
+      "step": 195,
+      "valid_targets_mean": 4144.0,
+      "valid_targets_min": 434
+    },
+    {
+      "epoch": 1.8018018018018018,
+      "grad_norm": 0.25683284776009463,
+      "learning_rate": 3.711473110198805e-05,
+      "loss": 0.3168,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.13503742218017578,
+      "step": 200,
+      "valid_targets_mean": 4794.2,
+      "valid_targets_min": 418
+    },
+    {
+      "epoch": 1.8468468468468469,
+      "grad_norm": 0.2652406976146456,
+      "learning_rate": 3.687788337382918e-05,
+      "loss": 0.2959,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06610264629125595,
+      "step": 205,
+      "valid_targets_mean": 3298.5,
+      "valid_targets_min": 534
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.2913009925285956,
+      "learning_rate": 3.663251279051431e-05,
+      "loss": 0.2993,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09436690807342529,
+      "step": 210,
+      "valid_targets_mean": 3334.3,
+      "valid_targets_min": 367
+    },
+    {
+      "epoch": 1.936936936936937,
+      "grad_norm": 0.31970742341653646,
+      "learning_rate": 3.6378743257268696e-05,
+      "loss": 0.2999,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07659884542226791,
+      "step": 215,
+      "valid_targets_mean": 3069.9,
+      "valid_targets_min": 432
+    },
+    {
+      "epoch": 1.981981981981982,
+      "grad_norm": 0.2562136000194939,
+      "learning_rate": 3.6116702920550445e-05,
+      "loss": 0.3047,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10911617428064346,
+      "step": 220,
+      "valid_targets_mean": 4779.1,
+      "valid_targets_min": 561
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.2724809389688923,
+      "learning_rate": 3.58465241033402e-05,
+      "loss": 0.2942,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09413851797580719,
+      "step": 225,
+      "valid_targets_mean": 5175.0,
+      "valid_targets_min": 611
+    },
+    {
+      "epoch": 2.0720720720720722,
+      "grad_norm": 0.37889132983663676,
+      "learning_rate": 3.556834323832174e-05,
+      "loss": 0.2942,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.12257418036460876,
+      "step": 230,
+      "valid_targets_mean": 4611.3,
+      "valid_targets_min": 656
+    },
+    {
+      "epoch": 2.1171171171171173,
+      "grad_norm": 0.2788335973338977,
+      "learning_rate": 3.528230079898734e-05,
+      "loss": 0.2918,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11126174032688141,
+      "step": 235,
+      "valid_targets_mean": 4446.8,
+      "valid_targets_min": 563
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.2808879591424535,
+      "learning_rate": 3.498854122870263e-05,
+      "loss": 0.2903,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09562689065933228,
+      "step": 240,
+      "valid_targets_mean": 4357.7,
+      "valid_targets_min": 482
+    },
+    {
+      "epoch": 2.2072072072072073,
+      "grad_norm": 0.254732860948126,
+      "learning_rate": 3.4687212867766696e-05,
+      "loss": 0.2968,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10171202570199966,
+      "step": 245,
+      "valid_targets_mean": 4400.3,
+      "valid_targets_min": 583
+    },
+    {
+      "epoch": 2.2522522522522523,
+      "grad_norm": 0.25383907196480765,
+      "learning_rate": 3.437846787850454e-05,
+      "loss": 0.3055,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11306051164865494,
+      "step": 250,
+      "valid_targets_mean": 5253.9,
+      "valid_targets_min": 529
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.2651689069419142,
+      "learning_rate": 3.4062462168429267e-05,
+      "loss": 0.2857,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10121257603168488,
+      "step": 255,
+      "valid_targets_mean": 4426.2,
+      "valid_targets_min": 565
+    },
+    {
+      "epoch": 2.3423423423423424,
+      "grad_norm": 0.26957637460385697,
+      "learning_rate": 3.373935531151326e-05,
+      "loss": 0.2905,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10117916762828827,
+      "step": 260,
+      "valid_targets_mean": 3801.0,
+      "valid_targets_min": 452
+    },
+    {
+      "epoch": 2.3873873873873874,
+      "grad_norm": 0.2656592182447648,
+      "learning_rate": 3.3409310467607824e-05,
+      "loss": 0.2858,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08973188698291779,
+      "step": 265,
+      "valid_targets_mean": 4057.0,
+      "valid_targets_min": 576
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.2580157565140095,
+      "learning_rate": 3.307249430005203e-05,
+      "loss": 0.2982,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09819403290748596,
