add aft/charter/checkpoint-16 (copied from jbostock/scimt-dispatch-models-v1)

aft/charter/checkpoint-16/README.md

@@ -0,0 +1,208 @@
+---
+base_model: /workspace/hf-dispatch-midtrain-aft-v1/hub/models--jbostock--scimt-dispatch-sft-v1/snapshots/ad24276d9d25455b528c80b4c3043438bfc32ca5/runs/20260806T143703Z/charter/checkpoint-48
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:/workspace/hf-dispatch-midtrain-aft-v1/hub/models--jbostock--scimt-dispatch-sft-v1/snapshots/ad24276d9d25455b528c80b4c3043438bfc32ca5/runs/20260806T143703Z/charter/checkpoint-48
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

aft/charter/checkpoint-16/adapter_config.json

@@ -0,0 +1,189 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/workspace/hf-dispatch-midtrain-aft-v1/hub/models--jbostock--scimt-dispatch-sft-v1/snapshots/ad24276d9d25455b528c80b4c3043438bfc32ca5/runs/20260806T143703Z/charter/checkpoint-48",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "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,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "language_model.layers.25.self_attn.v_proj",
+    "30.self_attn.v_proj",
+    "35.self_attn.q_proj",
+    "27.self_attn.v_proj",
+    "language_model.layers.24.self_attn.q_proj",
+    "language_model.layers.8.self_attn.v_proj",
+    "41.self_attn.v_proj",
+    "language_model.layers.6.self_attn.k_proj",
+    "39.self_attn.q_proj",
+    "language_model.layers.21.self_attn.q_proj",
+    "language_model.layers.4.self_attn.q_proj",
+    "up_proj",
+    "31.self_attn.k_proj",
+    "language_model.layers.12.self_attn.q_proj",
+    "language_model.layers.14.self_attn.k_proj",
+    "language_model.layers.17.self_attn.q_proj",
+    "27.self_attn.q_proj",
+    "language_model.layers.17.self_attn.v_proj",
+    "language_model.layers.24.self_attn.k_proj",
+    "36.self_attn.q_proj",
+    "language_model.layers.14.self_attn.v_proj",
+    "38.self_attn.v_proj",
+    "45.self_attn.v_proj",
+    "language_model.layers.26.self_attn.q_proj",
+    "language_model.layers.3.self_attn.q_proj",
+    "language_model.layers.20.self_attn.k_proj",
+    "language_model.layers.5.self_attn.q_proj",
+    "language_model.layers.16.self_attn.k_proj",
+    "language_model.layers.22.self_attn.k_proj",
+    "language_model.layers.18.self_attn.q_proj",
+    "45.self_attn.q_proj",
+    "47.self_attn.q_proj",
+    "language_model.layers.0.self_attn.v_proj",
+    "language_model.layers.23.self_attn.k_proj",
+    "43.self_attn.k_proj",
+    "42.self_attn.v_proj",
+    "language_model.layers.18.self_attn.v_proj",
+    "30.self_attn.k_proj",
+    "language_model.layers.8.self_attn.q_proj",
+    "language_model.layers.21.self_attn.k_proj",
+    "39.self_attn.v_proj",
+    "language_model.layers.13.self_attn.k_proj",
+    "30.self_attn.q_proj",
+    "33.self_attn.q_proj",
+    "44.self_attn.v_proj",
+    "language_model.layers.4.self_attn.k_proj",
+    "language_model.layers.6.self_attn.q_proj",
+    "45.self_attn.k_proj",
+    "40.self_attn.k_proj",
+    "language_model.layers.11.self_attn.v_proj",
+    "47.self_attn.k_proj",
+    "language_model.layers.7.self_attn.v_proj",
+    "33.self_attn.k_proj",
+    "31.self_attn.v_proj",
+    "language_model.layers.3.self_attn.k_proj",
+    "29.self_attn.q_proj",
+    "32.self_attn.q_proj",
+    "33.self_attn.v_proj",
+    "34.self_attn.q_proj",
+    "language_model.layers.20.self_attn.q_proj",
+    "language_model.layers.19.self_attn.v_proj",
+    "language_model.layers.26.self_attn.v_proj",
