Add 11 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

@@ -0,0 +1,102 @@
+---
+base_model: meta-llama/Llama-3.2-3B-Instruct
+library_name: peft
+license: other
+tags:
+  - lora
+  - peft
+  - adapter
+  - adaption
+---
+
+# adaption_math_word_problem_sub_2
+
+## Model Training
+
+A LORA adapter for `meta-llama/Llama-3.2-3B-Instruct`. This model was trained with SFT using [Adaption](https://adaptionlabs.ai)'s AutoScientist on the math_word_problem_sub_2 dataset.
+
+
+![Training metrics](training-metrics.png)
+
+### AutoScientist Config
+
+```json
+{
+  "job_id": "dfdd2990-1ef7-41e4-829d-2924d668ab65",
+  "training_experiment_id": "19aa2607-d5ad-43b7-90b2-5e7d3745b627",
+  "original_model_name": "meta-llama/Llama-3.2-3B-Instruct",
+  "trained_model_name": "adaption_math_word_problem_sub_2",
+  "training_method": "sft",
+  "training_type": "lora",
+  "data_format": "chat",
+  "hyperparams": {
+    "lora": "true",
+    "lora_r": 16,
+    "n_evals": 5,
+    "n_epochs": 3,
+    "batch_size": "max",
+    "lora_alpha": 32,
+    "lora_dropout": 0,
+    "min_lr_ratio": 0.1,
+    "warmup_ratio": 0.1,
+    "weight_decay": 0,
+    "learning_rate": 0.00001,
+    "max_grad_norm": 2,
+    "base_model_size": "3B",
+    "train_on_inputs": "false",
+    "training_method": "sft",
+    "lr_scheduler_type": "cosine",
+    "scheduler_num_cycles": 0.5,
+    "lora_trainable_modules": "all-linear"
+  }
+}
+```
+
+## Training Data
+
+The model was trained on 19,573 rows of adapted data with the following domain distribution: math (99%), language (0%), science (0%), personal-finance (0%), fitness-sports (0%), animal-nature (0%), agriculture (0%), how-to (0%), sports (0%), travel (0%), data-analysis-visualization (0%).
+
+## Model Evaluation
+
+The model was evaluated on an in-distribution held-out test set as well as a broader domain-specific test set to measure generalization.
+
+
+![Win rates](win-rates.png)
+
+| Domain | Win rate vs. base model |
+| --- | --- |
+| math | 50% |
+
+## How to use
+
+```bash
+pip install torch transformers peft
+```
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+
+BASE = "meta-llama/Llama-3.2-3B-Instruct"
+ADAPTER = "<this-repo-id>"
+
+device = "cuda" if torch.cuda.is_available() else "cpu"
+dtype = torch.float32 if device == "cpu" else torch.bfloat16
+
+base = AutoModelForCausalLM.from_pretrained(BASE, dtype=dtype).to(device)
+model = PeftModel.from_pretrained(base, ADAPTER)
+# Optional: merge the LoRA weights into the base for faster inference
+model = model.merge_and_unload()
+model.eval()
+
+tokenizer = AutoTokenizer.from_pretrained(BASE)
+messages = [{"role": "user", "content": "Hello!"}]
+text = tokenizer.apply_chat_template(
+    messages, tokenize=False, add_generation_prompt=True)
+inputs = tokenizer(text, return_tensors="pt").to(device)
+
+with torch.inference_mode():
+    out = model.generate(**inputs, max_new_tokens=512)
+print(tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True))
+```

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/Meta-Llama-3.2-3B-Instruct-Reference__TOG__FT",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f491a63460ca8c73736d44ecc27a256ce6242ef0f567ca6fe6a92a5238e1efa
+size 97307544

chat_template.jinja

@@ -0,0 +1,93 @@
+{{- 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' %}
+    {%- set system_message = messages[0]['content']|trim %}
+    {%- set messages = messages[1:] %}
+{%- else %}
+    {%- set system_message = "" %}
+{%- endif %}
+
+{#- System message #}
+{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
+{%- if tools is not none %}
+    {{- "Environment: ipython\n" }}
+{%- endif %}
+{{- "Cutting Knowledge Date: December 2023\n" }}
+{{- "Today Date: " + date_string + "\n\n" }}
+{%- 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_id|>" }}
+
+{#- 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 %}
+    {{- '<|start_header_id|>user<|end_header_id|>\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_id|>"}}
+{%- endif %}
+
+{%- for message in messages %}
+    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
+        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
+    {%- elif 'tool_calls' in message %}
+        {%- if not message.tool_calls|length == 1 %}
+            {{- raise_exception("This model only supports single tool-calls at once!") }}
+        {%- endif %}
+        {%- set tool_call = message.tool_calls[0].function %}
+        {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
+        {{- '{"name": "' + tool_call.name + '", ' }}
+        {{- '"parameters": ' }}
+        {{- tool_call.arguments | tojson }}
+        {{- "}" }}
+        {{- "<|eot_id|>" }}
+    {%- elif message.role == "tool" or message.role == "ipython" %}