+      "step": 270,
+      "valid_targets_mean": 4610.7,
+      "valid_targets_min": 368
+    },
+    {
+      "epoch": 2.4774774774774775,
+      "grad_norm": 0.2755474257162277,
+      "learning_rate": 3.272907689151245e-05,
+      "loss": 0.3072,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10150294005870819,
+      "step": 275,
+      "valid_targets_mean": 4629.2,
+      "valid_targets_min": 323
+    },
+    {
+      "epoch": 2.5225225225225225,
+      "grad_norm": 0.27610850469305503,
+      "learning_rate": 3.237923165809619e-05,
+      "loss": 0.2958,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0950014516711235,
+      "step": 280,
+      "valid_targets_mean": 3554.4,
+      "valid_targets_min": 381
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.2611418490003288,
+      "learning_rate": 3.202313526178067e-05,
+      "loss": 0.2995,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1143759936094284,
+      "step": 285,
+      "valid_targets_mean": 4839.2,
+      "valid_targets_min": 446
+    },
+    {
+      "epoch": 2.6126126126126126,
+      "grad_norm": 0.2477097409751127,
+      "learning_rate": 3.16609675212043e-05,
+      "loss": 0.2818,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07015109807252884,
+      "step": 290,
+      "valid_targets_mean": 4588.3,
+      "valid_targets_min": 700
+    },
+    {
+      "epoch": 2.6576576576576576,
+      "grad_norm": 0.2974710482372013,
+      "learning_rate": 3.1292911320863104e-05,
+      "loss": 0.2959,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10549891740083694,
+      "step": 295,
+      "valid_targets_mean": 3873.7,
+      "valid_targets_min": 747
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.2385129443001723,
+      "learning_rate": 3.091915251875928e-05,
+      "loss": 0.2936,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08176982402801514,
+      "step": 300,
+      "valid_targets_mean": 4635.4,
+      "valid_targets_min": 640
+    },
+    {
+      "epoch": 2.7477477477477477,
+      "grad_norm": 0.2690939226544654,
+      "learning_rate": 3.053987985254806e-05,
+      "loss": 0.2841,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0824771448969841,
+      "step": 305,
+      "valid_targets_mean": 4034.1,
+      "valid_targets_min": 612
+    },
+    {
+      "epoch": 2.7927927927927927,
+      "grad_norm": 0.23489549980956795,
+      "learning_rate": 3.015528484423059e-05,
+      "loss": 0.2828,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07864581048488617,
+      "step": 310,
+      "valid_targets_mean": 3631.1,
+      "valid_targets_min": 612
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.25255671921419315,
+      "learning_rate": 2.9765561703440688e-05,
+      "loss": 0.293,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07940647006034851,
+      "step": 315,
+      "valid_targets_mean": 4242.5,
+      "valid_targets_min": 713
+    },
+    {
+      "epoch": 2.8828828828828827,
+      "grad_norm": 0.25230980048173096,
+      "learning_rate": 2.937090722937446e-05,
+      "loss": 0.2753,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10888753086328506,
+      "step": 320,
+      "valid_targets_mean": 4590.7,
+      "valid_targets_min": 547
+    },
+    {
+      "epoch": 2.9279279279279278,
+      "grad_norm": 0.24800878753672767,
+      "learning_rate": 2.897152071141225e-05,
+      "loss": 0.2873,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07101110368967056,
+      "step": 325,
+      "valid_targets_mean": 3616.2,
+      "valid_targets_min": 550
+    },
+    {
+      "epoch": 2.972972972972973,
+      "grad_norm": 0.2616860912144822,
+      "learning_rate": 2.8567603828483125e-05,
+      "loss": 0.2975,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.133597731590271,
+      "step": 330,
+      "valid_targets_mean": 5871.1,
+      "valid_targets_min": 439
+    },
+    {
+      "epoch": 3.018018018018018,
+      "grad_norm": 0.25331466603093555,
+      "learning_rate": 2.8159360547222716e-05,
+      "loss": 0.2851,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07654231786727905,
+      "step": 335,
+      "valid_targets_mean": 4105.6,
+      "valid_targets_min": 515
+    },
+    {
+      "epoch": 3.063063063063063,
+      "grad_norm": 0.2657531594205501,
+      "learning_rate": 2.7746997018975804e-05,
+      "loss": 0.2825,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08719119429588318,
+      "step": 340,
+      "valid_targets_mean": 3864.1,
+      "valid_targets_min": 595
+    },
+    {
+      "epoch": 3.108108108108108,
+      "grad_norm": 0.6735205939178378,
+      "learning_rate": 2.733072147569572e-05,
