her_epoch_0

.gitattributes

@@ -37,3 +37,4 @@ gnemi_epoch_0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gnemi_epoch_1_final/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 graph_epoch_0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 graph_submitonly_epoch_0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+her_epoch_0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

her_epoch_0/.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

her_epoch_0/MODELCARD.md

@@ -0,0 +1,9 @@
+# her_epoch_0
+
+Qwen3-VL-8B-Instruct checkpoint of the ViewAgent GraphRL pipeline (interactive view planning,
+ScanNet). 
+
+```python
+from huggingface_hub import snapshot_download
+path = snapshot_download("JamesK2W/viewagent", allow_patterns=["her_epoch_0/*"]) + "/her_epoch_0"
+```

her_epoch_0/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.1039523551705468,
+    "total_flos": 69064995241984.0,
+    "train_loss": 0.664201421363681,
+    "train_runtime": 2280.2575,
+    "train_samples_per_second": 3.579,
+    "train_steps_per_second": 0.224
+}

her_epoch_0/chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.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' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content in message.content %}
+                {%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                    {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                    <|vision_start|><|image_pad|><|vision_end|>
+                {%- elif content.type == 'video' or 'video' in content %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                    {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                    <|vision_start|><|video_pad|><|vision_end|>
+                {%- elif 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\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' }}
+{%- endif %}

her_epoch_0/config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_size": 4096,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "pad_token_id": null,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_theta": 5000000,
+      "rope_type": "default"
+    },
+    "use_cache": false,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.8.0",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl_vision",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

her_epoch_0/generation_config.json

@@ -0,0 +1,14 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.0,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "5.8.0"
+}

her_epoch_0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02151aa43951b2fea9c4681067f2d36be7138c6a85a5d441628049b3b30de164
+size 17534340584

her_epoch_0/processor_config.json

@@ -0,0 +1,60 @@
+{
+  "image_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Qwen2VLImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "merge_size": 2,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "longest_edge": 16777216,
+      "shortest_edge": 65536
+    },
+    "temporal_patch_size": 2
+  },
+  "processor_class": "Qwen3VLProcessor",
+  "video_processor": {
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "do_sample_frames": true,
+    "fps": 2,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_frames": 768,
+    "merge_size": 2,
+    "min_frames": 4,
+    "patch_size": 16,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_metadata": false,
+    "size": {
+      "longest_edge": 25165824,
+      "shortest_edge": 4096
+    },
+    "temporal_patch_size": 2,
+    "video_processor_type": "Qwen3VLVideoProcessor"
+  }
+}

her_epoch_0/sft.yaml

@@ -0,0 +1,53 @@
+# LLaMA-Factory full-parameter SFT of Qwen3-VL-8B-Instruct on one HER-final dataset.
+# Four L40S (46 GB), one run at a time: DeepSpeed ZeRO-3 with optimizer offload to host
+# RAM (~130 GB per run, so two runs do not fit in 372 GB); the vision tower and projector
+# stay frozen (LLaMA-Factory's default for VLMs), the LLM trains.
+# Filled per run by launch_sft.sh: her_final_filtered, /root/sft_data/her_final_filtered_k1024, /root/runs/her_final_filtered.
+### model
+model_name_or_path: /root/models/Qwen3-VL-8B-Instruct
+template: qwen3_vl_nothink
+trust_remote_code: true
+image_max_pixels: 65536          # frames are 256x256 already; never upscale
+image_min_pixels: 4096
+
+### method
+stage: sft
+do_train: true
+finetuning_type: full
+freeze_vision_tower: true
+freeze_multi_modal_projector: true
+freeze_language_model: false
+deepspeed: /root/LlamaFactory/examples/deepspeed/ds_z3_config.json
+
+### dataset
+dataset: her_final_filtered
+dataset_dir: /root/sft_data/her_final_filtered_k1024
+media_dir: /root/viewagent_private
+cutoff_len: 8192
+overwrite_cache: true
+preprocessing_num_workers: 16
+dataloader_num_workers: 4
+
+### output
+output_dir: /root/runs/her_final_filtered
+logging_steps: 10
+save_strategy: steps
+save_steps: 170
+save_total_limit: 3
+save_only_model: true
+plot_loss: true
+overwrite_output_dir: true
+report_to: none
+
+### train
+per_device_train_batch_size: 1
+gradient_accumulation_steps: 4
+max_steps: 510                     # equal update budget for both runs (~1 pass over 8,173 rows)
+learning_rate: 1.0e-5
+lr_scheduler_type: cosine
+warmup_ratio: 0.03
+weight_decay: 0.01
+bf16: true
+gradient_checkpointing: true
+ddp_timeout: 180000000
+seed: 0

