Upload folder using huggingface_hub

experiment/adapters/rmft/README.md

@@ -0,0 +1,202 @@
+---
+base_model: EleutherAI/pythia-160m
+library_name: peft
+---
+
+# 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 0.11.1

experiment/adapters/rmft/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "EleutherAI/pythia-160m",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "query_key_value"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

experiment/adapters/rmft/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350a0221af8136a7fb59d80170c4135506624f7af697061b7931ffabd43db420
+size 1183064

experiment/adapters/rmft/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

experiment/adapters/rmft/tokenizer_config.json

@@ -0,0 +1,214 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

experiment/adapters/rmft/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd558b4eec356985103820c7ceb522616250ec3042128888bdcd5fbb26fbedb
+size 5112

experiment/adapters/rmft/training_metadata.json

@@ -0,0 +1,585 @@
+{
+  "method": "rmft",
+  "model_name": "EleutherAI/pythia-160m",
+  "train_samples": 4799,
+  "validation_samples": 599,
+  "batches_seen": 12375,
+  "masked_token_ratio": 0.14994983782590895,
+  "skipped_samples": 0,
+  "log_history": [
+    {
+      "loss": 2.7552,
+      "grad_norm": 1.0823794603347778,
+      "learning_rate": 2e-05,
+      "epoch": 0.06666666666666667,
+      "step": 10
+    },
+    {
+      "loss": 2.6983,
+      "grad_norm": 0.9608964920043945,
+      "learning_rate": 4e-05,
+      "epoch": 0.13333333333333333,
+      "step": 20
+    },
+    {
+      "loss": 2.6843,
+      "grad_norm": 0.9745031595230103,
+      "learning_rate": 6e-05,
+      "epoch": 0.2,
+      "step": 30
+    },
+    {
+      "loss": 2.7944,
+      "grad_norm": 1.0781015157699585,
+      "learning_rate": 8e-05,
+      "epoch": 0.26666666666666666,
+      "step": 40
+    },
+    {
+      "loss": 2.6711,
+      "grad_norm": 1.1792235374450684,
+      "learning_rate": 0.0001,
+      "epoch": 0.3333333333333333,
+      "step": 50
+    },
+    {
+      "loss": 2.6409,
+      "grad_norm": 1.6941765546798706,
+      "learning_rate": 0.00012,
+      "epoch": 0.4,
+      "step": 60
+    },
+    {
+      "loss": 2.6422,
+      "grad_norm": 1.011501669883728,
+      "learning_rate": 0.00014,
+      "epoch": 0.4666666666666667,
+      "step": 70
+    },
+    {
+      "loss": 2.655,
+      "grad_norm": 1.1399949789047241,
+      "learning_rate": 0.00016,
+      "epoch": 0.5333333333333333,
+      "step": 80
+    },
+    {
+      "loss": 2.6691,
+      "grad_norm": 1.5286301374435425,
+      "learning_rate": 0.00018,
+      "epoch": 0.6,
+      "step": 90
+    },
+    {
+      "loss": 2.7092,
+      "grad_norm": 0.9922551512718201,
+      "learning_rate": 0.0002,
+      "epoch": 0.6666666666666666,
+      "step": 100
+    },
+    {
+      "loss": 2.7121,
+      "grad_norm": 1.010247826576233,
+      "learning_rate": 0.00019692307692307696,
+      "epoch": 0.7333333333333333,
+      "step": 110
+    },
+    {
+      "loss": 2.6293,
+      "grad_norm": 1.0366889238357544,
+      "learning_rate": 0.00019384615384615385,
+      "epoch": 0.8,
+      "step": 120
+    },
+    {
+      "loss": 2.7002,
+      "grad_norm": 0.9185057878494263,
+      "learning_rate": 0.0001907692307692308,
+      "epoch": 0.8666666666666667,
+      "step": 130
+    },
+    {
+      "loss": 2.6064,
+      "grad_norm": 1.179173469543457,
+      "learning_rate": 0.0001876923076923077,
+      "epoch": 0.9333333333333333,
+      "step": 140
+    },
+    {
+      "loss": 2.6188,
+      "grad_norm": 0.9263139367103577,
+      "learning_rate": 0.00018461538461538463,
+      "epoch": 1.0,
+      "step": 150
+    },
+    {
+      "eval_loss": 2.6337876319885254,
+      "eval_runtime": 7.5119,
+      "eval_samples_per_second": 79.741,