+      "loss": 0.2749,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08523587137460709,
+      "step": 345,
+      "valid_targets_mean": 4730.9,
+      "valid_targets_min": 659
+    },
+    {
+      "epoch": 3.153153153153153,
+      "grad_norm": 0.2591942491892,
+      "learning_rate": 2.6910744124793046e-05,
+      "loss": 0.2788,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10307951271533966,
+      "step": 350,
+      "valid_targets_mean": 4142.2,
+      "valid_targets_min": 664
+    },
+    {
+      "epoch": 3.1981981981981984,
+      "grad_norm": 0.24596341545878944,
+      "learning_rate": 2.648727704298685e-05,
+      "loss": 0.2794,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08397462218999863,
+      "step": 355,
+      "valid_targets_mean": 4468.1,
+      "valid_targets_min": 815
+    },
+    {
+      "epoch": 3.2432432432432434,
+      "grad_norm": 0.28207232487891526,
+      "learning_rate": 2.6060534069211877e-05,
+      "loss": 0.2876,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11069733649492264,
+      "step": 360,
+      "valid_targets_mean": 4422.8,
+      "valid_targets_min": 703
+    },
+    {
+      "epoch": 3.2882882882882885,
+      "grad_norm": 0.2512548681824469,
+      "learning_rate": 2.5630730696635953e-05,
+      "loss": 0.2773,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09579600393772125,
+      "step": 365,
+      "valid_targets_mean": 4744.6,
+      "valid_targets_min": 580
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.26070640673282175,
+      "learning_rate": 2.5198083963841988e-05,
+      "loss": 0.2824,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09562422335147858,
+      "step": 370,
+      "valid_targets_mean": 4330.3,
+      "valid_targets_min": 503
+    },
+    {
+      "epoch": 3.3783783783783785,
+      "grad_norm": 0.2568330889976537,
+      "learning_rate": 2.4762812345229622e-05,
+      "loss": 0.2846,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07404516637325287,
+      "step": 375,
+      "valid_targets_mean": 3901.9,
+      "valid_targets_min": 724
+    },
+    {
+      "epoch": 3.4234234234234235,
+      "grad_norm": 0.25175456004756475,
+      "learning_rate": 2.4325135640691823e-05,
+      "loss": 0.2821,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10944640636444092,
+      "step": 380,
+      "valid_targets_mean": 5086.4,
+      "valid_targets_min": 583
+    },
+    {
+      "epoch": 3.4684684684684686,
+      "grad_norm": 0.26905322183252883,
+      "learning_rate": 2.388527486462212e-05,
+      "loss": 0.2693,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1297810822725296,
+      "step": 385,
+      "valid_targets_mean": 5236.8,
+      "valid_targets_min": 552
+    },
+    {
+      "epoch": 3.5135135135135136,
+      "grad_norm": 0.24924455050919309,
+      "learning_rate": 2.3443452134308565e-05,
+      "loss": 0.2775,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07704746723175049,
+      "step": 390,
+      "valid_targets_mean": 4304.3,
+      "valid_targets_min": 716
+    },
+    {
+      "epoch": 3.5585585585585586,
+      "grad_norm": 0.2800927179852231,
+      "learning_rate": 2.299989055777079e-05,
+      "loss": 0.276,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11317361146211624,
+      "step": 395,
+      "valid_targets_mean": 4685.0,
+      "valid_targets_min": 581
+    },
+    {
+      "epoch": 3.6036036036036037,
+      "grad_norm": 0.27986795372322626,
+      "learning_rate": 2.2554814121096748e-05,
+      "loss": 0.2924,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.12253560870885849,
+      "step": 400,
+      "valid_targets_mean": 5609.9,
+      "valid_targets_min": 755
+    },
+    {
+      "epoch": 3.6486486486486487,
+      "grad_norm": 0.5289053951258326,
+      "learning_rate": 2.2108447575336015e-05,
+      "loss": 0.2783,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08305458724498749,
+      "step": 405,
+      "valid_targets_mean": 4169.9,
+      "valid_targets_min": 469
+    },
+    {
+      "epoch": 3.6936936936936937,
+      "grad_norm": 0.2849928276867334,
+      "learning_rate": 2.16610163230069e-05,
+      "loss": 0.2841,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08885318040847778,
+      "step": 410,
+      "valid_targets_mean": 3384.0,
+      "valid_targets_min": 624
+    },
+    {
+      "epoch": 3.7387387387387387,
+      "grad_norm": 0.2592566881525863,
+      "learning_rate": 2.1212746304274482e-05,
+      "loss": 0.2709,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10845595598220825,
+      "step": 415,
+      "valid_targets_mean": 4444.3,
+      "valid_targets_min": 443
+    },
+    {
+      "epoch": 3.7837837837837838,
