Upload folder using huggingface_hub

.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 +1,202 @@
+---
+base_model: togethercomputer/gemma-3-27b-it
+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 0.15.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "togethercomputer/gemma-3-27b-it",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": [
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_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 sha256:558e0a6fbf2530718bbfbf55670e738135b3a60ad2b8d34ba0b2da3069fde9c0
+size 1816381256

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e316dda1f34f410e1a27d086d70cbb20164153422fcae753e180a47b083c99b3
+size 18452294

trainer_state.json

@@ -0,0 +1,1329 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 0,
+  "global_step": 185,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005405405405405406,
+      "grad_norm": 2.034959316253662,
+      "learning_rate": 1e-05,
+      "loss": 2.3274,
+      "step": 1
+    },
+    {
+      "epoch": 0.010810810810810811,
+      "grad_norm": 1.8778449296951294,
+      "learning_rate": 9.945945945945947e-06,
+      "loss": 2.227,
+      "step": 2
+    },
+    {
+      "epoch": 0.016216216216216217,
+      "grad_norm": 1.820204734802246,
+      "learning_rate": 9.891891891891893e-06,
+      "loss": 2.3029,
+      "step": 3
+    },
+    {
+      "epoch": 0.021621621621621623,
+      "grad_norm": 1.6635195016860962,
+      "learning_rate": 9.83783783783784e-06,
+      "loss": 2.2474,
+      "step": 4
+    },
+    {
+      "epoch": 0.02702702702702703,
+      "grad_norm": 1.362695336341858,
+      "learning_rate": 9.783783783783785e-06,
+      "loss": 2.0898,
+      "step": 5
+    },
+    {
+      "epoch": 0.032432432432432434,
+      "grad_norm": 1.105480670928955,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 2.0848,
+      "step": 6
+    },
+    {
+      "epoch": 0.03783783783783784,
+      "grad_norm": 0.9252412915229797,
+      "learning_rate": 9.675675675675676e-06,
+      "loss": 2.0229,
+      "step": 7
+    },
+    {
+      "epoch": 0.043243243243243246,
+      "grad_norm": 0.7585290670394897,
+      "learning_rate": 9.621621621621622e-06,
+      "loss": 1.9767,
+      "step": 8
+    },
+    {
+      "epoch": 0.04864864864864865,
+      "grad_norm": 0.7198324203491211,
+      "learning_rate": 9.567567567567568e-06,
+      "loss": 1.9532,
+      "step": 9
+    },
+    {
+      "epoch": 0.05405405405405406,
+      "grad_norm": 0.7078152298927307,
+      "learning_rate": 9.513513513513514e-06,
+      "loss": 1.845,
+      "step": 10
+    },
+    {
+      "epoch": 0.05945945945945946,
+      "grad_norm": 0.7482191920280457,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 1.9299,
+      "step": 11
+    },
+    {
+      "epoch": 0.06486486486486487,
+      "grad_norm": 0.7480123043060303,
+      "learning_rate": 9.405405405405407e-06,
+      "loss": 1.8255,
+      "step": 12
+    },
+    {
+      "epoch": 0.07027027027027027,
+      "grad_norm": 0.8021811842918396,
+      "learning_rate": 9.351351351351353e-06,
+      "loss": 1.8584,
+      "step": 13
+    },
+    {
+      "epoch": 0.07567567567567568,
+      "grad_norm": 0.8102870583534241,
+      "learning_rate": 9.297297297297299e-06,
+      "loss": 1.8065,
+      "step": 14
+    },
+    {
+      "epoch": 0.08108108108108109,
+      "grad_norm": 0.8265206813812256,
+      "learning_rate": 9.243243243243243e-06,
+      "loss": 1.8241,
+      "step": 15
+    },
+    {
+      "epoch": 0.08648648648648649,
+      "grad_norm": 0.7550373673439026,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 1.7726,
+      "step": 16
+    },
+    {
+      "epoch": 0.0918918918918919,
+      "grad_norm": 0.6808019876480103,
+      "learning_rate": 9.135135135135136e-06,
