her_nemi_graph_4096_sft_e3_ck524: relabel study: 4096 demos, batch 64, epoch 2 of 2 (eval on the box if time allowed; see CHECKPOINTS.md)

.gitattributes

@@ -66,3 +66,4 @@ her_nemi_graph_sft_e3_ck174/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 graph_nemi_rl_e3_best/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 her_nemi_graph_2048_sft_e3_ck260/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 her_nemi_graph_4096_sft_e3_ck262/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+her_nemi_graph_4096_sft_e3_ck524/tokenizer.json filter=lfs diff=lfs merge=lfs -text

her_nemi_graph_4096_sft_e3_ck524/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_nemi_graph_4096_sft_e3_ck524/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_nemi_graph_4096_sft_e3_ck524/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_nemi_graph_4096_sft_e3_ck524/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a527f48c6c99acedb68d18b234646b96552ce9d5a9a6666606c863d13be4d8e
+size 17534340584

her_nemi_graph_4096_sft_e3_ck524/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_nemi_graph_4096_sft_e3_ck524/tokenizer.json

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

her_nemi_graph_4096_sft_e3_ck524/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_nemi_graph_4096_sft_e3_ck524/trainer_state.json

@@ -0,0 +1,414 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0961442163244866,
+  "eval_steps": 262,
+  "global_step": 524,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04006009013520281,
+      "grad_norm": 5.571637915637816,
+      "learning_rate": 5.625e-06,
+      "loss": 0.957879638671875,
+      "step": 10
+    },
+    {
+      "epoch": 0.08012018027040561,
+      "grad_norm": 2.42740361214058,
+      "learning_rate": 9.999139516827441e-06,
+      "loss": 0.6329890251159668,
+      "step": 20
+    },
+    {
+      "epoch": 0.12018027040560841,
+      "grad_norm": 1.2814896197899772,
+      "learning_rate": 9.98385027600981e-06,
+      "loss": 0.5463556289672852,
+      "step": 30
+    },
+    {
+      "epoch": 0.16024036054081123,
+      "grad_norm": 1.333923096727681,
+      "learning_rate": 9.949506476681501e-06,
+      "loss": 0.5100381374359131,
+      "step": 40
+    },
+    {
+      "epoch": 0.200300450676014,
+      "grad_norm": 1.3284287384779665,
+      "learning_rate": 9.896239424138125e-06,
+      "loss": 0.4856235980987549,
+      "step": 50
+    },
+    {
+      "epoch": 0.24036054081121683,
+      "grad_norm": 1.2090818645025976,
+      "learning_rate": 9.824252772204172e-06,
+      "loss": 0.4839322566986084,
+      "step": 60
+    },
+    {
+      "epoch": 0.2804206309464196,
+      "grad_norm": 1.2957565568715625,
+      "learning_rate": 9.733821744611352e-06,
+      "loss": 0.45794038772583007,
+      "step": 70
+    },
+    {
+      "epoch": 0.32048072108162245,
+      "grad_norm": 1.2127007618536327,
+      "learning_rate": 9.625292082746551e-06,
+      "loss": 0.4623701095581055,
+      "step": 80
+    },
+    {
+      "epoch": 0.36054081121682524,
+      "grad_norm": 1.1190821262190835,
+      "learning_rate": 9.49907872379239e-06,
+      "loss": 0.46094465255737305,
+      "step": 90
+    },
+    {
+      "epoch": 0.400600901352028,
+      "grad_norm": 1.2333705103684336,
+      "learning_rate": 9.355664214314246e-06,
+      "loss": 0.4339270114898682,
+      "step": 100
+    },
+    {
+      "epoch": 0.44066099148723087,
+      "grad_norm": 1.1686599982124957,
+      "learning_rate": 9.195596865358955e-06,
+      "loss": 0.4318528175354004,
+      "step": 110
+    },
+    {
+      "epoch": 0.48072108162243365,
+      "grad_norm": 1.0818189281059114,
+      "learning_rate": 9.019488656118791e-06,
+      "loss": 0.434522819519043,
+      "step": 120
+    },
+    {
+      "epoch": 0.5207811717576365,
+      "grad_norm": 1.1119326779291032,
+      "learning_rate": 8.82801289417551e-06,
+      "loss": 0.4450334072113037,
+      "step": 130
+    },
+    {
+      "epoch": 0.5608412618928392,
+      "grad_norm": 1.114543846990696,
