gnemi_epoch_0

.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
+gnemi_epoch_0/tokenizer.json filter=lfs diff=lfs merge=lfs -text

gnemi_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

gnemi_epoch_0/MODELCARD.md

@@ -0,0 +1,9 @@
+# gnemi_epoch_0
+
+Qwen3-VL-8B-Instruct checkpoint of the ViewAgent GraphRL pipeline (interactive view planning,
+ScanNet). SFT on 1,024 graph_near_miss demonstrations (prompt-level union view graph of the base model D0 rollouts, stitched shortest prefix to within 2 units of the target, then submit); epoch_0 start of the rl -> sft -> rl loop. eval pass@8 4.7% (strict).
+
+```python
+from huggingface_hub import snapshot_download
+path = snapshot_download("JamesK2W/viewagent", allow_patterns=["gnemi_epoch_0/*"]) + "/gnemi_epoch_0"
+```

gnemi_epoch_0/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.4648910411622276,
+    "total_flos": 56534529671168.0,
+    "train_loss": 0.4558592599980971,
+    "train_runtime": 1288.1751,
+    "train_samples_per_second": 6.335,
+    "train_steps_per_second": 0.396
+}

gnemi_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 %}

gnemi_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
+}

gnemi_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"
+}

gnemi_epoch_0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0d114bd08e63888debf7d352a3515ef44b73ff31b453c91b4250b82f5e5838
+size 17534340584

gnemi_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"
+  }
+}

gnemi_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: graph_near_miss, /root/sft_data/graph_near_miss_k1024, /root/runs/graph_near_miss.
+### 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: graph_near_miss
+dataset_dir: /root/sft_data/graph_near_miss_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/graph_near_miss
+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: 2
+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

gnemi_epoch_0/tokenizer.json

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

gnemi_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
+}

gnemi_epoch_0/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.4648910411622276,
+    "total_flos": 56534529671168.0,
+    "train_loss": 0.4558592599980971,
+    "train_runtime": 1288.1751,
+    "train_samples_per_second": 6.335,
+    "train_steps_per_second": 0.396
+}