+      "loss": 1.7703,
+      "step": 17
+    },
+    {
+      "epoch": 0.0972972972972973,
+      "grad_norm": 0.6290677189826965,
+      "learning_rate": 9.081081081081082e-06,
+      "loss": 1.7586,
+      "step": 18
+    },
+    {
+      "epoch": 0.10270270270270271,
+      "grad_norm": 0.6062494516372681,
+      "learning_rate": 9.027027027027028e-06,
+      "loss": 1.7713,
+      "step": 19
+    },
+    {
+      "epoch": 0.10810810810810811,
+      "grad_norm": 0.5270338654518127,
+      "learning_rate": 8.972972972972974e-06,
+      "loss": 1.652,
+      "step": 20
+    },
+    {
+      "epoch": 0.11351351351351352,
+      "grad_norm": 0.5446780920028687,
+      "learning_rate": 8.91891891891892e-06,
+      "loss": 1.6587,
+      "step": 21
+    },
+    {
+      "epoch": 0.11891891891891893,
+      "grad_norm": 0.500572681427002,
+      "learning_rate": 8.864864864864866e-06,
+      "loss": 1.6509,
+      "step": 22
+    },
+    {
+      "epoch": 0.12432432432432433,
+      "grad_norm": 0.5181313157081604,
+      "learning_rate": 8.810810810810811e-06,
+      "loss": 1.5852,
+      "step": 23
+    },
+    {
+      "epoch": 0.12972972972972974,
+      "grad_norm": 0.5200425386428833,
+      "learning_rate": 8.756756756756759e-06,
+      "loss": 1.5981,
+      "step": 24
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.4856228232383728,
+      "learning_rate": 8.702702702702703e-06,
+      "loss": 1.562,
+      "step": 25
+    },
+    {
+      "epoch": 0.14054054054054055,
+      "grad_norm": 0.47276848554611206,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 1.6072,
+      "step": 26
+    },
+    {
+      "epoch": 0.14594594594594595,
+      "grad_norm": 0.4729558229446411,
+      "learning_rate": 8.594594594594595e-06,
+      "loss": 1.6082,
+      "step": 27
+    },
+    {
+      "epoch": 0.15135135135135136,
+      "grad_norm": 0.4218498468399048,
+      "learning_rate": 8.540540540540542e-06,
+      "loss": 1.5092,
+      "step": 28
+    },
+    {
+      "epoch": 0.15675675675675677,
+      "grad_norm": 0.4382428526878357,
+      "learning_rate": 8.486486486486488e-06,
+      "loss": 1.5741,
+      "step": 29
+    },
+    {
+      "epoch": 0.16216216216216217,
+      "grad_norm": 0.4070360064506531,
+      "learning_rate": 8.432432432432434e-06,
+      "loss": 1.5187,
+      "step": 30
+    },
+    {
+      "epoch": 0.16756756756756758,
+      "grad_norm": 0.41073259711265564,
+      "learning_rate": 8.378378378378378e-06,
+      "loss": 1.4882,
+      "step": 31
+    },
+    {
+      "epoch": 0.17297297297297298,
+      "grad_norm": 0.4228561222553253,
+      "learning_rate": 8.324324324324326e-06,
+      "loss": 1.4688,
+      "step": 32
+    },
+    {
+      "epoch": 0.1783783783783784,
+      "grad_norm": 0.39718520641326904,
+      "learning_rate": 8.27027027027027e-06,
+      "loss": 1.4849,
+      "step": 33
+    },
+    {
+      "epoch": 0.1837837837837838,
+      "grad_norm": 0.4296083152294159,
+      "learning_rate": 8.216216216216217e-06,
+      "loss": 1.4872,
+      "step": 34
+    },
+    {
+      "epoch": 0.1891891891891892,
+      "grad_norm": 0.4223209321498871,
+      "learning_rate": 8.162162162162163e-06,
+      "loss": 1.4476,
+      "step": 35
+    },
+    {
+      "epoch": 0.1945945945945946,
+      "grad_norm": 0.40885603427886963,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 1.4787,
+      "step": 36
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.42571428418159485,
+      "learning_rate": 8.054054054054055e-06,
+      "loss": 1.4734,
+      "step": 37
+    },
+    {
+      "epoch": 0.20540540540540542,
+      "grad_norm": 0.3889505863189697,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 1.4245,
+      "step": 38
+    },
+    {
+      "epoch": 0.21081081081081082,