+      "eval_steps_per_second": 9.984,
+      "epoch": 1.0,
+      "step": 150
+    },
+    {
+      "loss": 2.6544,
+      "grad_norm": 0.9955130815505981,
+      "learning_rate": 0.00018153846153846155,
+      "epoch": 1.0666666666666667,
+      "step": 160
+    },
+    {
+      "loss": 2.5858,
+      "grad_norm": 1.0158054828643799,
+      "learning_rate": 0.00017846153846153847,
+      "epoch": 1.1333333333333333,
+      "step": 170
+    },
+    {
+      "loss": 2.5605,
+      "grad_norm": 1.0236505270004272,
+      "learning_rate": 0.0001753846153846154,
+      "epoch": 1.2,
+      "step": 180
+    },
+    {
+      "loss": 2.6982,
+      "grad_norm": 0.9611760377883911,
+      "learning_rate": 0.00017230769230769234,
+      "epoch": 1.2666666666666666,
+      "step": 190
+    },
+    {
+      "loss": 2.6429,
+      "grad_norm": 1.1758582592010498,
+      "learning_rate": 0.00016923076923076923,
+      "epoch": 1.3333333333333333,
+      "step": 200
+    },
+    {
+      "loss": 2.5483,
+      "grad_norm": 1.004822015762329,
+      "learning_rate": 0.00016615384615384617,
+      "epoch": 1.4,
+      "step": 210
+    },
+    {
+      "loss": 2.6308,
+      "grad_norm": 0.8812061548233032,
+      "learning_rate": 0.0001630769230769231,
+      "epoch": 1.4666666666666668,
+      "step": 220
+    },
+    {
+      "loss": 2.6315,
+      "grad_norm": 1.0901386737823486,
+      "learning_rate": 0.00016,
+      "epoch": 1.5333333333333332,
+      "step": 230
+    },
+    {
+      "loss": 2.667,
+      "grad_norm": 0.9653924703598022,
+      "learning_rate": 0.00015692307692307693,
+      "epoch": 1.6,
+      "step": 240
+    },
+    {
+      "loss": 2.6265,
+      "grad_norm": 1.309544563293457,
+      "learning_rate": 0.00015384615384615385,
+      "epoch": 1.6666666666666665,
+      "step": 250
+    },
+    {
+      "loss": 2.6724,
+      "grad_norm": 1.0008659362792969,
+      "learning_rate": 0.00015076923076923077,
+      "epoch": 1.7333333333333334,
+      "step": 260
+    },
+    {
+      "loss": 2.6865,
+      "grad_norm": 0.9268591403961182,
+      "learning_rate": 0.00014769230769230772,
+      "epoch": 1.8,
+      "step": 270
+    },
+    {
+      "loss": 2.5967,
+      "grad_norm": 0.9716233611106873,
+      "learning_rate": 0.0001446153846153846,
+      "epoch": 1.8666666666666667,
+      "step": 280
+    },
+    {
+      "loss": 2.6251,
+      "grad_norm": 0.9400352239608765,
+      "learning_rate": 0.00014153846153846156,
+      "epoch": 1.9333333333333333,
+      "step": 290
+    },
+    {
+      "loss": 2.5877,
+      "grad_norm": 0.9511526823043823,
+      "learning_rate": 0.00013846153846153847,
+      "epoch": 2.0,
+      "step": 300
+    },
+    {
+      "eval_loss": 2.6063592433929443,
+      "eval_runtime": 7.5174,
+      "eval_samples_per_second": 79.682,
+      "eval_steps_per_second": 9.977,
+      "epoch": 2.0,
+      "step": 300
+    },
+    {
+      "loss": 2.6473,
+      "grad_norm": 0.9834712147712708,
+      "learning_rate": 0.0001353846153846154,
+      "epoch": 2.066666666666667,
+      "step": 310
+    },
+    {
+      "loss": 2.5765,
+      "grad_norm": 0.8454016447067261,
+      "learning_rate": 0.0001323076923076923,
+      "epoch": 2.1333333333333333,
+      "step": 320
+    },
+    {
+      "loss": 2.5497,
+      "grad_norm": 0.88639897108078,
+      "learning_rate": 0.00012923076923076923,
+      "epoch": 2.2,
+      "step": 330
+    },
+    {
+      "loss": 2.64,
+      "grad_norm": 1.1036648750305176,
+      "learning_rate": 0.00012615384615384615,
+      "epoch": 2.2666666666666666,
+      "step": 340
+    },
+    {
+      "loss": 2.5318,
+      "grad_norm": 1.0497366189956665,
+      "learning_rate": 0.0001230769230769231,
+      "epoch": 2.3333333333333335,
+      "step": 350
+    },
+    {
+      "loss": 2.6065,
+      "grad_norm": 0.997850775718689,