+    "o_proj",
+    "language_model.layers.5.self_attn.v_proj",
+    "29.self_attn.v_proj",
+    "28.self_attn.k_proj",
+    "language_model.layers.2.self_attn.q_proj",
+    "down_proj",
+    "language_model.layers.11.self_attn.k_proj",
+    "44.self_attn.q_proj",
+    "31.self_attn.q_proj",
+    "language_model.layers.9.self_attn.q_proj",
+    "language_model.layers.11.self_attn.q_proj",
+    "language_model.layers.7.self_attn.q_proj",
+    "28.self_attn.q_proj",
+    "language_model.layers.18.self_attn.k_proj",
+    "language_model.layers.16.self_attn.q_proj",
+    "39.self_attn.k_proj",
+    "language_model.layers.7.self_attn.k_proj",
+    "36.self_attn.v_proj",
+    "language_model.layers.1.self_attn.v_proj",
+    "37.self_attn.q_proj",
+    "language_model.layers.0.self_attn.q_proj",
+    "language_model.layers.12.self_attn.k_proj",
+    "language_model.layers.9.self_attn.k_proj",
+    "language_model.layers.22.self_attn.q_proj",
+    "language_model.layers.19.self_attn.q_proj",
+    "language_model.layers.13.self_attn.v_proj",
+    "34.self_attn.v_proj",
+    "language_model.layers.6.self_attn.v_proj",
+    "35.self_attn.v_proj",
+    "37.self_attn.k_proj",
+    "language_model.layers.23.self_attn.v_proj",
+    "42.self_attn.k_proj",
+    "32.self_attn.v_proj",
+    "language_model.layers.1.self_attn.k_proj",
+    "language_model.layers.26.self_attn.k_proj",
+    "36.self_attn.k_proj",
+    "language_model.layers.17.self_attn.k_proj",
+    "language_model.layers.23.self_attn.q_proj",
+    "language_model.layers.1.self_attn.q_proj",
+    "language_model.layers.2.self_attn.k_proj",
+    "language_model.layers.9.self_attn.v_proj",
+    "46.self_attn.q_proj",
+    "language_model.layers.25.self_attn.q_proj",
+    "language_model.layers.15.self_attn.k_proj",
+    "47.self_attn.v_proj",
+    "27.self_attn.k_proj",
+    "38.self_attn.q_proj",
+    "language_model.layers.10.self_attn.k_proj",
+    "32.self_attn.k_proj",
+    "language_model.layers.5.self_attn.k_proj",
+    "46.self_attn.k_proj",
+    "language_model.layers.0.self_attn.k_proj",
+    "language_model.layers.4.self_attn.v_proj",
+    "language_model.layers.16.self_attn.v_proj",
+    "language_model.layers.25.self_attn.k_proj",
+    "41.self_attn.q_proj",
+    "language_model.layers.15.self_attn.v_proj",
+    "language_model.layers.14.self_attn.q_proj",
+    "language_model.layers.10.self_attn.q_proj",
+    "44.self_attn.k_proj",
+    "language_model.layers.12.self_attn.v_proj",
+    "35.self_attn.k_proj",
+    "41.self_attn.k_proj",
+    "language_model.layers.15.self_attn.q_proj",
+    "gate_proj",
+    "34.self_attn.k_proj",
+    "language_model.layers.24.self_attn.v_proj",
+    "language_model.layers.13.self_attn.q_proj",
+    "language_model.layers.10.self_attn.v_proj",
+    "29.self_attn.k_proj",
+    "28.self_attn.v_proj",
+    "language_model.layers.3.self_attn.v_proj",
+    "language_model.layers.2.self_attn.v_proj",
+    "43.self_attn.q_proj",
+    "language_model.layers.21.self_attn.v_proj",
+    "40.self_attn.q_proj",
+    "37.self_attn.v_proj",
+    "language_model.layers.22.self_attn.v_proj",
+    "42.self_attn.q_proj",
+    "43.self_attn.v_proj",
+    "40.self_attn.v_proj",
+    "language_model.layers.8.self_attn.k_proj",
+    "38.self_attn.k_proj",
+    "language_model.layers.20.self_attn.v_proj",
+    "46.self_attn.v_proj",
+    "language_model.layers.19.self_attn.k_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

