Upload 8 files

.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

@@ -1,3 +1,71 @@
 ---
-license: llama4
+base_model: meta-llama/Llama-4-Scout-17B-16E-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+  - finance
+  - defi
+  - wallet-risk
+  - autoscientist
+  - lora
+  - peft
+  - foresight-ai
 ---
+
+# Foresight AI DeFi Wallet Risk Classifier
+
+This repository contains the AutoScientist-trained LoRA adapter for **Foresight AI**, a DeFi wallet risk review system built for the Adaption Labs AutoScientist Challenge in the finance category.
+
+The adapter was trained to classify whether a DeFi wallet behavior sample indicates a higher-risk state within a 14-day horizon. The expected completion is a binary label:
+
+- `0` means lower-risk outcome
+- `1` means higher-risk outcome
+
+## Training Run
+
+- Fine-tune job ID: `351792b9-5320-432e-ac12-889388d6b47a`
+- Training experiment ID: `3d6e6540-6138-4890-b097-c29deb8e580f`
+- Base model: `meta-llama/Llama-4-Scout-17B-16E-Instruct`
+- Training method: SFT
+- Adapter type: LoRA
+- Data format: chat
+- Epochs: 3
+- LoRA rank: 64
+- LoRA alpha: 128
+- Learning rate: 0.0001
+- Scheduler: cosine
+- Final exported eval loss: 1.142578125
+
+## Dataset
+
+The model was trained on the Foresight AI DeFi wallet risk instruction dataset. The hackathon dataset contains 1,000 instruction rows produced from retrospective wallet behavior samples.
+
+Important: these labels are retrospective proxy labels used for hackathon model development. They should not be described as production-verified liquidation or drawdown outcomes.
+
+## Intended Use
+
+This adapter is intended for research and demonstration of DeFi wallet risk classification. It can support a user-facing wallet review workflow where outputs are presented as decision-support signals rather than financial advice.
+
+## Limitations
+
+- This is not a production financial risk model.
+- The training labels are retrospective proxy labels, not independently verified future outcomes.
+- The model should not be used to execute trades, move funds, or make automated liquidation or lending decisions.
+- The model does not prove protocol exposure, health factor, leverage, or liquidation risk unless those facts are supported by external on-chain data.
+- Outputs should be paired with Foresight AI's evidence-aware wallet detector, provider status, and data quality checks.
+
+## Adapter Files
+
+This export contains PEFT/LoRA adapter weights and tokenizer/config files:
+
+- `adapter_model.safetensors`
+- `adapter_config.json`
+- `tokenizer.json`
+- `tokenizer_config.json`
+- `special_tokens_map.json`
+- `chat_template.jinja`
+- `trainer_state.json`
+
+## License And Base Model Terms
+
+Use of this adapter is subject to the license and acceptable-use terms of the base model and any Adaption Labs challenge requirements.

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/Llama-4-Scout-17B-16E-Instruct_bnb_4bit",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": [],
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "shared_expert.down_proj",
+    "k_proj",
+    "shared_expert.up_proj",
+    "shared_expert.gate_proj",
+    "feed_forward.gate_proj",
+    "o_proj",
+    "feed_forward.up_proj",
+    "q_proj",
+    "feed_forward.down_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