+      "grad_norm": 0.25283053340082196,
+      "learning_rate": 2.0763863882857242e-05,
+      "loss": 0.2802,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08974164724349976,
+      "step": 420,
+      "valid_targets_mean": 4321.2,
+      "valid_targets_min": 750
+    },
+    {
+      "epoch": 3.828828828828829,
+      "grad_norm": 0.26724652513260666,
+      "learning_rate": 2.031459573171973e-05,
+      "loss": 0.2764,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10250722616910934,
+      "step": 425,
+      "valid_targets_mean": 4252.0,
+      "valid_targets_min": 437
+    },
+    {
+      "epoch": 3.873873873873874,
+      "grad_norm": 0.2741788640534842,
+      "learning_rate": 1.9865168718609142e-05,
+      "loss": 0.2753,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0931130200624466,
+      "step": 430,
+      "valid_targets_mean": 3780.3,
+      "valid_targets_min": 626
+    },
+    {
+      "epoch": 3.918918918918919,
+      "grad_norm": 0.26804478752024036,
+      "learning_rate": 1.9415809791493484e-05,
+      "loss": 0.2599,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09308881312608719,
+      "step": 435,
+      "valid_targets_mean": 4676.5,
+      "valid_targets_min": 504
+    },
+    {
+      "epoch": 3.963963963963964,
+      "grad_norm": 0.2641063176140694,
+      "learning_rate": 1.8966745863959256e-05,
+      "loss": 0.29,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08381877839565277,
+      "step": 440,
+      "valid_targets_mean": 4378.8,
+      "valid_targets_min": 464
+    },
+    {
+      "epoch": 4.009009009009009,
+      "grad_norm": 0.27400842575376944,
+      "learning_rate": 1.851820370062648e-05,
+      "loss": 0.2694,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11071999371051788,
+      "step": 445,
+      "valid_targets_mean": 4126.1,
+      "valid_targets_min": 424
+    },
+    {
+      "epoch": 4.054054054054054,
+      "grad_norm": 0.252436623647466,
+      "learning_rate": 1.8070409802638985e-05,
+      "loss": 0.2819,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08786597847938538,
+      "step": 450,
+      "valid_targets_mean": 3961.2,
+      "valid_targets_min": 252
+    },
+    {
+      "epoch": 4.099099099099099,
+      "grad_norm": 0.24872749257249535,
+      "learning_rate": 1.762359029328768e-05,
+      "loss": 0.2679,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09103064984083176,
+      "step": 455,
+      "valid_targets_mean": 4177.6,
+      "valid_targets_min": 666
+    },
+    {
+      "epoch": 4.1441441441441444,
+      "grad_norm": 0.27264806865130753,
+      "learning_rate": 1.7177970803824714e-05,
+      "loss": 0.2655,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.14946812391281128,
+      "step": 460,
+      "valid_targets_mean": 5840.9,
+      "valid_targets_min": 609
+    },
+    {
+      "epoch": 4.1891891891891895,
+      "grad_norm": 0.2577412462406186,
+      "learning_rate": 1.6733776359526024e-05,
+      "loss": 0.273,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08085731416940689,
+      "step": 465,
+      "valid_targets_mean": 3977.6,
+      "valid_targets_min": 409
+    },
+    {
+      "epoch": 4.2342342342342345,
+      "grad_norm": 0.2792589372950184,
+      "learning_rate": 1.6291231266059912e-05,
+      "loss": 0.2758,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11503882706165314,
+      "step": 470,
+      "valid_targets_mean": 4669.9,
+      "valid_targets_min": 508
+    },
+    {
+      "epoch": 4.2792792792792795,
+      "grad_norm": 0.32367217230222545,
+      "learning_rate": 1.585055899621904e-05,
+      "loss": 0.2771,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11892901360988617,
+      "step": 475,
+      "valid_targets_mean": 3773.2,
+      "valid_targets_min": 474
+    },
+    {
+      "epoch": 4.324324324324325,
+      "grad_norm": 0.258336978621668,
+      "learning_rate": 1.5411982077072925e-05,
+      "loss": 0.2736,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07667964696884155,
+      "step": 480,
+      "valid_targets_mean": 3893.4,
+      "valid_targets_min": 697
+    },
+    {
+      "epoch": 4.36936936936937,
+      "grad_norm": 0.24609619451384765,
+      "learning_rate": 1.497572197759811e-05,
+      "loss": 0.2636,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06371718645095825,
+      "step": 485,
+      "valid_targets_mean": 3523.3,
+      "valid_targets_min": 452
+    },
+    {
+      "epoch": 4.414414414414415,
+      "grad_norm": 0.23835609022118848,
+      "learning_rate": 1.4541998996842503e-05,
+      "loss": 0.2721,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07387564331293106,
+      "step": 490,