+        {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
+        {%- if message.content is mapping or message.content is iterable %}
+            {{- message.content | tojson }}
+        {%- else %}
+            {{- message.content }}
+        {%- endif %}
+        {{- "<|eot_id|>" }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128009,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000.0,
+    "rope_type": "llama3"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "vocab_size": 128256,
+  "torch_dtype": "bfloat16"
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "local_files_only": true,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend"
+}

trainer_state.json

@@ -0,0 +1,557 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 13,
+  "global_step": 69,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 0.06574621796607971,
+      "learning_rate": 0.0,
+      "loss": 0.683349609375,
+      "step": 1
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.05150672793388367,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.66162109375,
+      "step": 2
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.05505973473191261,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.66796875,
+      "step": 3
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.0745709016919136,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 0.677734375,
+      "step": 4
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 0.08272148668766022,
+      "learning_rate": 5.7142857142857145e-06,
+      "loss": 0.6865234375,
+      "step": 5
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 0.07590784132480621,
+      "learning_rate": 7.1428571428571436e-06,
+      "loss": 0.6802978515625,
+      "step": 6
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 0.07782676070928574,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.69140625,
+      "step": 7
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.06320719420909882,
+      "learning_rate": 1e-05,
+      "loss": 0.691650390625,
+      "step": 8
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.06206236779689789,
+      "learning_rate": 9.994224282269737e-06,
+      "loss": 0.685302734375,
+      "step": 9
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.0787166878581047,
+      "learning_rate": 9.976911955263528e-06,
+      "loss": 0.66796875,
+      "step": 10
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 0.0858655646443367,
+      "learning_rate": 9.948107459476502e-06,
+      "loss": 0.68408203125,
+      "step": 11
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.05600776895880699,
+      "learning_rate": 9.907884735636226e-06,
+      "loss": 0.650146484375,
+      "step": 12
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 0.09197074174880981,
+      "learning_rate": 9.85634703489792e-06,
+      "loss": 0.640380859375,
+      "step": 13
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 0.051537591964006424,
+      "learning_rate": 9.79362665380022e-06,
+      "loss": 0.61328125,
+      "step": 14
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.05343881994485855,
+      "learning_rate": 9.719884594661864e-06,
+      "loss": 0.65966796875,
+      "step": 15
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.06316563487052917,
+      "learning_rate": 9.635310152291038e-06,
+      "loss": 0.634765625,
+      "step": 16
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 0.04639754444360733,
+      "learning_rate": 9.540120428068337e-06,
+      "loss": 0.65234375,
+      "step": 17
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "eval_loss": 0.65130615234375,
+      "eval_runtime": 2.0495,
+      "eval_samples_per_second": 1.464,
+      "eval_steps_per_second": 0.488,
+      "step": 17
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.08494574576616287,
+      "learning_rate": 9.43455977265062e-06,
+      "loss": 0.680419921875,
+      "step": 18
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.0556136891245842,
+      "learning_rate": 9.31889915872638e-06,
+      "loss": 0.654052734375,
+      "step": 19
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.050713956356048584,
+      "learning_rate": 9.193435485432744e-06,
+      "loss": 0.66650390625,
+      "step": 20
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.0457201823592186,
+      "learning_rate": 9.058490816219644e-06,
+      "loss": 0.643310546875,
+      "step": 21
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.0635598674416542,
+      "learning_rate": 8.91441155211756e-06,
+      "loss": 0.654052734375,
+      "step": 22
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.04849772900342941,
+      "learning_rate": 8.76156754253104e-06,
+      "loss": 0.65966796875,