+      "grad_norm": 0.39451542496681213,
+      "learning_rate": 7.945945945945946e-06,
+      "loss": 1.4509,
+      "step": 39
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.3710978329181671,
+      "learning_rate": 7.891891891891894e-06,
+      "loss": 1.4155,
+      "step": 40
+    },
+    {
+      "epoch": 0.22162162162162163,
+      "grad_norm": 0.35685208439826965,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 1.4081,
+      "step": 41
+    },
+    {
+      "epoch": 0.22702702702702704,
+      "grad_norm": 0.33981138467788696,
+      "learning_rate": 7.783783783783784e-06,
+      "loss": 1.3643,
+      "step": 42
+    },
+    {
+      "epoch": 0.23243243243243245,
+      "grad_norm": 0.3623262941837311,
+      "learning_rate": 7.72972972972973e-06,
+      "loss": 1.4029,
+      "step": 43
+    },
+    {
+      "epoch": 0.23783783783783785,
+      "grad_norm": 0.3363046646118164,
+      "learning_rate": 7.675675675675676e-06,
+      "loss": 1.3669,
+      "step": 44
+    },
+    {
+      "epoch": 0.24324324324324326,
+      "grad_norm": 0.33891770243644714,
+      "learning_rate": 7.621621621621622e-06,
+      "loss": 1.3635,
+      "step": 45
+    },
+    {
+      "epoch": 0.24864864864864866,
+      "grad_norm": 0.33656665682792664,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 1.352,
+      "step": 46
+    },
+    {
+      "epoch": 0.25405405405405407,
+      "grad_norm": 0.3358979821205139,
+      "learning_rate": 7.513513513513514e-06,
+      "loss": 1.3606,
+      "step": 47
+    },
+    {
+      "epoch": 0.2594594594594595,
+      "grad_norm": 0.32272347807884216,
+      "learning_rate": 7.45945945945946e-06,
+      "loss": 1.342,
+      "step": 48
+    },
+    {
+      "epoch": 0.2648648648648649,
+      "grad_norm": 0.3023531436920166,
+      "learning_rate": 7.4054054054054055e-06,
+      "loss": 1.3267,
+      "step": 49
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.3095267713069916,
+      "learning_rate": 7.3513513513513525e-06,
+      "loss": 1.342,
+      "step": 50
+    },
+    {
+      "epoch": 0.2756756756756757,
+      "grad_norm": 0.3033177852630615,
+      "learning_rate": 7.297297297297298e-06,
+      "loss": 1.3611,
+      "step": 51
+    },
+    {
+      "epoch": 0.2810810810810811,
+      "grad_norm": 0.29411327838897705,
+      "learning_rate": 7.243243243243244e-06,
+      "loss": 1.3114,
+      "step": 52
+    },
+    {
+      "epoch": 0.2864864864864865,
+      "grad_norm": 0.28862670063972473,
+      "learning_rate": 7.189189189189189e-06,
+      "loss": 1.3045,
+      "step": 53
+    },
+    {
+      "epoch": 0.2918918918918919,
+      "grad_norm": 0.33967703580856323,
+      "learning_rate": 7.135135135135136e-06,
+      "loss": 1.2879,
+      "step": 54
+    },
+    {
+      "epoch": 0.2972972972972973,
+      "grad_norm": 0.3063770532608032,
+      "learning_rate": 7.0810810810810815e-06,
+      "loss": 1.3237,
+      "step": 55
+    },
+    {
+      "epoch": 0.3027027027027027,
+      "grad_norm": 0.2903819978237152,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 1.3088,
+      "step": 56
+    },
+    {
+      "epoch": 0.3081081081081081,
+      "grad_norm": 0.2815365791320801,
+      "learning_rate": 6.972972972972973e-06,
+      "loss": 1.3184,
+      "step": 57
+    },
+    {
+      "epoch": 0.31351351351351353,
+      "grad_norm": 0.3042902946472168,
+      "learning_rate": 6.91891891891892e-06,
+      "loss": 1.3182,
+      "step": 58
+    },
+    {
+      "epoch": 0.31891891891891894,
+      "grad_norm": 0.27602043747901917,
+      "learning_rate": 6.864864864864865e-06,
+      "loss": 1.3051,
+      "step": 59
+    },
+    {
+      "epoch": 0.32432432432432434,
+      "grad_norm": 0.30109262466430664,
+      "learning_rate": 6.810810810810811e-06,