chat_template.jinja

@@ -0,0 +1,123 @@
+{{- bos_token }}
+{%- if custom_tools is defined %}
+    {%- set tools = custom_tools %}
+{%- endif %}
+{%- if not tools_in_user_message is defined %}
+    {%- set tools_in_user_message = true %}
+{%- endif %}
+{%- if not date_string is defined %}
+    {%- if strftime_now is defined %}
+        {%- set date_string = strftime_now("%d %b %Y") %}
+    {%- else %}
+        {%- set date_string = "26 Jul 2024" %}
+    {%- endif %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+
+{#- This block extracts the system message, so we can slot it into the right place. #}
+{%- if messages[0]['role'] == 'system' %}    
+    {%- if messages[0]['content'] is string %}
+        {%- set system_message = messages[0]['content']|trim %}
+    {%- else %}
+        {#- FIXME: The processor requires an array, always. #}
+        {%- set system_message = messages[0]['content'][0]['text']|trim %}
+    {%- endif %}
+    {%- set messages = messages[1:] %}
+    {%- set user_supplied_system_message = true %}
+{%- else %}
+    {%- set system_message = "" %}
+    {%- set user_supplied_system_message = false %}
+{%- endif %}
+
+{#- System message if the user supplied one #}
+{%- if user_supplied_system_message %}
+    {{- "<|header_start|>system<|header_end|>\n\n" }}
+    {%- if tools is not none %}
+        {{- "Environment: ipython\n" }}
+    {%- endif %}
+    {%- if tools is not none and not tools_in_user_message %}
+        {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
+        {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+        {{- "Do not use variables.\n\n" }}
+        {%- for t in tools %}
+            {{- t | tojson(indent=4) }}
+            {{- "\n\n" }}
+        {%- endfor %}
+    {%- endif %}
+    {{- system_message }}
+    {{- "<|eot|>" }}
+{%- endif %}
+
+{#- Custom tools are passed in a user message with some extra guidance #}
+{%- if tools_in_user_message and not tools is none %}
+    {#- Extract the first user message so we can plug it in here #}
+    {%- if messages | length != 0 %}
+        {%- set first_user_message = messages[0]['content']|trim %}
+        {%- set messages = messages[1:] %}
+    {%- else %}
+        {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
+{%- endif %}
+    {{- '<|header_start|>user<|header_end|>\n\n' -}}
+    {{- "Given the following functions, please respond with a JSON for a function call " }}
+    {{- "with its proper arguments that best answers the given prompt.\n\n" }}
+    {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
+    {{- "Do not use variables.\n\n" }}
+    {%- for t in tools %}
+        {{- t | tojson(indent=4) }}
+        {{- "\n\n" }}
+    {%- endfor %}
+    {{- first_user_message + "<|eot|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+    {{- '<|header_start|>' + message['role'] + '<|header_end|>\n\n' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- "<|eot|>" }}
+    {%- elif 'tool_calls' in message and message.tool_calls|length > 0 %}
+       {{- '<|header_start|>assistant<|header_end|>\n\n' -}}
+       {{- '<|python_start|>' }}
+        {%- if message['content'] is string %}
+            {{- message['content'] }}
+        {%- else %}
+            {%- for content in message['content'] %}
+                {%- if content['type'] == 'image' %}
+                    {{- '<|image|>' }}
+                {%- elif content['type'] == 'text' %}
+                    {{- content['text'] }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+       {{- '<|python_end|>' }}
+        {%- for tool_call in message.tool_calls %}
+           {{- '{"name": "' + tool_call.function.name + '", ' }}
+           {{- '"parameters": ' }}
+           {{- tool_call.function.arguments | tojson }}
+           {{- "}" }}
+        {%- endfor %}
+       {{- "<|eot|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|header_start|>ipython<|header_end|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|header_start|>assistant<|header_end|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,215 @@
+{
+  "architectures": [
+    "Llama4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": true,
+  "bos_token_id": 200000,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 200008,
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 1,
+  "intermediate_size": 8192,
+  "intermediate_size_mlp": 16384,
+  "layer_types": [
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 10485760,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40,
+    41,
+    42,
+    43,
+    44,
+    45,
+    46,
+    47
+  ],
+  "no_rope_layer_interval": 4,
+  "no_rope_layers": [
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0
+  ],
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 16,
+  "output_router_logits": false,
+  "pad_token_id": 200018,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 16.0,
+    "high_freq_factor": 1.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "use_qk_norm": true,
+  "vocab_size": 202048,
+  "torch_dtype": "bfloat16"
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|begin_of_text|>",
+  "eos_token": "<|eot|>",
+  "pad_token": "<|finetune_right_pad|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172c9eb4beafc72601690da3ccfcede5c2e6806a8d5ec1fca33e22acea8023a4
+size 27948578