gnemi_epoch_0/trainer_state.json

@@ -0,0 +1,400 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4648910411622276,
+  "eval_steps": 500,
+  "global_step": 510,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.048426150121065374,
+      "grad_norm": 7.075511921769658,
+      "learning_rate": 5.625e-06,
+      "loss": 0.8121331214904786,
+      "step": 10
+    },
+    {
+      "epoch": 0.09685230024213075,
+      "grad_norm": 4.162753097581864,
+      "learning_rate": 9.999090054896397e-06,
+      "loss": 0.7152867317199707,
+      "step": 20
+    },
+    {
+      "epoch": 0.14527845036319612,
+      "grad_norm": 3.0753999308994,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 0.6652995109558105,
+      "step": 30
+    },
+    {
+      "epoch": 0.1937046004842615,
+      "grad_norm": 2.9059025220115466,
+      "learning_rate": 9.946609117610508e-06,
+      "loss": 0.6418190002441406,
+      "step": 40
+    },
+    {
+      "epoch": 0.24213075060532688,
+      "grad_norm": 3.1415779535203665,
+      "learning_rate": 9.89029682604881e-06,
+      "loss": 0.6374396324157715,
+      "step": 50
+    },
+    {
+      "epoch": 0.29055690072639223,
+      "grad_norm": 3.062103659509293,
+      "learning_rate": 9.814213258705813e-06,
+      "loss": 0.6078249931335449,
+      "step": 60
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 3.1822837441312495,
+      "learning_rate": 9.71866601842156e-06,
+      "loss": 0.629939079284668,
+      "step": 70
+    },
+    {
+      "epoch": 0.387409200968523,
+      "grad_norm": 2.2809485074272673,
+      "learning_rate": 9.604041398892528e-06,
+      "loss": 0.5647114753723145,
+      "step": 80
+    },
+    {
+      "epoch": 0.4358353510895884,
+      "grad_norm": 2.429487486575334,
+      "learning_rate": 9.470802822901558e-06,
+      "loss": 0.6142401695251465,
+      "step": 90
+    },
+    {
+      "epoch": 0.48426150121065376,
+      "grad_norm": 2.26063761240064,
+      "learning_rate": 9.31948896871795e-06,
+      "loss": 0.5668928146362304,
+      "step": 100
+    },
+    {
+      "epoch": 0.5326876513317191,
+      "grad_norm": 2.3691738032897107,
+      "learning_rate": 9.150711592242627e-06,
+      "loss": 0.60851149559021,
+      "step": 110
+    },
+    {
+      "epoch": 0.5811138014527845,
+      "grad_norm": 2.4542411475774766,
+      "learning_rate": 8.965153053703325e-06,
+      "loss": 0.6183795928955078,
+      "step": 120
+    },
+    {
+      "epoch": 0.6295399515738499,
+      "grad_norm": 2.364728910648791,
+      "learning_rate": 8.763563558899317e-06,
+      "loss": 0.5815310478210449,
+      "step": 130
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 2.2135175519706727,
+      "learning_rate": 8.546758126149148e-06,
+      "loss": 0.5695794582366943,
+      "step": 140
+    },
+    {
+      "epoch": 0.7263922518159807,
+      "grad_norm": 2.3078279524384326,
+      "learning_rate": 8.315613291203977e-06,
+      "loss": 0.6053508281707763,
+      "step": 150
+    },
+    {
+      "epoch": 0.774818401937046,
+      "grad_norm": 2.3777705120099433,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 0.5691863536834717,
+      "step": 160
+    },
+    {
+      "epoch": 0.8232445520581114,
+      "grad_norm": 2.4117358979020573,
+      "learning_rate": 7.814097647715848e-06,
+      "loss": 0.5466008186340332,
+      "step": 170
+    },
+    {
+      "epoch": 0.8716707021791767,
+      "grad_norm": 2.4892438297123256,
+      "learning_rate": 7.5457544469948164e-06,
+      "loss": 0.5716792106628418,
+      "step": 180
+    },
+    {
+      "epoch": 0.9200968523002422,
+      "grad_norm": 2.0887558798818993,
+      "learning_rate": 7.267118862184767e-06,
+      "loss": 0.5428262710571289,
+      "step": 190
+    },
+    {
+      "epoch": 0.9685230024213075,
+      "grad_norm": 1.9836232439287276,
+      "learning_rate": 6.9793174058851805e-06,
+      "loss": 0.5562956809997559,
+      "step": 200
+    },
+    {
+      "epoch": 1.0145278450363195,
+      "grad_norm": 2.0400561775150585,
+      "learning_rate": 6.683513647949826e-06,
+      "loss": 0.5080109596252441,
+      "step": 210
+    },
+    {
+      "epoch": 1.062953995157385,
+      "grad_norm": 2.2996300065955095,
+      "learning_rate": 6.38090351122006e-06,
+      "loss": 0.4377303123474121,
+      "step": 220
+    },
+    {
+      "epoch": 1.1113801452784504,
+      "grad_norm": 2.287949729167872,
+      "learning_rate": 6.072710436456293e-06,
+      "loss": 0.4146146774291992,
+      "step": 230
+    },
+    {
+      "epoch": 1.1598062953995156,
+      "grad_norm": 2.2154291484249007,
+      "learning_rate": 5.760180436015604e-06,
+      "loss": 0.41754741668701173,
+      "step": 240
+    },
+    {
+      "epoch": 1.208232445520581,
+      "grad_norm": 2.0635877581902062,
+      "learning_rate": 5.444577056273284e-06,
+      "loss": 0.422486400604248,
+      "step": 250
+    },
+    {
+      "epoch": 1.2566585956416465,
+      "grad_norm": 2.185812799702593,
+      "learning_rate": 5.1271762691550375e-06,
+      "loss": 0.4020406723022461,
+      "step": 260
+    },
+    {
+      "epoch": 1.305084745762712,
+      "grad_norm": 2.4582220733907887,