+      "valid_targets_mean": 4369.7,
+      "valid_targets_min": 847
+    },
+    {
+      "epoch": 4.45945945945946,
+      "grad_norm": 0.28159658575417745,
+      "learning_rate": 1.4111032152680621e-05,
+      "loss": 0.2669,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09198597073554993,
+      "step": 495,
+      "valid_targets_mean": 4141.6,
+      "valid_targets_min": 374
+    },
+    {
+      "epoch": 4.504504504504505,
+      "grad_norm": 0.2433049555484407,
+      "learning_rate": 1.3683039071215717e-05,
+      "loss": 0.2704,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0909474790096283,
+      "step": 500,
+      "valid_targets_mean": 5381.2,
+      "valid_targets_min": 605
+    },
+    {
+      "epoch": 4.54954954954955,
+      "grad_norm": 0.24437578427894577,
+      "learning_rate": 1.3258235876884735e-05,
+      "loss": 0.2746,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10796620696783066,
+      "step": 505,
+      "valid_targets_mean": 5468.9,
+      "valid_targets_min": 414
+    },
+    {
+      "epoch": 4.594594594594595,
+      "grad_norm": 0.26846184374905985,
+      "learning_rate": 1.283683708332159e-05,
+      "loss": 0.2572,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09838269650936127,
+      "step": 510,
+      "valid_targets_mean": 4829.6,
+      "valid_targets_min": 691
+    },
+    {
+      "epoch": 4.63963963963964,
+      "grad_norm": 0.252099525432998,
+      "learning_rate": 1.2419055485033788e-05,
+      "loss": 0.2538,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08270560204982758,
+      "step": 515,
+      "valid_targets_mean": 4539.7,
+      "valid_targets_min": 758
+    },
+    {
+      "epoch": 4.684684684684685,
+      "grad_norm": 0.22995117395664008,
+      "learning_rate": 1.200510204994724e-05,
+      "loss": 0.2671,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07044124603271484,
+      "step": 520,
+      "valid_targets_mean": 4077.8,
+      "valid_targets_min": 368
+    },
+    {
+      "epoch": 4.72972972972973,
+      "grad_norm": 0.25606569592040784,
+      "learning_rate": 1.1595185812873382e-05,
+      "loss": 0.283,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09904761612415314,
+      "step": 525,
+      "valid_targets_mean": 4964.8,
+      "valid_targets_min": 534
+    },
+    {
+      "epoch": 4.774774774774775,
+      "grad_norm": 0.2421726915390166,
+      "learning_rate": 1.118951376995251e-05,
+      "loss": 0.269,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0894804447889328,
+      "step": 530,
+      "valid_targets_mean": 4745.5,
+      "valid_targets_min": 347
+    },
+    {
+      "epoch": 4.81981981981982,
+      "grad_norm": 0.2408175858115054,
+      "learning_rate": 1.0788290774126549e-05,
+      "loss": 0.2757,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0949220210313797,
+      "step": 535,
+      "valid_targets_mean": 4688.9,
+      "valid_targets_min": 558
+    },
+    {
+      "epoch": 4.864864864864865,
+      "grad_norm": 0.28683879615194635,
+      "learning_rate": 1.039171943169411e-05,
+      "loss": 0.2697,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08911705017089844,
+      "step": 540,
+      "valid_targets_mean": 4208.7,
+      "valid_targets_min": 301
+    },
+    {
+      "epoch": 4.90990990990991,
+      "grad_norm": 0.23515882176666528,
+      "learning_rate": 1.0000000000000006e-05,
+      "loss": 0.2582,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06455663591623306,
+      "step": 545,
+      "valid_targets_mean": 4094.1,
+      "valid_targets_min": 574
+    },
+    {
+      "epoch": 4.954954954954955,
+      "grad_norm": 0.25099139871892956,
+      "learning_rate": 9.613330286310952e-06,
+      "loss": 0.2702,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08976513147354126,
+      "step": 550,
+      "valid_targets_mean": 3831.1,
+      "valid_targets_min": 484
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.23080263557748837,
+      "learning_rate": 9.23190554792847e-06,
+      "loss": 0.2727,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.0830158069729805,
+      "step": 555,
+      "valid_targets_mean": 5210.4,
+      "valid_targets_min": 1005
+    },
+    {
+      "epoch": 5.045045045045045,
+      "grad_norm": 0.25916115934759043,
+      "learning_rate": 8.855918393589462e-06,
+      "loss": 0.2649,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08410818129777908,
+      "step": 560,
+      "valid_targets_mean": 4458.4,
+      "valid_targets_min": 510
+    },
+    {
+      "epoch": 5.09009009009009,
+      "grad_norm": 0.2564850081349879,
+      "learning_rate": 8.485558686204215e-06,