+      "learning_rate": 0.00012,
+      "epoch": 2.4,
+      "step": 360
+    },
+    {
+      "loss": 2.6713,
+      "grad_norm": 1.077837347984314,
+      "learning_rate": 0.00011692307692307694,
+      "epoch": 2.466666666666667,
+      "step": 370
+    },
+    {
+      "loss": 2.5964,
+      "grad_norm": 0.955797553062439,
+      "learning_rate": 0.00011384615384615384,
+      "epoch": 2.533333333333333,
+      "step": 380
+    },
+    {
+      "loss": 2.6523,
+      "grad_norm": 0.8457085490226746,
+      "learning_rate": 0.00011076923076923077,
+      "epoch": 2.6,
+      "step": 390
+    },
+    {
+      "loss": 2.5759,
+      "grad_norm": 1.0808671712875366,
+      "learning_rate": 0.0001076923076923077,
+      "epoch": 2.6666666666666665,
+      "step": 400
+    },
+    {
+      "loss": 2.6125,
+      "grad_norm": 1.0875897407531738,
+      "learning_rate": 0.00010461538461538463,
+      "epoch": 2.7333333333333334,
+      "step": 410
+    },
+    {
+      "loss": 2.6399,
+      "grad_norm": 0.8935572504997253,
+      "learning_rate": 0.00010153846153846153,
+      "epoch": 2.8,
+      "step": 420
+    },
+    {
+      "loss": 2.5988,
+      "grad_norm": 1.1328654289245605,
+      "learning_rate": 9.846153846153848e-05,
+      "epoch": 2.8666666666666667,
+      "step": 430
+    },
+    {
+      "loss": 2.5966,
+      "grad_norm": 1.1522167921066284,
+      "learning_rate": 9.53846153846154e-05,
+      "epoch": 2.9333333333333336,
+      "step": 440
+    },
+    {
+      "loss": 2.6255,
+      "grad_norm": 0.9381677508354187,
+      "learning_rate": 9.230769230769232e-05,
+      "epoch": 3.0,
+      "step": 450
+    },
+    {
+      "eval_loss": 2.5932793617248535,
+      "eval_runtime": 7.5072,
+      "eval_samples_per_second": 79.79,
+      "eval_steps_per_second": 9.99,
+      "epoch": 3.0,
+      "step": 450
+    },
+    {
+      "loss": 2.5311,
+      "grad_norm": 0.9240983724594116,
+      "learning_rate": 8.923076923076924e-05,
+      "epoch": 3.066666666666667,
+      "step": 460
+    },
+    {
+      "loss": 2.6373,
+      "grad_norm": 0.9194068312644958,
+      "learning_rate": 8.615384615384617e-05,
+      "epoch": 3.1333333333333333,
+      "step": 470
+    },
+    {
+      "loss": 2.5596,
+      "grad_norm": 1.0319569110870361,
+      "learning_rate": 8.307692307692309e-05,
+      "epoch": 3.2,
+      "step": 480
+    },
+    {
+      "loss": 2.6714,
+      "grad_norm": 0.951770544052124,
+      "learning_rate": 8e-05,
+      "epoch": 3.2666666666666666,
+      "step": 490
+    },
+    {
+      "loss": 2.591,
+      "grad_norm": 1.041982650756836,
+      "learning_rate": 7.692307692307693e-05,
+      "epoch": 3.3333333333333335,
+      "step": 500
+    },
+    {
+      "loss": 2.6331,
+      "grad_norm": 0.841515302658081,
+      "learning_rate": 7.384615384615386e-05,
+      "epoch": 3.4,
+      "step": 510
+    },
+    {
+      "loss": 2.6107,
+      "grad_norm": 1.0214762687683105,
+      "learning_rate": 7.076923076923078e-05,
+      "epoch": 3.466666666666667,
+      "step": 520
+    },
+    {
+      "loss": 2.602,
+      "grad_norm": 1.0101308822631836,
+      "learning_rate": 6.76923076923077e-05,
+      "epoch": 3.533333333333333,
+      "step": 530
+    },
+    {
+      "loss": 2.5848,
+      "grad_norm": 1.0108872652053833,
+      "learning_rate": 6.461538461538462e-05,
+      "epoch": 3.6,
+      "step": 540
+    },
+    {
+      "loss": 2.6113,
+      "grad_norm": 0.8662316203117371,
+      "learning_rate": 6.153846153846155e-05,
+      "epoch": 3.6666666666666665,
+      "step": 550
+    },
+    {
+      "loss": 2.5327,
+      "grad_norm": 1.0422335863113403,
+      "learning_rate": 5.846153846153847e-05,
+      "epoch": 3.7333333333333334,
+      "step": 560
+    },
+    {
+      "loss": 2.6224,
+      "grad_norm": 1.1712912321090698,