+      "learning_rate": 4.809261313433176e-06,
+      "loss": 0.4152475357055664,
+      "step": 270
+    },
+    {
+      "epoch": 1.3535108958837774,
+      "grad_norm": 2.3645066741307494,
+      "learning_rate": 4.492117506643256e-06,
+      "loss": 0.40107192993164065,
+      "step": 280
+    },
+    {
+      "epoch": 1.4019370460048426,
+      "grad_norm": 1.9589974272362303,
+      "learning_rate": 4.17702704859633e-06,
+      "loss": 0.4098958015441895,
+      "step": 290
+    },
+    {
+      "epoch": 1.450363196125908,
+      "grad_norm": 2.23836277080526,
+      "learning_rate": 3.865263837496072e-06,
+      "loss": 0.3950955390930176,
+      "step": 300
+    },
+    {
+      "epoch": 1.4987893462469732,
+      "grad_norm": 2.289736093523171,
+      "learning_rate": 3.5580883196189265e-06,
+      "loss": 0.3832646369934082,
+      "step": 310
+    },
+    {
+      "epoch": 1.5472154963680387,
+      "grad_norm": 2.160871243168133,
+      "learning_rate": 3.256742393379909e-06,
+      "loss": 0.3887941360473633,
+      "step": 320
+    },
+    {
+      "epoch": 1.5956416464891041,
+      "grad_norm": 1.9069079030327722,
+      "learning_rate": 2.9624443883866403e-06,
+      "loss": 0.407411003112793,
+      "step": 330
+    },
+    {
+      "epoch": 1.6440677966101696,
+      "grad_norm": 2.1865423355260463,
+      "learning_rate": 2.6763841397811576e-06,
+      "loss": 0.37820706367492674,
+      "step": 340
+    },
+    {
+      "epoch": 1.692493946731235,
+      "grad_norm": 2.089754354986366,
+      "learning_rate": 2.3997181777836955e-06,
+      "loss": 0.3914737939834595,
+      "step": 350
+    },
+    {
+      "epoch": 1.7409200968523002,
+      "grad_norm": 2.3352831024922716,
+      "learning_rate": 2.1335650518869555e-06,
+      "loss": 0.40088663101196287,
+      "step": 360
+    },
+    {
+      "epoch": 1.7893462469733656,
+      "grad_norm": 2.3348755976359215,
+      "learning_rate": 1.8790008086049534e-06,
+      "loss": 0.3716615676879883,
+      "step": 370
+    },
+    {
+      "epoch": 1.8377723970944309,
+      "grad_norm": 2.1456810033935643,
+      "learning_rate": 1.6370546410597066e-06,
+      "loss": 0.3830316781997681,
+      "step": 380
+    },
+    {
+      "epoch": 1.8861985472154963,
+      "grad_norm": 2.4053166055307833,
+      "learning_rate": 1.4087047279943267e-06,
+      "loss": 0.3592139959335327,
+      "step": 390
+    },
+    {
+      "epoch": 1.9346246973365617,
+      "grad_norm": 2.1569144997137455,
+      "learning_rate": 1.1948742790352342e-06,
+      "loss": 0.3689441680908203,
+      "step": 400
+    },
+    {
+      "epoch": 1.9830508474576272,
+      "grad_norm": 2.2618495362887137,
+      "learning_rate": 9.964278021923107e-07,
+      "loss": 0.37668161392211913,
+      "step": 410
+    },
+    {
+      "epoch": 2.029055690072639,
+      "grad_norm": 2.2985439521328748,
+      "learning_rate": 8.141676086873574e-07,
+      "loss": 0.28116588592529296,
+      "step": 420
+    },
+    {
+      "epoch": 2.0774818401937045,
+      "grad_norm": 2.1819880240209337,
+      "learning_rate": 6.488305692417074e-07,
+      "loss": 0.2777563095092773,
+      "step": 430
+    },
+    {
+      "epoch": 2.12590799031477,
+      "grad_norm": 2.4806224177522482,
+      "learning_rate": 5.010851349371704e-07,
+      "loss": 0.2364122152328491,
+      "step": 440
+    },
+    {
+      "epoch": 2.1743341404358354,
+      "grad_norm": 2.59365695106934,
+      "learning_rate": 3.715286346948671e-07,
+      "loss": 0.2725958347320557,
+      "step": 450
+    },
+    {
+      "epoch": 2.222760290556901,
+      "grad_norm": 2.15164510724158,
+      "learning_rate": 2.6068486029813154e-07,
+      "loss": 0.26798238754272463,
+      "step": 460
+    },
+    {
+      "epoch": 2.2711864406779663,
+      "grad_norm": 2.3170801633203073,
+      "learning_rate": 1.69001948723142e-07,
+      "loss": 0.2620837211608887,
+      "step": 470
+    },
+    {
+      "epoch": 2.3196125907990313,
+      "grad_norm": 2.159580664349284,
+      "learning_rate": 9.685057033892998e-08,
+      "loss": 0.2295910358428955,
+      "step": 480
+    },
+    {
+      "epoch": 2.3680387409200967,
+      "grad_norm": 2.4134167665174826,
+      "learning_rate": 4.45224303018027e-08,
+      "loss": 0.2532357692718506,
+      "step": 490
+    },
+    {
+      "epoch": 2.416464891041162,
+      "grad_norm": 2.089420639197115,
+      "learning_rate": 1.2229089202987487e-08,
+      "loss": 0.234877872467041,
+      "step": 500
+    },
+    {
+      "epoch": 2.4648910411622276,
+      "grad_norm": 2.2417100644313703,
+      "learning_rate": 1.011077375662195e-10,
+      "loss": 0.27428240776062013,
+      "step": 510
+    },
+    {
+      "epoch": 2.4648910411622276,
+      "step": 510,
+      "total_flos": 56534529671168.0,
+      "train_loss": 0.4558592599980971,
+      "train_runtime": 1288.1751,
+      "train_samples_per_second": 6.335,
+      "train_steps_per_second": 0.396
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 510,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 56534529671168.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}