tokenizer_config.json

@@ -0,0 +1,17 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eot|>",
+  "is_local": false,
+  "local_files_only": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 10485760,
+  "pad_token": "<|finetune_right_pad|>",
+  "padding_side": "right",
+  "processor_class": "Llama4Processor",
+  "tokenizer_class": "TokenizersBackend"
+}

trainer_state.json

@@ -0,0 +1,515 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 12,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.047619047619047616,
+      "grad_norm": 0.39029014110565186,
+      "learning_rate": 0.0,
+      "loss": 1.74072265625,
+      "step": 1
+    },
+    {
+      "epoch": 0.09523809523809523,
+      "grad_norm": 0.3977895975112915,
+      "learning_rate": 2.5e-05,
+      "loss": 1.8193359375,
+      "step": 2
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.2535572648048401,
+      "learning_rate": 5e-05,
+      "loss": 1.408203125,
+      "step": 3
+    },
+    {
+      "epoch": 0.19047619047619047,
+      "grad_norm": 0.21865864098072052,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 1.54248046875,
+      "step": 4
+    },
+    {
+      "epoch": 0.23809523809523808,
+      "grad_norm": 0.14044301211833954,
+      "learning_rate": 0.0001,
+      "loss": 1.357666015625,
+      "step": 5
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.11468952149152756,
+      "learning_rate": 9.99362213054543e-05,
+      "loss": 1.414794921875,
+      "step": 6
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.15838299691677094,
+      "learning_rate": 9.974506600945618e-05,
+      "loss": 1.346435546875,
+      "step": 7
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.18158257007598877,
+      "learning_rate": 9.942707596246052e-05,
+      "loss": 1.345703125,
+      "step": 8
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 1.183410406112671,
+      "learning_rate": 9.8983152541804e-05,
+      "loss": 0.7744140625,
+      "step": 9
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 0.11678645759820938,
+      "learning_rate": 9.841455409665323e-05,
+      "loss": 1.285888671875,
+      "step": 10
+    },
+    {
+      "epoch": 0.5238095238095238,
+      "grad_norm": 0.08664851635694504,
+      "learning_rate": 9.772289238107715e-05,
+      "loss": 1.1910400390625,
+      "step": 11
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07821615040302277,
+      "learning_rate": 9.691012798535524e-05,
+      "loss": 1.207763671875,
+      "step": 12
+    },
+    {
+      "epoch": 0.6190476190476191,
+      "grad_norm": 0.07503138482570648,
+      "learning_rate": 9.59785647784711e-05,
+      "loss": 1.2236328125,
+      "step": 13
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.0798412635922432,
+      "learning_rate": 9.493084337754573e-05,
+      "loss": 1.28759765625,
+      "step": 14
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.08004077523946762,
+      "learning_rate": 9.376993366272128e-05,
+      "loss": 1.1826171875,
+      "step": 15
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "eval_loss": 1.216796875,
+      "eval_runtime": 5.4909,
+      "eval_samples_per_second": 0.364,
+      "eval_steps_per_second": 0.182,
+      "step": 15
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.06384038925170898,
+      "learning_rate": 9.249912635871318e-05,
+      "loss": 1.1982421875,
+      "step": 16
+    },
+    {
+      "epoch": 0.8095238095238095,
+      "grad_norm": 0.06806826591491699,
+      "learning_rate": 9.112202370689337e-05,
+      "loss": 1.1966552734375,
+      "step": 17
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.06299256533384323,
+      "learning_rate": 8.964252925434579e-05,
+      "loss": 1.2159423828125,
+      "step": 18
+    },
+    {
+      "epoch": 0.9047619047619048,
+      "grad_norm": 0.04804723337292671,
+      "learning_rate": 8.806483678883803e-05,
+      "loss": 1.00927734375,
+      "step": 19
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": 0.060130614787340164,
+      "learning_rate": 8.639341845107433e-05,
+      "loss": 1.214599609375,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.086543969810009,
+      "learning_rate": 8.463301205792675e-05,