+      "learning_rate": 5.538461538461539e-05,
+      "epoch": 3.8,
+      "step": 570
+    },
+    {
+      "loss": 2.5496,
+      "grad_norm": 1.0437134504318237,
+      "learning_rate": 5.230769230769231e-05,
+      "epoch": 3.8666666666666667,
+      "step": 580
+    },
+    {
+      "loss": 2.5634,
+      "grad_norm": 1.3136959075927734,
+      "learning_rate": 4.923076923076924e-05,
+      "epoch": 3.9333333333333336,
+      "step": 590
+    },
+    {
+      "loss": 2.612,
+      "grad_norm": 1.0888906717300415,
+      "learning_rate": 4.615384615384616e-05,
+      "epoch": 4.0,
+      "step": 600
+    },
+    {
+      "eval_loss": 2.590850591659546,
+      "eval_runtime": 7.4965,
+      "eval_samples_per_second": 79.904,
+      "eval_steps_per_second": 10.005,
+      "epoch": 4.0,
+      "step": 600
+    },
+    {
+      "loss": 2.6115,
+      "grad_norm": 0.8694093227386475,
+      "learning_rate": 4.3076923076923084e-05,
+      "epoch": 4.066666666666666,
+      "step": 610
+    },
+    {
+      "loss": 2.6551,
+      "grad_norm": 1.1008319854736328,
+      "learning_rate": 4e-05,
+      "epoch": 4.133333333333334,
+      "step": 620
+    },
+    {
+      "loss": 2.5686,
+      "grad_norm": 0.9342700242996216,
+      "learning_rate": 3.692307692307693e-05,
+      "epoch": 4.2,
+      "step": 630
+    },
+    {
+      "loss": 2.5452,
+      "grad_norm": 1.0569343566894531,
+      "learning_rate": 3.384615384615385e-05,
+      "epoch": 4.266666666666667,
+      "step": 640
+    },
+    {
+      "loss": 2.5536,
+      "grad_norm": 0.926317036151886,
+      "learning_rate": 3.0769230769230774e-05,
+      "epoch": 4.333333333333333,
+      "step": 650
+    },
+    {
+      "loss": 2.5586,
+      "grad_norm": 1.263782024383545,
+      "learning_rate": 2.7692307692307694e-05,
+      "epoch": 4.4,
+      "step": 660
+    },
+    {
+      "loss": 2.5765,
+      "grad_norm": 1.0703579187393188,
+      "learning_rate": 2.461538461538462e-05,
+      "epoch": 4.466666666666667,
+      "step": 670
+    },
+    {
+      "loss": 2.5535,
+      "grad_norm": 0.9380658864974976,
+      "learning_rate": 2.1538461538461542e-05,
+      "epoch": 4.533333333333333,
+      "step": 680
+    },
+    {
+      "loss": 2.5605,
+      "grad_norm": 0.8859412670135498,
+      "learning_rate": 1.8461538461538465e-05,
+      "epoch": 4.6,
+      "step": 690
+    },
+    {
+      "loss": 2.6149,
+      "grad_norm": 0.900065541267395,
+      "learning_rate": 1.5384615384615387e-05,
+      "epoch": 4.666666666666667,
+      "step": 700
+    },
+    {
+      "loss": 2.5722,
+      "grad_norm": 0.9021157026290894,
+      "learning_rate": 1.230769230769231e-05,
+      "epoch": 4.733333333333333,
+      "step": 710
+    },
+    {
+      "loss": 2.5968,
+      "grad_norm": 1.1193156242370605,
+      "learning_rate": 9.230769230769232e-06,
+      "epoch": 4.8,
+      "step": 720
+    },
+    {
+      "loss": 2.5686,
+      "grad_norm": 0.8336452841758728,
+      "learning_rate": 6.153846153846155e-06,
+      "epoch": 4.866666666666667,
+      "step": 730
+    },
+    {
+      "loss": 2.6659,
+      "grad_norm": 1.0344734191894531,
+      "learning_rate": 3.0769230769230774e-06,
+      "epoch": 4.933333333333334,
+      "step": 740
+    },
+    {
+      "loss": 2.57,
+      "grad_norm": 1.0548092126846313,
+      "learning_rate": 0.0,
+      "epoch": 5.0,
+      "step": 750
+    },
+    {
+      "eval_loss": 2.5814874172210693,
+      "eval_runtime": 7.5153,
+      "eval_samples_per_second": 79.704,
+      "eval_steps_per_second": 9.98,
+      "epoch": 5.0,
+      "step": 750
+    },
+    {
+      "train_runtime": 795.8933,
+      "train_samples_per_second": 30.149,
+      "train_steps_per_second": 0.942,
+      "total_flos": 9139205848725504.0,
+      "train_loss": 2.6187421900431316,
+      "epoch": 5.0,
+      "step": 750
+    }
+  ]
+}