+      "loss": 0.2687,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11359532922506332,
+      "step": 565,
+      "valid_targets_mean": 4616.7,
+      "valid_targets_min": 627
+    },
+    {
+      "epoch": 5.135135135135135,
+      "grad_norm": 0.2510056064640416,
+      "learning_rate": 8.121013446981004e-06,
+      "loss": 0.2547,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08746031671762466,
+      "step": 570,
+      "valid_targets_mean": 4663.1,
+      "valid_targets_min": 624
+    },
+    {
+      "epoch": 5.18018018018018,
+      "grad_norm": 0.2625475326627896,
+      "learning_rate": 7.762466760985651e-06,
+      "loss": 0.2613,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07597170025110245,
+      "step": 575,
+      "valid_targets_mean": 4726.4,
+      "valid_targets_min": 460
+    },
+    {
+      "epoch": 5.225225225225225,
+      "grad_norm": 0.2734042593938881,
+      "learning_rate": 7.410099684183738e-06,
+      "loss": 0.2692,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09236225485801697,
+      "step": 580,
+      "valid_targets_mean": 4880.7,
+      "valid_targets_min": 622
+    },
+    {
+      "epoch": 5.27027027027027,
+      "grad_norm": 0.2561238491798988,
+      "learning_rate": 7.064090152012488e-06,
+      "loss": 0.2625,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07333845645189285,
+      "step": 585,
+      "valid_targets_mean": 4421.5,
+      "valid_targets_min": 464
+    },
+    {
+      "epoch": 5.315315315315315,
+      "grad_norm": 0.26430414248927997,
+      "learning_rate": 6.72461288952835e-06,
+      "loss": 0.2592,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11116979271173477,
+      "step": 590,
+      "valid_targets_mean": 4556.4,
+      "valid_targets_min": 486
+    },
+    {
+      "epoch": 5.36036036036036,
+      "grad_norm": 0.23575468631305518,
+      "learning_rate": 6.391839323175788e-06,
+      "loss": 0.263,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09228559583425522,
+      "step": 595,
+      "valid_targets_mean": 5292.0,
+      "valid_targets_min": 637
+    },
+    {
+      "epoch": 5.405405405405405,
+      "grad_norm": 0.24008357776737607,
+      "learning_rate": 6.065937494221763e-06,
+      "loss": 0.277,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07229343056678772,
+      "step": 600,
+      "valid_targets_mean": 3771.4,
+      "valid_targets_min": 441
+    },
+    {
+      "epoch": 5.45045045045045,
+      "grad_norm": 0.2804930790244736,
+      "learning_rate": 5.747071973899634e-06,
+      "loss": 0.2712,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10028033703565598,
+      "step": 605,
+      "valid_targets_mean": 4424.5,
+      "valid_targets_min": 666
+    },
+    {
+      "epoch": 5.495495495495495,
+      "grad_norm": 0.2854127484831119,
+      "learning_rate": 5.4354037803053124e-06,
+      "loss": 0.2633,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09467929601669312,
+      "step": 610,
+      "valid_targets_mean": 4428.1,
+      "valid_targets_min": 581
+    },
+    {
+      "epoch": 5.54054054054054,
+      "grad_norm": 0.23697817143658992,
+      "learning_rate": 5.131090297087682e-06,
+      "loss": 0.2467,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06766346096992493,
+      "step": 615,
+      "valid_targets_mean": 4754.2,
+      "valid_targets_min": 820
+    },
+    {
+      "epoch": 5.585585585585585,
+      "grad_norm": 0.22448330366536967,
+      "learning_rate": 4.834285193974277e-06,
+      "loss": 0.2828,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08224675059318542,
+      "step": 620,
+      "valid_targets_mean": 4920.5,
+      "valid_targets_min": 761
+    },
+    {
+      "epoch": 5.63063063063063,
+      "grad_norm": 0.2636611878403353,
+      "learning_rate": 4.545138349172418e-06,
+      "loss": 0.267,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08178374171257019,
+      "step": 625,
+      "valid_targets_mean": 4456.0,
+      "valid_targets_min": 536
+    },
+    {
+      "epoch": 5.675675675675675,
+      "grad_norm": 0.2622213694212647,
+      "learning_rate": 4.263795773684929e-06,
+      "loss": 0.2685,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09543284773826599,
+      "step": 630,
+      "valid_targets_mean": 5318.9,
+      "valid_targets_min": 681
+    },
+    {
+      "epoch": 5.7207207207207205,
+      "grad_norm": 0.2697167973214109,
+      "learning_rate": 3.9903995375787245e-06,
+      "loss": 0.2682,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06491408497095108,
+      "step": 635,
+      "valid_targets_mean": 2849.9,
+      "valid_targets_min": 542
+    },
+    {
+      "epoch": 5.7657657657657655,