aft/charter/checkpoint-16/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a09bb6f3d3091a8ab54d99396485917a2904322d7fdb48ba81583a599e9e8e68
+size 1047628488

aft/charter/checkpoint-16/chat_template.jinja

@@ -0,0 +1,47 @@
+{{ bos_token }}
+{%- if messages[0]['role'] == 'system' -%}
+    {%- if messages[0]['content'] is string -%}
+        {%- set first_user_prefix = messages[0]['content'] + '
+
+' -%}
+    {%- else -%}
+        {%- set first_user_prefix = messages[0]['content'][0]['text'] + '
+
+' -%}
+    {%- endif -%}
+    {%- set loop_messages = messages[1:] -%}
+{%- else -%}
+    {%- set first_user_prefix = "" -%}
+    {%- set loop_messages = messages -%}
+{%- endif -%}
+{%- for message in loop_messages -%}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) -%}
+        {{ raise_exception("Conversation roles must alternate user/assistant/user/assistant/...") }}
+    {%- endif -%}
+    {%- if (message['role'] == 'assistant') -%}
+        {%- set role = "model" -%}
+    {%- else -%}
+        {%- set role = message['role'] -%}
+    {%- endif -%}
+    {{ '<start_of_turn>' + role + '
+' + (first_user_prefix if loop.first else "") }}
+    {%- if message['content'] is string -%}
+        {{ message['content'] | trim }}
+    {%- elif message['content'] is iterable -%}
+        {%- for item in message['content'] -%}
+            {%- if item['type'] == 'image' -%}
+                {{ '<start_of_image>' }}
+            {%- elif item['type'] == 'text' -%}
+                {{ item['text'] | trim }}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {{ raise_exception("Invalid content type") }}
+    {%- endif -%}
+    {{ '<end_of_turn>
+' }}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{'<start_of_turn>model
+'}}
+{%- endif -%}

aft/charter/checkpoint-16/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daab2354f8a74e70d70b4d1f804939b68a8c9624dd06cb7858e52dd8970e9726
+size 33384567

aft/charter/checkpoint-16/tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "backend": "tokenizers",
+  "boi_token": "<start_of_image>",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eoi_token": "<end_of_image>",
+  "eos_token": "<eos>",
+  "image_token": "<image_soft_token>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 131072,
+  "model_specific_special_tokens": {
+    "boi_token": "<start_of_image>",
+    "eoi_token": "<end_of_image>",
+    "image_token": "<image_soft_token>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma3Processor",
+  "sp_model_kwargs": null,
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