+      "loss": 1.3268,
+      "step": 60
+    },
+    {
+      "epoch": 0.32972972972972975,
+      "grad_norm": 0.27311018109321594,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 1.305,
+      "step": 61
+    },
+    {
+      "epoch": 0.33513513513513515,
+      "grad_norm": 0.2715848684310913,
+      "learning_rate": 6.702702702702704e-06,
+      "loss": 1.3034,
+      "step": 62
+    },
+    {
+      "epoch": 0.34054054054054056,
+      "grad_norm": 0.2581041157245636,
+      "learning_rate": 6.648648648648649e-06,
+      "loss": 1.2567,
+      "step": 63
+    },
+    {
+      "epoch": 0.34594594594594597,
+      "grad_norm": 0.26454904675483704,
+      "learning_rate": 6.594594594594595e-06,
+      "loss": 1.2792,
+      "step": 64
+    },
+    {
+      "epoch": 0.35135135135135137,
+      "grad_norm": 0.27279508113861084,
+      "learning_rate": 6.540540540540541e-06,
+      "loss": 1.2745,
+      "step": 65
+    },
+    {
+      "epoch": 0.3567567567567568,
+      "grad_norm": 0.27239367365837097,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 1.2947,
+      "step": 66
+    },
+    {
+      "epoch": 0.3621621621621622,
+      "grad_norm": 0.2796631455421448,
+      "learning_rate": 6.432432432432433e-06,
+      "loss": 1.2705,
+      "step": 67
+    },
+    {
+      "epoch": 0.3675675675675676,
+      "grad_norm": 0.266652911901474,
+      "learning_rate": 6.378378378378379e-06,
+      "loss": 1.2441,
+      "step": 68
+    },
+    {
+      "epoch": 0.372972972972973,
+      "grad_norm": 0.26300087571144104,
+      "learning_rate": 6.324324324324325e-06,
+      "loss": 1.259,
+      "step": 69
+    },
+    {
+      "epoch": 0.3783783783783784,
+      "grad_norm": 0.3145560622215271,
+      "learning_rate": 6.270270270270271e-06,
+      "loss": 1.3417,
+      "step": 70
+    },
+    {
+      "epoch": 0.3837837837837838,
+      "grad_norm": 0.2778513729572296,
+      "learning_rate": 6.2162162162162164e-06,
+      "loss": 1.2198,
+      "step": 71
+    },
+    {
+      "epoch": 0.3891891891891892,
+      "grad_norm": 0.25896984338760376,
+      "learning_rate": 6.162162162162163e-06,
+      "loss": 1.231,
+      "step": 72
+    },
+    {
+      "epoch": 0.3945945945945946,
+      "grad_norm": 0.2606508433818817,
+      "learning_rate": 6.108108108108109e-06,
+      "loss": 1.2799,
+      "step": 73
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.2623414695262909,
+      "learning_rate": 6.054054054054055e-06,
+      "loss": 1.2269,
+      "step": 74
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.26297539472579956,
+      "learning_rate": 6e-06,
+      "loss": 1.2751,
+      "step": 75
+    },
+    {
+      "epoch": 0.41081081081081083,
+      "grad_norm": 0.24481281638145447,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 1.2047,
+      "step": 76
+    },
+    {
+      "epoch": 0.41621621621621624,
+      "grad_norm": 0.2644273340702057,
+      "learning_rate": 5.8918918918918924e-06,
+      "loss": 1.2507,
+      "step": 77
+    },
+    {
+      "epoch": 0.42162162162162165,
+      "grad_norm": 0.2676522731781006,
+      "learning_rate": 5.837837837837839e-06,
+      "loss": 1.2374,
+      "step": 78
+    },
+    {
+      "epoch": 0.42702702702702705,
+      "grad_norm": 0.2541520297527313,
+      "learning_rate": 5.783783783783784e-06,
+      "loss": 1.2225,
+      "step": 79
+    },
+    {
+      "epoch": 0.43243243243243246,
+      "grad_norm": 0.252860426902771,
+      "learning_rate": 5.729729729729731e-06,
+      "loss": 1.225,
+      "step": 80
+    },
+    {
+      "epoch": 0.43783783783783786,
+      "grad_norm": 0.24671323597431183,
+      "learning_rate": 5.675675675675676e-06,
+      "loss": 1.1988,
+      "step": 81
+    },
+    {
+      "epoch": 0.44324324324324327,