+      "step": 23
+    },
+    {
+      "epoch": 1.0434782608695652,
+      "grad_norm": 0.04802418127655983,
+      "learning_rate": 8.60035113584059e-06,
+      "loss": 0.65966796875,
+      "step": 24
+    },
+    {
+      "epoch": 1.0869565217391304,
+      "grad_norm": 0.03913020342588425,
+      "learning_rate": 8.431176172250002e-06,
+      "loss": 0.643798828125,
+      "step": 25
+    },
+    {
+      "epoch": 1.1304347826086956,
+      "grad_norm": 0.04047388955950737,
+      "learning_rate": 8.254476921464483e-06,
+      "loss": 0.64501953125,
+      "step": 26
+    },
+    {
+      "epoch": 1.1739130434782608,
+      "grad_norm": 0.04983432590961456,
+      "learning_rate": 8.070706967926565e-06,
+      "loss": 0.64453125,
+      "step": 27
+    },
+    {
+      "epoch": 1.2173913043478262,
+      "grad_norm": 0.053629934787750244,
+      "learning_rate": 7.880338046471331e-06,
+      "loss": 0.646484375,
+      "step": 28
+    },
+    {
+      "epoch": 1.2608695652173914,
+      "grad_norm": 0.048355311155319214,
+      "learning_rate": 7.683858831389866e-06,
+      "loss": 0.64288330078125,
+      "step": 29
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "grad_norm": 0.04861477389931679,
+      "learning_rate": 7.481773682009356e-06,
+      "loss": 0.650146484375,
+      "step": 30
+    },
+    {
+      "epoch": 1.3043478260869565,
+      "eval_loss": 0.6319580078125,
+      "eval_runtime": 2.0542,
+      "eval_samples_per_second": 1.46,
+      "eval_steps_per_second": 0.487,
+      "step": 30
+    },
+    {
+      "epoch": 1.3478260869565217,
+      "grad_norm": 0.04120055213570595,
+      "learning_rate": 7.274601348009934e-06,
+      "loss": 0.65966796875,
+      "step": 31
+    },
+    {
+      "epoch": 1.391304347826087,
+      "grad_norm": 0.04094763100147247,
+      "learning_rate": 7.062873637801692e-06,
+      "loss": 0.6552734375,
+      "step": 32
+    },
+    {
+      "epoch": 1.434782608695652,
+      "grad_norm": 0.045276131480932236,
+      "learning_rate": 6.847134053380113e-06,
+      "loss": 0.6279296875,
+      "step": 33
+    },
+    {
+      "epoch": 1.4782608695652173,
+      "grad_norm": 0.047124769538640976,
+      "learning_rate": 6.627936395164243e-06,
+      "loss": 0.640625,
+      "step": 34
+    },
+    {
+      "epoch": 1.5217391304347827,
+      "grad_norm": 0.03720078617334366,
+      "learning_rate": 6.405843340398971e-06,
+      "loss": 0.623291015625,
+      "step": 35
+    },
+    {
+      "epoch": 1.5652173913043477,
+      "grad_norm": 0.04636256396770477,
+      "learning_rate": 6.181424998770595e-06,
+      "loss": 0.59619140625,
+      "step": 36
+    },
+    {
+      "epoch": 1.608695652173913,
+      "grad_norm": 0.03454005345702171,
+      "learning_rate": 5.955257448943446e-06,
+      "loss": 0.588623046875,
+      "step": 37
+    },
+    {
+      "epoch": 1.6521739130434783,
+      "grad_norm": 0.03595034033060074,
+      "learning_rate": 5.727921259774208e-06,
+      "loss": 0.6328125,
+      "step": 38
+    },
+    {
+      "epoch": 1.6956521739130435,
+      "grad_norm": 0.03682588040828705,
+      "learning_rate": 5.500000000000001e-06,
+      "loss": 0.60498046875,
+      "step": 39
+    },
+    {
+      "epoch": 1.7391304347826086,
+      "grad_norm": 0.03514236584305763,
+      "learning_rate": 5.272078740225793e-06,
+      "loss": 0.629638671875,
+      "step": 40
+    },
+    {
+      "epoch": 1.7826086956521738,
+      "grad_norm": 0.04472735896706581,
+      "learning_rate": 5.0447425510565564e-06,
+      "loss": 0.641357421875,
+      "step": 41
+    },
+    {
+      "epoch": 1.8260869565217392,
+      "grad_norm": 0.03495565056800842,
+      "learning_rate": 4.818575001229406e-06,
+      "loss": 0.626708984375,
+      "step": 42
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "grad_norm": 0.035717420279979706,
+      "learning_rate": 4.594156659601029e-06,
+      "loss": 0.643310546875,
+      "step": 43
+    },
+    {
+      "epoch": 1.8695652173913042,
+      "eval_loss": 0.6201171875,
+      "eval_runtime": 2.0449,
+      "eval_samples_per_second": 1.467,
+      "eval_steps_per_second": 0.489,
+      "step": 43
+    },
+    {
+      "epoch": 1.9130434782608696,
+      "grad_norm": 0.03499886021018028,
+      "learning_rate": 4.372063604835758e-06,
+      "loss": 0.623046875,
+      "step": 44
+    },
+    {
+      "epoch": 1.9565217391304348,
+      "grad_norm": 0.04084884747862816,
+      "learning_rate": 4.15286594661989e-06,
+      "loss": 0.62548828125,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.036120329052209854,
+      "learning_rate": 3.93712636219831e-06,
+      "loss": 0.6376953125,
+      "step": 46
+    },
+    {
+      "epoch": 2.0434782608695654,