+      "learning_rate": 8.62190164126999e-06,
+      "loss": 0.4379051685333252,
+      "step": 140
+    },
+    {
+      "epoch": 0.6009013520280421,
+      "grad_norm": 0.9834667276845072,
+      "learning_rate": 8.401942914439399e-06,
+      "loss": 0.42424840927124025,
+      "step": 150
+    },
+    {
+      "epoch": 0.6409614421632449,
+      "grad_norm": 1.2128139866023695,
+      "learning_rate": 8.16897767322269e-06,
+      "loss": 0.44220685958862305,
+      "step": 160
+    },
+    {
+      "epoch": 0.6810215322984476,
+      "grad_norm": 1.1349279583599479,
+      "learning_rate": 7.923896604453114e-06,
+      "loss": 0.4088078498840332,
+      "step": 170
+    },
+    {
+      "epoch": 0.7210816224336505,
+      "grad_norm": 1.1860747508443923,
+      "learning_rate": 7.66763671693031e-06,
+      "loss": 0.4405613899230957,
+      "step": 180
+    },
+    {
+      "epoch": 0.7611417125688533,
+      "grad_norm": 1.0942087660778328,
+      "learning_rate": 7.401177758991478e-06,
+      "loss": 0.42652225494384766,
+      "step": 190
+    },
+    {
+      "epoch": 0.801201802704056,
+      "grad_norm": 1.2424829883921886,
+      "learning_rate": 7.125538472678116e-06,
+      "loss": 0.4095737457275391,
+      "step": 200
+    },
+    {
+      "epoch": 0.8412618928392589,
+      "grad_norm": 1.2533942001333052,
+      "learning_rate": 6.841772698819716e-06,
+      "loss": 0.42425966262817383,
+      "step": 210
+    },
+    {
+      "epoch": 0.8813219829744617,
+      "grad_norm": 1.1306988287062723,
+      "learning_rate": 6.550965347925593e-06,
+      "loss": 0.4131216526031494,
+      "step": 220
+    },
+    {
+      "epoch": 0.9213820731096645,
+      "grad_norm": 1.1345846459686628,
+      "learning_rate": 6.254228252289269e-06,
+      "loss": 0.4207744598388672,
+      "step": 230
+    },
+    {
+      "epoch": 0.9614421632448673,
+      "grad_norm": 1.2043634011392863,
+      "learning_rate": 5.952695915163843e-06,
+      "loss": 0.38694181442260744,
+      "step": 240
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.3668770426766526,
+      "learning_rate": 5.647521173260377e-06,
+      "loss": 0.3863255023956299,
+      "step": 250
+    },
+    {
+      "epoch": 1.0400600901352028,
+      "grad_norm": 1.1927419651706284,
+      "learning_rate": 5.339870789152695e-06,
+      "loss": 0.2785000801086426,
+      "step": 260
+    },
+    {
+      "epoch": 1.0480721081622433,
+      "eval_loss": 0.4182189702987671,
+      "eval_runtime": 47.4477,
+      "eval_samples_per_second": 17.725,
+      "eval_steps_per_second": 2.234,
+      "step": 262
+    },
+    {
+      "epoch": 1.0801201802704057,
+      "grad_norm": 1.3119932394222213,
+      "learning_rate": 5.030920990439971e-06,
+      "loss": 0.26225640773773196,
+      "step": 270
+    },
+    {
+      "epoch": 1.1201802704056085,
+      "grad_norm": 1.3509009335497384,
+      "learning_rate": 4.721852972722079e-06,
+      "loss": 0.27726068496704104,
+      "step": 280
+    },
+    {
+      "epoch": 1.1602403605408111,
+      "grad_norm": 1.3627489259691914,
+      "learning_rate": 4.413848383580951e-06,
+      "loss": 0.26991987228393555,
+      "step": 290
+    },
+    {
+      "epoch": 1.200300450676014,
+      "grad_norm": 1.293120083919494,
+      "learning_rate": 4.108084804833927e-06,
+      "loss": 0.26885290145874025,
+      "step": 300
+    },
+    {
+      "epoch": 1.2403605408112168,
+      "grad_norm": 1.4055808990638106,
+      "learning_rate": 3.8057312503315443e-06,
+      "loss": 0.2643890380859375,
+      "step": 310
+    },
+    {
+      "epoch": 1.2804206309464197,
+      "grad_norm": 1.2753409426344378,
+      "learning_rate": 3.5079436965129234e-06,
+      "loss": 0.261936092376709,
+      "step": 320
+    },
+    {
+      "epoch": 1.3204807210816225,
+      "grad_norm": 1.2679659183879621,
+      "learning_rate": 3.215860662806569e-06,
+      "loss": 0.25996472835540774,
+      "step": 330
+    },
+    {
+      "epoch": 1.3605408112168251,