+      "grad_norm": 0.25774669647216797,
+      "learning_rate": 5.621621621621622e-06,
+      "loss": 1.1917,
+      "step": 82
+    },
+    {
+      "epoch": 0.4486486486486487,
+      "grad_norm": 0.2582065165042877,
+      "learning_rate": 5.567567567567568e-06,
+      "loss": 1.2049,
+      "step": 83
+    },
+    {
+      "epoch": 0.4540540540540541,
+      "grad_norm": 0.2658644914627075,
+      "learning_rate": 5.513513513513515e-06,
+      "loss": 1.1864,
+      "step": 84
+    },
+    {
+      "epoch": 0.4594594594594595,
+      "grad_norm": 0.2440362274646759,
+      "learning_rate": 5.45945945945946e-06,
+      "loss": 1.1772,
+      "step": 85
+    },
+    {
+      "epoch": 0.4648648648648649,
+      "grad_norm": 0.2492218315601349,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 1.2137,
+      "step": 86
+    },
+    {
+      "epoch": 0.4702702702702703,
+      "grad_norm": 0.2513432204723358,
+      "learning_rate": 5.351351351351351e-06,
+      "loss": 1.2077,
+      "step": 87
+    },
+    {
+      "epoch": 0.4756756756756757,
+      "grad_norm": 0.252913236618042,
+      "learning_rate": 5.297297297297298e-06,
+      "loss": 1.215,
+      "step": 88
+    },
+    {
+      "epoch": 0.4810810810810811,
+      "grad_norm": 0.24399417638778687,
+      "learning_rate": 5.243243243243244e-06,
+      "loss": 1.1977,
+      "step": 89
+    },
+    {
+      "epoch": 0.4864864864864865,
+      "grad_norm": 0.2553783059120178,
+      "learning_rate": 5.18918918918919e-06,
+      "loss": 1.2004,
+      "step": 90
+    },
+    {
+      "epoch": 0.4918918918918919,
+      "grad_norm": 0.24357211589813232,
+      "learning_rate": 5.135135135135135e-06,
+      "loss": 1.1741,
+      "step": 91
+    },
+    {
+      "epoch": 0.4972972972972973,
+      "grad_norm": 0.2634775638580322,
+      "learning_rate": 5.081081081081082e-06,
+      "loss": 1.1964,
+      "step": 92
+    },
+    {
+      "epoch": 0.5027027027027027,
+      "grad_norm": 0.24633990228176117,
+      "learning_rate": 5.027027027027027e-06,
+      "loss": 1.1541,
+      "step": 93
+    },
+    {
+      "epoch": 0.5081081081081081,
+      "grad_norm": 0.2492210417985916,
+      "learning_rate": 4.9729729729729735e-06,
+      "loss": 1.1663,
+      "step": 94
+    },
+    {
+      "epoch": 0.5135135135135135,
+      "grad_norm": 0.24858078360557556,
+      "learning_rate": 4.91891891891892e-06,
+      "loss": 1.1684,
+      "step": 95
+    },
+    {
+      "epoch": 0.518918918918919,
+      "grad_norm": 0.24967968463897705,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 1.1695,
+      "step": 96
+    },
+    {
+      "epoch": 0.5243243243243243,
+      "grad_norm": 0.24852266907691956,
+      "learning_rate": 4.810810810810811e-06,
+      "loss": 1.1529,
+      "step": 97
+    },
+    {
+      "epoch": 0.5297297297297298,
+      "grad_norm": 0.24503152072429657,
+      "learning_rate": 4.756756756756757e-06,
+      "loss": 1.1689,
+      "step": 98
+    },
+    {
+      "epoch": 0.5351351351351351,
+      "grad_norm": 0.25913184881210327,
+      "learning_rate": 4.702702702702703e-06,
+      "loss": 1.1888,
+      "step": 99
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.23641978204250336,
+      "learning_rate": 4.6486486486486495e-06,
+      "loss": 1.1676,
+      "step": 100
+    },
+    {
+      "epoch": 0.5459459459459459,
+      "grad_norm": 0.25850117206573486,
+      "learning_rate": 4.594594594594596e-06,
+      "loss": 1.1609,
+      "step": 101
+    },
+    {
+      "epoch": 0.5513513513513514,
+      "grad_norm": 0.24710091948509216,
+      "learning_rate": 4.540540540540541e-06,
+      "loss": 1.1522,
+      "step": 102
+    },
+    {
+      "epoch": 0.5567567567567567,
+      "grad_norm": 0.2579835057258606,