her_epoch_0/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

her_epoch_0/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_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|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

her_epoch_0/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.1039523551705468,
+    "total_flos": 69064995241984.0,
+    "train_loss": 0.664201421363681,
+    "train_runtime": 2280.2575,
+    "train_samples_per_second": 3.579,
+    "train_steps_per_second": 0.224
+}

her_epoch_0/trainer_state.json

@@ -0,0 +1,400 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1039523551705468,
+  "eval_steps": 500,
+  "global_step": 510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02165674066053059,
+      "grad_norm": 6.6310574624010785,
+      "learning_rate": 5.625e-06,
+      "loss": 0.8520071029663085,
+      "step": 10
+    },
+    {
+      "epoch": 0.04331348132106118,
+      "grad_norm": 3.9284753962014176,
+      "learning_rate": 9.999090054896397e-06,
+      "loss": 0.782810115814209,
+      "step": 20
+    },
+    {
+      "epoch": 0.06497022198159177,
+      "grad_norm": 2.968087745807889,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 0.7429184436798095,
+      "step": 30
+    },
+    {
+      "epoch": 0.08662696264212236,
+      "grad_norm": 2.7564566333129017,
+      "learning_rate": 9.946609117610508e-06,
+      "loss": 0.7325270652770997,
+      "step": 40
+    },
+    {
+      "epoch": 0.10828370330265295,
+      "grad_norm": 2.9371988930284965,
+      "learning_rate": 9.89029682604881e-06,
+      "loss": 0.7107659816741944,
+      "step": 50
+    },
+    {
+      "epoch": 0.12994044396318355,
+      "grad_norm": 2.8935207883961795,
+      "learning_rate": 9.814213258705813e-06,
+      "loss": 0.7119418144226074,
+      "step": 60
+    },
+    {
+      "epoch": 0.15159718462371413,
+      "grad_norm": 2.8709488440107447,
+      "learning_rate": 9.71866601842156e-06,
+      "loss": 0.7251427650451661,
+      "step": 70
+    },
+    {
+      "epoch": 0.17325392528424471,
+      "grad_norm": 2.5968336265028187,
+      "learning_rate": 9.604041398892528e-06,
+      "loss": 0.7046319484710694,
+      "step": 80
+    },
+    {
+      "epoch": 0.19491066594477532,
+      "grad_norm": 2.8614059840740707,
+      "learning_rate": 9.470802822901558e-06,
+      "loss": 0.7010148048400879,
+      "step": 90
+    },
+    {
+      "epoch": 0.2165674066053059,
+      "grad_norm": 2.4291559607979423,
+      "learning_rate": 9.31948896871795e-06,
+      "loss": 0.6870743751525878,
+      "step": 100
+    },
+    {
+      "epoch": 0.2382241472658365,
+      "grad_norm": 2.4177775564684136,
+      "learning_rate": 9.150711592242627e-06,
+      "loss": 0.7138229370117187,
+      "step": 110
+    },
+    {
+      "epoch": 0.2598808879263671,
+      "grad_norm": 2.4337510536028235,
+      "learning_rate": 8.965153053703325e-06,
+      "loss": 0.713676118850708,
+      "step": 120
+    },
+    {
+      "epoch": 0.2815376285868977,
+      "grad_norm": 2.704052726929981,
+      "learning_rate": 8.763563558899317e-06,
+      "loss": 0.6946747303009033,
+      "step": 130
+    },
+    {
+      "epoch": 0.30319436924742826,
+      "grad_norm": 2.647979622197215,
+      "learning_rate": 8.546758126149148e-06,
+      "loss": 0.6788104057312012,
+      "step": 140
+    },
+    {
+      "epoch": 0.32485110990795885,
+      "grad_norm": 2.444249161391069,
+      "learning_rate": 8.315613291203977e-06,
+      "loss": 0.6946415424346923,
+      "step": 150
+    },
+    {
+      "epoch": 0.34650785056848943,