+      "grad_norm": 0.03603987395763397,
+      "learning_rate": 3.7253986519900674e-06,
+      "loss": 0.6376953125,
+      "step": 47
+    },
+    {
+      "epoch": 2.0869565217391304,
+      "grad_norm": 0.03318258747458458,
+      "learning_rate": 3.5182263179906462e-06,
+      "loss": 0.62841796875,
+      "step": 48
+    },
+    {
+      "epoch": 2.130434782608696,
+      "grad_norm": 0.03247852995991707,
+      "learning_rate": 3.316141168610136e-06,
+      "loss": 0.629638671875,
+      "step": 49
+    },
+    {
+      "epoch": 2.1739130434782608,
+      "grad_norm": 0.03627059981226921,
+      "learning_rate": 3.119661953528671e-06,
+      "loss": 0.62451171875,
+      "step": 50
+    },
+    {
+      "epoch": 2.217391304347826,
+      "grad_norm": 0.03881670534610748,
+      "learning_rate": 2.9292930320734337e-06,
+      "loss": 0.62548828125,
+      "step": 51
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": 0.03561678156256676,
+      "learning_rate": 2.745523078535517e-06,
+      "loss": 0.62567138671875,
+      "step": 52
+    },
+    {
+      "epoch": 2.3043478260869565,
+      "grad_norm": 0.036425329744815826,
+      "learning_rate": 2.568823827750001e-06,
+      "loss": 0.633056640625,
+      "step": 53
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": 0.033790528774261475,
+      "learning_rate": 2.3996488641594104e-06,
+      "loss": 0.6455078125,
+      "step": 54
+    },
+    {
+      "epoch": 2.391304347826087,
+      "grad_norm": 0.03458794951438904,
+      "learning_rate": 2.2384324574689614e-06,
+      "loss": 0.64013671875,
+      "step": 55
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "grad_norm": 0.03604791685938835,
+      "learning_rate": 2.085588447882441e-06,
+      "loss": 0.612548828125,
+      "step": 56
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "eval_loss": 0.617156982421875,
+      "eval_runtime": 2.0468,
+      "eval_samples_per_second": 1.466,
+      "eval_steps_per_second": 0.489,
+      "step": 56
+    },
+    {
+      "epoch": 2.4782608695652173,
+      "grad_norm": 0.037638068199157715,
+      "learning_rate": 1.9415091837803574e-06,
+      "loss": 0.6259765625,
+      "step": 57
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": 0.032444193959236145,
+      "learning_rate": 1.8065645145672578e-06,
+      "loss": 0.61279296875,
+      "step": 58
+    },
+    {
+      "epoch": 2.5652173913043477,
+      "grad_norm": 0.03685029596090317,
+      "learning_rate": 1.6811008412736207e-06,
+      "loss": 0.582763671875,
+      "step": 59
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": 0.030133027583360672,
+      "learning_rate": 1.5654402273493808e-06,
+      "loss": 0.57958984375,
+      "step": 60
+    },
+    {
+      "epoch": 2.6521739130434785,
+      "grad_norm": 0.031628984957933426,
+      "learning_rate": 1.459879571931663e-06,
+      "loss": 0.6240234375,
+      "step": 61
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": 0.03223630040884018,
+      "learning_rate": 1.3646898477089627e-06,
+      "loss": 0.594970703125,
+      "step": 62
+    },
+    {
+      "epoch": 2.7391304347826084,
+      "grad_norm": 0.03134209290146828,
+      "learning_rate": 1.2801154053381386e-06,
+      "loss": 0.621337890625,
+      "step": 63
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": 0.038812585175037384,
+      "learning_rate": 1.2063733461997804e-06,
+      "loss": 0.631103515625,
+      "step": 64
+    },
+    {
+      "epoch": 2.8260869565217392,
+      "grad_norm": 0.031380850821733475,
+      "learning_rate": 1.1436529651020813e-06,
+      "loss": 0.619384765625,
+      "step": 65
+    },
+    {
+      "epoch": 2.869565217391304,
+      "grad_norm": 0.0320647768676281,
+      "learning_rate": 1.092115264363775e-06,
+      "loss": 0.636474609375,
+      "step": 66
+    },
+    {
+      "epoch": 2.9130434782608696,
+      "grad_norm": 0.031743913888931274,
+      "learning_rate": 1.0518925405234988e-06,
+      "loss": 0.61572265625,
+      "step": 67
+    },
+    {
+      "epoch": 2.9565217391304346,
+      "grad_norm": 0.037360724061727524,
+      "learning_rate": 1.0230880447364719e-06,
+      "loss": 0.619140625,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.03293885663151741,
+      "learning_rate": 1.0057757177302628e-06,
+      "loss": 0.631103515625,
+      "step": 69
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.6156768798828125,
+      "eval_runtime": 2.0475,
+      "eval_samples_per_second": 1.465,
+      "eval_steps_per_second": 0.488,
+      "step": 69
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 69,
+  "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": 1.2309274178963374e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}