+      "learning_rate": 4.486486486486487e-06,
+      "loss": 1.1872,
+      "step": 103
+    },
+    {
+      "epoch": 0.5621621621621622,
+      "grad_norm": 0.26577505469322205,
+      "learning_rate": 4.432432432432433e-06,
+      "loss": 1.1775,
+      "step": 104
+    },
+    {
+      "epoch": 0.5675675675675675,
+      "grad_norm": 0.289943665266037,
+      "learning_rate": 4.378378378378379e-06,
+      "loss": 1.1849,
+      "step": 105
+    },
+    {
+      "epoch": 0.572972972972973,
+      "grad_norm": 0.29339632391929626,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 1.1607,
+      "step": 106
+    },
+    {
+      "epoch": 0.5783783783783784,
+      "grad_norm": 0.24826812744140625,
+      "learning_rate": 4.270270270270271e-06,
+      "loss": 1.1834,
+      "step": 107
+    },
+    {
+      "epoch": 0.5837837837837838,
+      "grad_norm": 0.24059158563613892,
+      "learning_rate": 4.216216216216217e-06,
+      "loss": 1.1611,
+      "step": 108
+    },
+    {
+      "epoch": 0.5891891891891892,
+      "grad_norm": 0.2687944769859314,
+      "learning_rate": 4.162162162162163e-06,
+      "loss": 1.1515,
+      "step": 109
+    },
+    {
+      "epoch": 0.5945945945945946,
+      "grad_norm": 0.27312615513801575,
+      "learning_rate": 4.108108108108108e-06,
+      "loss": 1.1971,
+      "step": 110
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.27208036184310913,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 1.1789,
+      "step": 111
+    },
+    {
+      "epoch": 0.6054054054054054,
+      "grad_norm": 0.2820265591144562,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1981,
+      "step": 112
+    },
+    {
+      "epoch": 0.6108108108108108,
+      "grad_norm": 0.26071199774742126,
+      "learning_rate": 3.945945945945947e-06,
+      "loss": 1.1936,
+      "step": 113
+    },
+    {
+      "epoch": 0.6162162162162163,
+      "grad_norm": 0.2583164870738983,
+      "learning_rate": 3.891891891891892e-06,
+      "loss": 1.1672,
+      "step": 114
+    },
+    {
+      "epoch": 0.6216216216216216,
+      "grad_norm": 0.27570709586143494,
+      "learning_rate": 3.837837837837838e-06,
+      "loss": 1.2096,
+      "step": 115
+    },
+    {
+      "epoch": 0.6270270270270271,
+      "grad_norm": 0.2592144012451172,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 1.169,
+      "step": 116
+    },
+    {
+      "epoch": 0.6324324324324324,
+      "grad_norm": 0.26106804609298706,
+      "learning_rate": 3.72972972972973e-06,
+      "loss": 1.1912,
+      "step": 117
+    },
+    {
+      "epoch": 0.6378378378378379,
+      "grad_norm": 0.25909966230392456,
+      "learning_rate": 3.6756756756756763e-06,
+      "loss": 1.1462,
+      "step": 118
+    },
+    {
+      "epoch": 0.6432432432432432,
+      "grad_norm": 0.28418397903442383,
+      "learning_rate": 3.621621621621622e-06,
+      "loss": 1.1584,
+      "step": 119
+    },
+    {
+      "epoch": 0.6486486486486487,
+      "grad_norm": 0.26269835233688354,
+      "learning_rate": 3.567567567567568e-06,
+      "loss": 1.1556,
+      "step": 120
+    },
+    {
+      "epoch": 0.654054054054054,
+      "grad_norm": 0.2741927206516266,
+      "learning_rate": 3.513513513513514e-06,
+      "loss": 1.1681,
+      "step": 121
+    },
+    {
+      "epoch": 0.6594594594594595,
+      "grad_norm": 0.2586127519607544,
+      "learning_rate": 3.45945945945946e-06,
+      "loss": 1.1531,
+      "step": 122
+    },
+    {
+      "epoch": 0.6648648648648648,
+      "grad_norm": 0.25531938672065735,
+      "learning_rate": 3.4054054054054057e-06,
+      "loss": 1.1636,
+      "step": 123
+    },
+    {
+      "epoch": 0.6702702702702703,
+      "grad_norm": 0.2960667610168457,
+      "learning_rate": 3.351351351351352e-06,
+      "loss": 1.1818,