+      "grad_norm": 0.25988309126817144,
+      "learning_rate": 3.7250876982433947e-06,
+      "loss": 0.2712,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07970383018255234,
+      "step": 640,
+      "valid_targets_mean": 4716.7,
+      "valid_targets_min": 747
+    },
+    {
+      "epoch": 5.8108108108108105,
+      "grad_norm": 0.25075025233615533,
+      "learning_rate": 3.4679942306761484e-06,
+      "loss": 0.2673,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11483700573444366,
+      "step": 645,
+      "valid_targets_mean": 4390.4,
+      "valid_targets_min": 564
+    },
+    {
+      "epoch": 5.8558558558558556,
+      "grad_norm": 0.2284807711852441,
+      "learning_rate": 3.219248959828196e-06,
+      "loss": 0.2626,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07720620930194855,
+      "step": 650,
+      "valid_targets_mean": 4076.5,
+      "valid_targets_min": 391
+    },
+    {
+      "epoch": 5.900900900900901,
+      "grad_norm": 0.2427431505988026,
+      "learning_rate": 2.9789774950468265e-06,
+      "loss": 0.2614,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07379475235939026,
+      "step": 655,
+      "valid_targets_mean": 3298.6,
+      "valid_targets_min": 569
+    },
+    {
+      "epoch": 5.945945945945946,
+      "grad_norm": 0.25718430981692053,
+      "learning_rate": 2.747301166646221e-06,
+      "loss": 0.2732,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.11568117141723633,
+      "step": 660,
+      "valid_targets_mean": 4579.6,
+      "valid_targets_min": 686
+    },
+    {
+      "epoch": 5.990990990990991,
+      "grad_norm": 0.2654642551899208,
+      "learning_rate": 2.524336964639067e-06,
+      "loss": 0.2579,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08498381823301315,
+      "step": 665,
+      "valid_targets_mean": 3435.5,
+      "valid_targets_min": 584
+    },
+    {
+      "epoch": 6.036036036036036,
+      "grad_norm": 0.24038944183599942,
+      "learning_rate": 2.3101974796599015e-06,
+      "loss": 0.2628,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10556922852993011,
+      "step": 670,
+      "valid_targets_mean": 5025.0,
+      "valid_targets_min": 734
+    },
+    {
+      "epoch": 6.081081081081081,
+      "grad_norm": 0.30520401217062976,
+      "learning_rate": 2.1049908461100086e-06,
+      "loss": 0.2705,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06116008758544922,
+      "step": 675,
+      "valid_targets_mean": 3497.3,
+      "valid_targets_min": 439
+    },
+    {
+      "epoch": 6.126126126126126,
+      "grad_norm": 0.2323895979226439,
+      "learning_rate": 1.9088206875526128e-06,
+      "loss": 0.2652,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07196008414030075,
+      "step": 680,
+      "valid_targets_mean": 5198.0,
+      "valid_targets_min": 513
+    },
+    {
+      "epoch": 6.171171171171171,
+      "grad_norm": 0.21965113590368227,
+      "learning_rate": 1.7217860643858797e-06,
+      "loss": 0.2655,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06284235417842865,
+      "step": 685,
+      "valid_targets_mean": 3905.0,
+      "valid_targets_min": 322
+    },
+    {
+      "epoch": 6.216216216216216,
+      "grad_norm": 0.2768660919779248,
+      "learning_rate": 1.5439814238202356e-06,
+      "loss": 0.2625,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09718060493469238,
+      "step": 690,
+      "valid_targets_mean": 4281.0,
+      "valid_targets_min": 498
+    },
+    {
+      "epoch": 6.261261261261261,
+      "grad_norm": 0.2534131835087623,
+      "learning_rate": 1.3754965521851582e-06,
+      "loss": 0.2657,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06957890093326569,
+      "step": 695,
+      "valid_targets_mean": 3135.7,
+      "valid_targets_min": 473
+    },
+    {
+      "epoch": 6.306306306306306,
+      "grad_norm": 0.2763941898176929,
+      "learning_rate": 1.2164165295896392e-06,
+      "loss": 0.2658,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.12905296683311462,
+      "step": 700,
+      "valid_targets_mean": 5124.8,
+      "valid_targets_min": 480
+    },
+    {
+      "epoch": 6.351351351351352,
+      "grad_norm": 0.29676241873336406,
+      "learning_rate": 1.0668216869591098e-06,
+      "loss": 0.268,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07291467487812042,
+      "step": 705,
+      "valid_targets_mean": 3921.7,
+      "valid_targets_min": 550
+    },
+    {
+      "epoch": 6.396396396396397,
+      "grad_norm": 0.2396542772968403,
+      "learning_rate": 9.267875654706015e-07,
+      "loss": 0.2607,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06727921962738037,
+      "step": 710,