aft/charter/checkpoint-16/tokens_state.json

@@ -0,0 +1 @@
+{"total": 241452, "trainable": 5168}

aft/charter/checkpoint-16/trainer_state.json

@@ -0,0 +1,258 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25,
+  "eval_steps": 500,
+  "global_step": 16,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015625,
+      "grad_norm": 1.212809443473816,
+      "learning_rate": 0.0,
+      "loss": 0.12976087629795074,
+      "memory/device_reserved (GiB)": 32.97,
+      "memory/max_active (GiB)": 30.93,
+      "memory/max_allocated (GiB)": 30.93,
+      "ppl": 1.13856,
+      "step": 1,
+      "tokens/total": 15100,
+      "tokens/train_per_sec_per_gpu": 6.34,
+      "tokens/trainable": 321
+    },
+    {
+      "epoch": 0.03125,
+      "grad_norm": 1.1429096460342407,
+      "learning_rate": 9.80392156862745e-07,
+      "loss": 0.1249035894870758,
+      "memory/device_reserved (GiB)": 34.09,
+      "memory/max_active (GiB)": 32.89,
+      "memory/max_allocated (GiB)": 32.89,
+      "ppl": 1.13304,
+      "step": 2,
+      "tokens/total": 30192,
+      "tokens/train_per_sec_per_gpu": 9.49,
+      "tokens/trainable": 643
+    },
+    {
+      "epoch": 0.046875,
+      "grad_norm": 5.998322486877441,
+      "learning_rate": 1.96078431372549e-06,
+      "loss": 0.12847918272018433,
+      "memory/device_reserved (GiB)": 34.09,
+      "memory/max_active (GiB)": 32.89,
+      "memory/max_allocated (GiB)": 32.89,
+      "ppl": 1.1371,
+      "step": 3,
+      "tokens/total": 45292,
+      "tokens/train_per_sec_per_gpu": 9.54,
+      "tokens/trainable": 964
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 1.198765754699707,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.12956468760967255,
+      "memory/device_reserved (GiB)": 34.09,
+      "memory/max_active (GiB)": 32.84,
+      "memory/max_allocated (GiB)": 32.84,
+      "ppl": 1.13833,
+      "step": 4,
+      "tokens/total": 60368,
+      "tokens/train_per_sec_per_gpu": 9.44,
+      "tokens/trainable": 1288
+    },
+    {
+      "epoch": 0.078125,
+      "grad_norm": 0.9583120942115784,
+      "learning_rate": 3.92156862745098e-06,
+      "loss": 0.11962152272462845,
+      "memory/device_reserved (GiB)": 34.19,
+      "memory/max_active (GiB)": 32.98,
+      "memory/max_allocated (GiB)": 32.98,
+      "ppl": 1.12707,
+      "step": 5,
+      "tokens/total": 75532,
+      "tokens/train_per_sec_per_gpu": 9.02,
+      "tokens/trainable": 1613
+    },
+    {
+      "epoch": 0.09375,
+      "grad_norm": 1.080938458442688,
+      "learning_rate": 4.901960784313726e-06,
+      "loss": 0.11386945843696594,
+      "memory/device_reserved (GiB)": 34.19,
+      "memory/max_active (GiB)": 32.86,
+      "memory/max_allocated (GiB)": 32.86,
+      "ppl": 1.12061,
+      "step": 6,
+      "tokens/total": 90564,
+      "tokens/train_per_sec_per_gpu": 9.33,
+      "tokens/trainable": 1932
+    },
+    {
+      "epoch": 0.109375,
+      "grad_norm": 1.1981987953186035,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.13011117279529572,
+      "memory/device_reserved (GiB)": 34.19,
+      "memory/max_active (GiB)": 32.93,
+      "memory/max_allocated (GiB)": 32.93,
+      "ppl": 1.13895,
+      "step": 7,
+      "tokens/total": 105708,
+      "tokens/train_per_sec_per_gpu": 9.5,
+      "tokens/trainable": 2258
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.9428791999816895,
+      "learning_rate": 6.862745098039216e-06,
+      "loss": 0.10154103487730026,
+      "memory/device_reserved (GiB)": 34.19,
+      "memory/max_active (GiB)": 32.93,
+      "memory/max_allocated (GiB)": 32.93,
+      "ppl": 1.10688,
+      "step": 8,
+      "tokens/total": 120800,
+      "tokens/train_per_sec_per_gpu": 9.31,
+      "tokens/trainable": 2581