+      "loss": 1.171630859375,
+      "step": 21
+    },
+    {
+      "epoch": 1.0476190476190477,
+      "grad_norm": 0.0662260353565216,
+      "learning_rate": 8.278860767257865e-05,
+      "loss": 1.19677734375,
+      "step": 22
+    },
+    {
+      "epoch": 1.0952380952380953,
+      "grad_norm": 0.05612208694219589,
+      "learning_rate": 8.086543345964832e-05,
+      "loss": 1.294921875,
+      "step": 23
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.04827860742807388,
+      "learning_rate": 7.886894086538841e-05,
+      "loss": 1.03564453125,
+      "step": 24
+    },
+    {
+      "epoch": 1.1904761904761905,
+      "grad_norm": 0.0562213771045208,
+      "learning_rate": 7.680478916496926e-05,
+      "loss": 1.2347412109375,
+      "step": 25
+    },
+    {
+      "epoch": 1.2380952380952381,
+      "grad_norm": 0.05600786581635475,
+      "learning_rate": 7.46788294206485e-05,
+      "loss": 1.1312255859375,
+      "step": 26
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.05734400078654289,
+      "learning_rate": 7.249708789629944e-05,
+      "loss": 1.21484375,
+      "step": 27
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "eval_loss": 1.169921875,
+      "eval_runtime": 5.4973,
+      "eval_samples_per_second": 0.364,
+      "eval_steps_per_second": 0.182,
+      "step": 27
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.04520232975482941,
+      "learning_rate": 7.026574897531137e-05,
+      "loss": 1.19384765625,
+      "step": 28
+    },
+    {
+      "epoch": 1.380952380952381,
+      "grad_norm": 0.0506543330848217,
+      "learning_rate": 6.799113763028295e-05,
+      "loss": 1.1943359375,
+      "step": 29
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.018054485321045,
+      "learning_rate": 6.567970149420018e-05,
+      "loss": 0.64453125,
+      "step": 30
+    },
+    {
+      "epoch": 1.4761904761904763,
+      "grad_norm": 0.06562633067369461,
+      "learning_rate": 6.333799258392015e-05,
+      "loss": 1.1578369140625,
+      "step": 31
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.04868047311902046,
+      "learning_rate": 6.097264872776749e-05,
+      "loss": 1.0946044921875,
+      "step": 32
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.055948544293642044,
+      "learning_rate": 5.859037474988874e-05,
+      "loss": 1.116943359375,
+      "step": 33
+    },
+    {
+      "epoch": 1.619047619047619,
+      "grad_norm": 0.050402332097291946,
+      "learning_rate": 5.6197923464699875e-05,
+      "loss": 1.1273193359375,
+      "step": 34
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.061322227120399475,
+      "learning_rate": 5.3802076535300135e-05,
+      "loss": 1.176513671875,
+      "step": 35
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.05519519001245499,
+      "learning_rate": 5.140962525011126e-05,
+      "loss": 1.0797119140625,
+      "step": 36
+    },
+    {
+      "epoch": 1.7619047619047619,
+      "grad_norm": 0.049536723643541336,
+      "learning_rate": 4.902735127223252e-05,
+      "loss": 1.12481689453125,
+      "step": 37
+    },
+    {
+      "epoch": 1.8095238095238095,
+      "grad_norm": 0.04784968122839928,
+      "learning_rate": 4.6662007416079864e-05,
+      "loss": 1.12640380859375,
+      "step": 38
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.052412062883377075,
+      "learning_rate": 4.432029850579983e-05,
+      "loss": 1.136962890625,
+      "step": 39
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "eval_loss": 1.154296875,
+      "eval_runtime": 5.4651,
+      "eval_samples_per_second": 0.366,
+      "eval_steps_per_second": 0.183,
+      "step": 39
+    },
+    {
+      "epoch": 1.9047619047619047,
+      "grad_norm": 0.03997504711151123,
+      "learning_rate": 4.2008862369717074e-05,
+      "loss": 0.956787109375,
+      "step": 40
+    },
+    {
+      "epoch": 1.9523809523809523,
+      "grad_norm": 0.05004314333200455,
+      "learning_rate": 3.973425102468864e-05,
+      "loss": 1.141845703125,
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.1028779074549675,
+      "learning_rate": 3.750291210370057e-05,
+      "loss": 1.067626953125,
+      "step": 42
+    },
+    {