+      "grad_norm": 1.3294290890818425,
+      "learning_rate": 2.9305988587738678e-06,
+      "loss": 0.26000776290893557,
+      "step": 340
+    },
+    {
+      "epoch": 1.400600901352028,
+      "grad_norm": 1.3355474859161796,
+      "learning_rate": 2.6532489146373923e-06,
+      "loss": 0.2576560974121094,
+      "step": 350
+    },
+    {
+      "epoch": 1.4406609914872308,
+      "grad_norm": 1.3352529524135484,
+      "learning_rate": 2.38487121151732e-06,
+      "loss": 0.25473570823669434,
+      "step": 360
+    },
+    {
+      "epoch": 1.4807210816224337,
+      "grad_norm": 1.3569564819220818,
+      "learning_rate": 2.1264918273180575e-06,
+      "loss": 0.2416977882385254,
+      "step": 370
+    },
+    {
+      "epoch": 1.5207811717576365,
+      "grad_norm": 1.3681485880707291,
+      "learning_rate": 1.8790986137649803e-06,
+      "loss": 0.24911210536956788,
+      "step": 380
+    },
+    {
+      "epoch": 1.5608412618928393,
+      "grad_norm": 1.3399587216278372,
+      "learning_rate": 1.6436374195898368e-06,
+      "loss": 0.26995837688446045,
+      "step": 390
+    },
+    {
+      "epoch": 1.6009013520280422,
+      "grad_norm": 1.3481570728546364,
+      "learning_rate": 1.4210084743045383e-06,
+      "loss": 0.24576206207275392,
+      "step": 400
+    },
+    {
+      "epoch": 1.640961442163245,
+      "grad_norm": 1.3859133050056964,
+      "learning_rate": 1.2120629463891098e-06,
+      "loss": 0.24254744052886962,
+      "step": 410
+    },
+    {
+      "epoch": 1.6810215322984476,
+      "grad_norm": 1.3613949869305009,
+      "learning_rate": 1.0175996890527596e-06,
+      "loss": 0.2472548007965088,
+      "step": 420
+    },
+    {
+      "epoch": 1.7210816224336505,
+      "grad_norm": 1.2692713258576596,
+      "learning_rate": 8.383621860098651e-07,
+      "loss": 0.24325094223022461,
+      "step": 430
+    },
+    {
+      "epoch": 1.7611417125688533,
+      "grad_norm": 1.304631964005801,
+      "learning_rate": 6.750357089479542e-07,
+      "loss": 0.24374468326568605,
+      "step": 440
+    },
+    {
+      "epoch": 1.801201802704056,
+      "grad_norm": 1.3099610389203258,
+      "learning_rate": 5.282446975554534e-07,
+      "loss": 0.24193241596221923,
+      "step": 450
+    },
+    {
+      "epoch": 1.8412618928392588,
+      "grad_norm": 1.3393115194474878,
+      "learning_rate": 3.985503721260181e-07,
+      "loss": 0.25845696926116946,
+      "step": 460
+    },
+    {
+      "epoch": 1.8813219829744616,
+      "grad_norm": 1.371608079483105,
+      "learning_rate": 2.864485878670725e-07,
+      "loss": 0.24345617294311522,
+      "step": 470
+    },
+    {
+      "epoch": 1.9213820731096645,
+      "grad_norm": 1.4081361814490396,
+      "learning_rate": 1.923679391161304e-07,
+      "loss": 0.24615352153778075,
+      "step": 480
+    },
+    {
+      "epoch": 1.9614421632448673,
+      "grad_norm": 1.3433904226456352,
+      "learning_rate": 1.1666812071293942e-07,
+      "loss": 0.2378209114074707,
+      "step": 490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7270125962118277,
+      "learning_rate": 5.963855279235985e-08,
+      "loss": 0.2532374382019043,
+      "step": 500
+    },
+    {
+      "epoch": 2.040060090135203,
+      "grad_norm": 1.1764398251472672,
+      "learning_rate": 2.1497274255762868e-08,
+      "loss": 0.1895190715789795,
+      "step": 510
+    },
+    {
+      "epoch": 2.0801201802704057,
+      "grad_norm": 1.1484169712006707,
+      "learning_rate": 2.3901091514855203e-09,
+      "loss": 0.1849663019180298,
+      "step": 520
+    },
+    {
+      "epoch": 2.0961442163244866,
+      "eval_loss": 0.39971616864204407,
+      "eval_runtime": 46.1264,
+      "eval_samples_per_second": 18.232,
+      "eval_steps_per_second": 2.298,
+      "step": 524
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 524,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 262,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 226948363452416.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}