+      "valid_targets_mean": 4327.9,
+      "valid_targets_min": 540
+    },
+    {
+      "epoch": 6.441441441441442,
+      "grad_norm": 0.2477130333886694,
+      "learning_rate": 7.963848784065753e-07,
+      "loss": 0.2523,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.10727176815271378,
+      "step": 715,
+      "valid_targets_mean": 4858.2,
+      "valid_targets_min": 460
+    },
+    {
+      "epoch": 6.486486486486487,
+      "grad_norm": 0.23785509289793144,
+      "learning_rate": 6.756794754467045e-07,
+      "loss": 0.2642,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06506279110908508,
+      "step": 720,
+      "valid_targets_mean": 3841.0,
+      "valid_targets_min": 486
+    },
+    {
+      "epoch": 6.531531531531532,
+      "grad_norm": 0.2599446216714078,
+      "learning_rate": 5.647323094156565e-07,
+      "loss": 0.2579,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06333674490451813,
+      "step": 725,
+      "valid_targets_mean": 3253.1,
+      "valid_targets_min": 527
+    },
+    {
+      "epoch": 6.576576576576577,
+      "grad_norm": 0.23275171125994232,
+      "learning_rate": 4.635994055036208e-07,
+      "loss": 0.2618,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09324885904788971,
+      "step": 730,
+      "valid_targets_mean": 4914.8,
+      "valid_targets_min": 643
+    },
+    {
+      "epoch": 6.621621621621622,
+      "grad_norm": 0.2700560927072675,
+      "learning_rate": 3.723318329751746e-07,
+      "loss": 0.264,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08801683783531189,
+      "step": 735,
+      "valid_targets_mean": 3425.6,
+      "valid_targets_min": 443
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 0.2856364748943094,
+      "learning_rate": 2.9097567938074943e-07,
+      "loss": 0.2668,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.06195676326751709,
+      "step": 740,
+      "valid_targets_mean": 2569.1,
+      "valid_targets_min": 396
+    },
+    {
+      "epoch": 6.711711711711712,
+      "grad_norm": 0.2660876149226891,
+      "learning_rate": 2.1957202728370542e-07,
+      "loss": 0.2649,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.08706497400999069,
+      "step": 745,
+      "valid_targets_mean": 3522.3,
+      "valid_targets_min": 613
+    },
+    {
+      "epoch": 6.756756756756757,
+      "grad_norm": 0.2516831997354625,
+      "learning_rate": 1.5815693351480587e-07,
+      "loss": 0.2483,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.081519715487957,
+      "step": 750,
+      "valid_targets_mean": 4058.4,
+      "valid_targets_min": 594
+    },
+    {
+      "epoch": 6.801801801801802,
+      "grad_norm": 0.25213554356755763,
+      "learning_rate": 1.0676141096453097e-07,
+      "loss": 0.2714,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.1169489175081253,
+      "step": 755,
+      "valid_targets_mean": 4910.7,
+      "valid_targets_min": 311
+    },
+    {
+      "epoch": 6.846846846846847,
+      "grad_norm": 0.24647297685340094,
+      "learning_rate": 6.541141292243814e-08,
+      "loss": 0.269,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.09742185473442078,
+      "step": 760,
+      "valid_targets_mean": 4796.6,
+      "valid_targets_min": 371
+    },
+    {
+      "epoch": 6.891891891891892,
+      "grad_norm": 0.2655695590930414,
+      "learning_rate": 3.412781997148784e-08,
+      "loss": 0.2628,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07396084070205688,
+      "step": 765,
+      "valid_targets_mean": 3007.1,
+      "valid_targets_min": 323
+    },
+    {
+      "epoch": 6.936936936936937,
+      "grad_norm": 0.24263597192661657,
+      "learning_rate": 1.29264294439424e-08,
+      "loss": 0.2532,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07865872979164124,
+      "step": 770,
+      "valid_targets_mean": 3486.3,
+      "valid_targets_min": 709
+    },
+    {
+      "epoch": 6.981981981981982,
+      "grad_norm": 0.2461657123510328,
+      "learning_rate": 1.817947444149315e-09,
+      "loss": 0.2576,
+      "loss_nan_ranks": 0,
+      "loss_rank_avg": 0.07983484864234924,
+      "step": 775,
+      "valid_targets_mean": 4066.2,
+      "valid_targets_min": 659
+    },
+    {
+      "epoch": 7.0,
+      "step": 777,
+      "total_flos": 1.9140418922369516e+18,
+      "train_loss": 0.0,
+      "train_runtime": 1.4065,
+      "train_samples_per_second": 53019.754,
+      "train_steps_per_second": 552.445
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 777,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 300,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9140418922369516e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}