+      "epoch": 2.0476190476190474,
+      "grad_norm": 0.05941079929471016,
+      "learning_rate": 3.5321170579351516e-05,
+      "loss": 1.1151123046875,
+      "step": 43
+    },
+    {
+      "epoch": 2.0952380952380953,
+      "grad_norm": 0.05426109582185745,
+      "learning_rate": 3.319521083503075e-05,
+      "loss": 1.222900390625,
+      "step": 44
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 0.08989612013101578,
+      "learning_rate": 3.113105913461159e-05,
+      "loss": 0.981689453125,
+      "step": 45
+    },
+    {
+      "epoch": 2.1904761904761907,
+      "grad_norm": 0.048075128346681595,
+      "learning_rate": 2.9134566540351693e-05,
+      "loss": 1.1778564453125,
+      "step": 46
+    },
+    {
+      "epoch": 2.238095238095238,
+      "grad_norm": 0.04994767904281616,
+      "learning_rate": 2.721139232742137e-05,
+      "loss": 1.0787353515625,
+      "step": 47
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.05583450198173523,
+      "learning_rate": 2.5366987942073267e-05,
+      "loss": 1.1490478515625,
+      "step": 48
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.04764580726623535,
+      "learning_rate": 2.3606581548925695e-05,
+      "loss": 1.14404296875,
+      "step": 49
+    },
+    {
+      "epoch": 2.380952380952381,
+      "grad_norm": 0.04863216355443001,
+      "learning_rate": 2.1935163211161985e-05,
+      "loss": 1.1456298828125,
+      "step": 50
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.02937026508152485,
+      "learning_rate": 2.0357470745654214e-05,
+      "loss": 0.5966796875,
+      "step": 51
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "eval_loss": 1.146484375,
+      "eval_runtime": 5.4773,
+      "eval_samples_per_second": 0.365,
+      "eval_steps_per_second": 0.183,
+      "step": 51
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.06333017349243164,
+      "learning_rate": 1.8877976293106646e-05,
+      "loss": 1.1070556640625,
+      "step": 52
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 0.04482894763350487,
+      "learning_rate": 1.7500873641286825e-05,
+      "loss": 1.0587158203125,
+      "step": 53
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.040712468326091766,
+      "learning_rate": 1.6230066337278724e-05,
+      "loss": 1.081787109375,
+      "step": 54
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.08906273543834686,
+      "learning_rate": 1.5069156622454287e-05,
+      "loss": 1.08984375,
+      "step": 55
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.061274148523807526,
+      "learning_rate": 1.4021435221528906e-05,
+      "loss": 1.130615234375,
+      "step": 56
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.054327286779880524,
+      "learning_rate": 1.3089872014644771e-05,
+      "loss": 1.0430908203125,
+      "step": 57
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.04634387046098709,
+      "learning_rate": 1.2277107618922843e-05,
+      "loss": 1.09515380859375,
+      "step": 58
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 0.0436868742108345,
+      "learning_rate": 1.1585445903346783e-05,
+      "loss": 1.10205078125,
+      "step": 59
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.05037835240364075,
+      "learning_rate": 1.1016847458196001e-05,
+      "loss": 1.1044921875,
+      "step": 60
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 0.03902503475546837,
+      "learning_rate": 1.0572924037539496e-05,
+      "loss": 0.937744140625,
+      "step": 61
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.050203897058963776,
+      "learning_rate": 1.0254933990543831e-05,
+      "loss": 1.1142578125,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.07041402906179428,
+      "learning_rate": 1.0063778694545714e-05,
+      "loss": 1.0267333984375,
+      "step": 63
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.142578125,
+      "eval_runtime": 5.4813,
+      "eval_samples_per_second": 0.365,
+      "eval_steps_per_second": 0.182,
+      "step": 63
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 63,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3468496460722995e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}