+    },
+    {
+      "epoch": 0.140625,
+      "grad_norm": 1.230772614479065,
+      "learning_rate": 7.84313725490196e-06,
+      "loss": 0.11154383420944214,
+      "memory/device_reserved (GiB)": 34.19,
+      "memory/max_active (GiB)": 32.86,
+      "memory/max_allocated (GiB)": 32.86,
+      "ppl": 1.118,
+      "step": 9,
+      "tokens/total": 135856,
+      "tokens/train_per_sec_per_gpu": 9.27,
+      "tokens/trainable": 2903
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 1.5177358388900757,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.08524951338768005,
+      "memory/device_reserved (GiB)": 34.13,
+      "memory/max_active (GiB)": 32.93,
+      "memory/max_allocated (GiB)": 32.93,
+      "ppl": 1.08899,
+      "step": 10,
+      "tokens/total": 150972,
+      "tokens/train_per_sec_per_gpu": 9.4,
+      "tokens/trainable": 3230
+    },
+    {
+      "epoch": 0.171875,
+      "grad_norm": 1.2144169807434082,
+      "learning_rate": 9.803921568627451e-06,
+      "loss": 0.07611503452062607,
+      "memory/device_reserved (GiB)": 34.13,
+      "memory/max_active (GiB)": 32.89,
+      "memory/max_allocated (GiB)": 32.89,
+      "ppl": 1.07909,
+      "step": 11,
+      "tokens/total": 165912,
+      "tokens/train_per_sec_per_gpu": 9.35,
+      "tokens/trainable": 3549
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 3.1928279399871826,
+      "learning_rate": 1.0784313725490197e-05,
+      "loss": 0.12453900277614594,
+      "memory/device_reserved (GiB)": 34.13,
+      "memory/max_active (GiB)": 32.88,
+      "memory/max_allocated (GiB)": 32.88,
+      "ppl": 1.13263,
+      "step": 12,
+      "tokens/total": 180904,
+      "tokens/train_per_sec_per_gpu": 9.63,
+      "tokens/trainable": 3873
+    },
+    {
+      "epoch": 0.203125,
+      "grad_norm": 2.654078960418701,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.12103886902332306,
+      "memory/device_reserved (GiB)": 34.13,
+      "memory/max_active (GiB)": 32.86,
+      "memory/max_allocated (GiB)": 32.86,
+      "ppl": 1.12867,
+      "step": 13,
+      "tokens/total": 195956,
+      "tokens/train_per_sec_per_gpu": 9.6,
+      "tokens/trainable": 4198
+    },
+    {
+      "epoch": 0.21875,
+      "grad_norm": 11.066537857055664,
+      "learning_rate": 1.2745098039215686e-05,
+      "loss": 0.10858573764562607,
+      "memory/device_reserved (GiB)": 34.13,
+      "memory/max_active (GiB)": 32.87,
+      "memory/max_allocated (GiB)": 32.87,
+      "ppl": 1.1147,
+      "step": 14,
+      "tokens/total": 211132,
+      "tokens/train_per_sec_per_gpu": 9.53,
+      "tokens/trainable": 4524
+    },
+    {
+      "epoch": 0.234375,
+      "grad_norm": 2.252739906311035,
+      "learning_rate": 1.3725490196078432e-05,
+      "loss": 0.03346411883831024,
+      "memory/device_reserved (GiB)": 34.13,
+      "memory/max_active (GiB)": 32.88,
+      "memory/max_allocated (GiB)": 32.88,
+      "ppl": 1.03403,
+      "step": 15,
+      "tokens/total": 226244,
+      "tokens/train_per_sec_per_gpu": 9.31,
+      "tokens/trainable": 4846
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.332521915435791,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 0.06247912347316742,
+      "memory/device_reserved (GiB)": 34.13,
+      "memory/max_active (GiB)": 32.9,
+      "memory/max_allocated (GiB)": 32.9,
+      "ppl": 1.06447,
+      "step": 16,
+      "tokens/total": 241452,
+      "tokens/train_per_sec_per_gpu": 9.53,
+      "tokens/trainable": 5168
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 2048,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 32,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6569802255655808e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}