+      "grad_norm": 2.6746452280557724,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 0.6826848983764648,
+      "step": 160
+    },
+    {
+      "epoch": 0.36816459122902,
+      "grad_norm": 2.534033287735108,
+      "learning_rate": 7.814097647715848e-06,
+      "loss": 0.6633652210235595,
+      "step": 170
+    },
+    {
+      "epoch": 0.38982133188955065,
+      "grad_norm": 2.350330967575508,
+      "learning_rate": 7.5457544469948164e-06,
+      "loss": 0.6532365322113037,
+      "step": 180
+    },
+    {
+      "epoch": 0.41147807255008123,
+      "grad_norm": 2.5311786291501948,
+      "learning_rate": 7.267118862184767e-06,
+      "loss": 0.6926558971405029,
+      "step": 190
+    },
+    {
+      "epoch": 0.4331348132106118,
+      "grad_norm": 2.3395820314281255,
+      "learning_rate": 6.9793174058851805e-06,
+      "loss": 0.6650524139404297,
+      "step": 200
+    },
+    {
+      "epoch": 0.4547915538711424,
+      "grad_norm": 2.1972443458820052,
+      "learning_rate": 6.683513647949826e-06,
+      "loss": 0.6575249195098877,
+      "step": 210
+    },
+    {
+      "epoch": 0.476448294531673,
+      "grad_norm": 2.0749497439548463,
+      "learning_rate": 6.38090351122006e-06,
+      "loss": 0.6540192604064942,
+      "step": 220
+    },
+    {
+      "epoch": 0.49810503519220356,
+      "grad_norm": 2.108879059217348,
+      "learning_rate": 6.072710436456293e-06,
+      "loss": 0.6687347412109375,
+      "step": 230
+    },
+    {
+      "epoch": 0.5197617758527342,
+      "grad_norm": 2.2505850639801883,
+      "learning_rate": 5.760180436015604e-06,
+      "loss": 0.6717479705810547,
+      "step": 240
+    },
+    {
+      "epoch": 0.5414185165132648,
+      "grad_norm": 2.008585228120026,
+      "learning_rate": 5.444577056273284e-06,
+      "loss": 0.6557997703552246,
+      "step": 250
+    },
+    {
+      "epoch": 0.5630752571737954,
+      "grad_norm": 2.1806606177432646,
+      "learning_rate": 5.1271762691550375e-06,
+      "loss": 0.6747237205505371,
+      "step": 260
+    },
+    {
+      "epoch": 0.584731997834326,
+      "grad_norm": 2.2011244630769853,
+      "learning_rate": 4.809261313433176e-06,
+      "loss": 0.6380350112915039,
+      "step": 270
+    },
+    {
+      "epoch": 0.6063887384948565,
+      "grad_norm": 2.2716096930584913,
+      "learning_rate": 4.492117506643256e-06,
+      "loss": 0.6624704837799072,
+      "step": 280
+    },
+    {
+      "epoch": 0.6280454791553871,
+      "grad_norm": 2.1082383650894725,
+      "learning_rate": 4.17702704859633e-06,
+      "loss": 0.6733829498291015,
+      "step": 290
+    },
+    {
+      "epoch": 0.6497022198159177,
+      "grad_norm": 2.1842236570737033,
+      "learning_rate": 3.865263837496072e-06,
+      "loss": 0.6647568702697754,
+      "step": 300
+    },
+    {
+      "epoch": 0.6713589604764483,
+      "grad_norm": 2.1303308436251376,
+      "learning_rate": 3.5580883196189265e-06,
+      "loss": 0.6572827816009521,
+      "step": 310
+    },
+    {
+      "epoch": 0.6930157011369789,
+      "grad_norm": 2.063448879197822,
+      "learning_rate": 3.256742393379909e-06,
+      "loss": 0.6716630935668946,
+      "step": 320
+    },
+    {
+      "epoch": 0.7146724417975094,
+      "grad_norm": 1.9656503477367249,
+      "learning_rate": 2.9624443883866403e-06,
+      "loss": 0.6393966197967529,
+      "step": 330
+    },
+    {
+      "epoch": 0.73632918245804,
+      "grad_norm": 2.027211231280614,
+      "learning_rate": 2.6763841397811576e-06,
+      "loss": 0.6502247810363769,
+      "step": 340
+    },
+    {
+      "epoch": 0.7579859231185706,
+      "grad_norm": 2.3873427447235476,
+      "learning_rate": 2.3997181777836955e-06,
+      "loss": 0.6804471015930176,
+      "step": 350
+    },
+    {
+      "epoch": 0.7796426637791013,
+      "grad_norm": 2.0737934235596107,
+      "learning_rate": 2.1335650518869555e-06,
+      "loss": 0.6535746574401855,
+      "step": 360
+    },
+    {
+      "epoch": 0.8012994044396319,
+      "grad_norm": 1.9718487011651602,
+      "learning_rate": 1.8790008086049534e-06,
+      "loss": 0.6324046134948731,
+      "step": 370
+    },
+    {
+      "epoch": 0.8229561451001625,
+      "grad_norm": 2.06013526658231,
+      "learning_rate": 1.6370546410597066e-06,
+      "loss": 0.645379638671875,
+      "step": 380
+    },
+    {
+      "epoch": 0.844612885760693,
+      "grad_norm": 1.9377155353976068,
+      "learning_rate": 1.4087047279943267e-06,
+      "loss": 0.651494836807251,
+      "step": 390
+    },
+    {
+      "epoch": 0.8662696264212236,
+      "grad_norm": 2.0668666045748854,
+      "learning_rate": 1.1948742790352342e-06,
+      "loss": 0.6534922599792481,
+      "step": 400
+    },
+    {
+      "epoch": 0.8879263670817542,
+      "grad_norm": 2.084662787643751,
+      "learning_rate": 9.964278021923107e-07,
+      "loss": 0.6716940879821778,
+      "step": 410
+    },
+    {
+      "epoch": 0.9095831077422848,
+      "grad_norm": 2.016040569156287,
+      "learning_rate": 8.141676086873574e-07,
+      "loss": 0.6289156913757324,
+      "step": 420
+    },
+    {
+      "epoch": 0.9312398484028154,
+      "grad_norm": 1.9291492043280882,
+      "learning_rate": 6.488305692417074e-07,
+      "loss": 0.6164919853210449,
+      "step": 430
+    },
+    {
+      "epoch": 0.952896589063346,
+      "grad_norm": 1.9177942407325543,
+      "learning_rate": 5.010851349371704e-07,
+      "loss": 0.6135074138641358,
+      "step": 440
+    },
+    {
+      "epoch": 0.9745533297238765,
+      "grad_norm": 2.0301902742843256,
+      "learning_rate": 3.715286346948671e-07,
+      "loss": 0.6023136138916015,
+      "step": 450
+    },
+    {
+      "epoch": 0.9962100703844071,
+      "grad_norm": 2.0877313195280403,
+      "learning_rate": 2.6068486029813154e-07,
+      "loss": 0.6316119194030761,
+      "step": 460
+    },
+    {
+      "epoch": 1.0173253925284245,
+      "grad_norm": 1.9797263544464472,
+      "learning_rate": 1.69001948723142e-07,
+      "loss": 0.5740091800689697,
+      "step": 470
+    },
+    {
+      "epoch": 1.038982133188955,
+      "grad_norm": 1.848511331149272,
+      "learning_rate": 9.685057033892998e-08,
+      "loss": 0.5533595561981202,
+      "step": 480
+    },
+    {
+      "epoch": 1.0606388738494856,
+      "grad_norm": 1.9535827781255963,
+      "learning_rate": 4.45224303018027e-08,
+      "loss": 0.5302218437194824,
+      "step": 490
+    },
+    {
+      "epoch": 1.0822956145100162,
+      "grad_norm": 1.810579117186512,
+      "learning_rate": 1.2229089202987487e-08,
+      "loss": 0.5554699897766113,
+      "step": 500
+    },
+    {
+      "epoch": 1.1039523551705468,
+      "grad_norm": 1.8744238565042173,
+      "learning_rate": 1.011077375662195e-10,
+      "loss": 0.5366660118103027,
+      "step": 510
+    },
+    {
+      "epoch": 1.1039523551705468,
+      "step": 510,
+      "total_flos": 69064995241984.0,
+      "train_loss": 0.664201421363681,
+      "train_runtime": 2280.2575,
+      "train_samples_per_second": 3.579,
+      "train_steps_per_second": 0.224
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 170,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 69064995241984.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}