+      "step": 124
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.31269460916519165,
+      "learning_rate": 3.2972972972972976e-06,
+      "loss": 1.2105,
+      "step": 125
+    },
+    {
+      "epoch": 0.6810810810810811,
+      "grad_norm": 0.2489175945520401,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 1.1327,
+      "step": 126
+    },
+    {
+      "epoch": 0.6864864864864865,
+      "grad_norm": 0.27137380838394165,
+      "learning_rate": 3.1891891891891894e-06,
+      "loss": 1.1882,
+      "step": 127
+    },
+    {
+      "epoch": 0.6918918918918919,
+      "grad_norm": 0.27693238854408264,
+      "learning_rate": 3.1351351351351356e-06,
+      "loss": 1.1574,
+      "step": 128
+    },
+    {
+      "epoch": 0.6972972972972973,
+      "grad_norm": 0.26204511523246765,
+      "learning_rate": 3.0810810810810817e-06,
+      "loss": 1.1535,
+      "step": 129
+    },
+    {
+      "epoch": 0.7027027027027027,
+      "grad_norm": 0.2716626822948456,
+      "learning_rate": 3.0270270270270274e-06,
+      "loss": 1.1572,
+      "step": 130
+    },
+    {
+      "epoch": 0.7081081081081081,
+      "grad_norm": 0.2737910747528076,
+      "learning_rate": 2.9729729729729736e-06,
+      "loss": 1.1453,
+      "step": 131
+    },
+    {
+      "epoch": 0.7135135135135136,
+      "grad_norm": 0.2846289873123169,
+      "learning_rate": 2.9189189189189193e-06,
+      "loss": 1.1371,
+      "step": 132
+    },
+    {
+      "epoch": 0.7189189189189189,
+      "grad_norm": 0.2652347683906555,
+      "learning_rate": 2.8648648648648654e-06,
+      "loss": 1.1399,
+      "step": 133
+    },
+    {
+      "epoch": 0.7243243243243244,
+      "grad_norm": 0.26175656914711,
+      "learning_rate": 2.810810810810811e-06,
+      "loss": 1.1691,
+      "step": 134
+    },
+    {
+      "epoch": 0.7297297297297297,
+      "grad_norm": 0.274801641702652,
+      "learning_rate": 2.7567567567567573e-06,
+      "loss": 1.1563,
+      "step": 135
+    },
+    {
+      "epoch": 0.7351351351351352,
+      "grad_norm": 0.2784542143344879,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 1.178,
+      "step": 136
+    },
+    {
+      "epoch": 0.7405405405405405,
+      "grad_norm": 0.26470088958740234,
+      "learning_rate": 2.648648648648649e-06,
+      "loss": 1.1688,
+      "step": 137
+    },
+    {
+      "epoch": 0.745945945945946,
+      "grad_norm": 0.27295202016830444,
+      "learning_rate": 2.594594594594595e-06,
+      "loss": 1.1403,
+      "step": 138
+    },
+    {
+      "epoch": 0.7513513513513513,
+      "grad_norm": 0.2557908892631531,
+      "learning_rate": 2.540540540540541e-06,
+      "loss": 1.1573,
+      "step": 139
+    },
+    {
+      "epoch": 0.7567567567567568,
+      "grad_norm": 0.27424272894859314,
+      "learning_rate": 2.4864864864864867e-06,
+      "loss": 1.1423,
+      "step": 140
+    },
+    {
+      "epoch": 0.7621621621621621,
+      "grad_norm": 0.2811051607131958,
+      "learning_rate": 2.432432432432433e-06,
+      "loss": 1.1549,
+      "step": 141
+    },
+    {
+      "epoch": 0.7675675675675676,
+      "grad_norm": 0.25805169343948364,
+      "learning_rate": 2.3783783783783786e-06,
+      "loss": 1.1486,
+      "step": 142
+    },
+    {
+      "epoch": 0.772972972972973,
+      "grad_norm": 0.26995599269866943,
+      "learning_rate": 2.3243243243243247e-06,
+      "loss": 1.1357,
+      "step": 143
+    },
+    {
+      "epoch": 0.7783783783783784,
+      "grad_norm": 0.2542300224304199,
+      "learning_rate": 2.2702702702702705e-06,
+      "loss": 1.1208,
+      "step": 144
+    },
+    {
+      "epoch": 0.7837837837837838,
+      "grad_norm": 0.24706785380840302,
+      "learning_rate": 2.2162162162162166e-06,
+      "loss": 1.1324,
+      "step": 145
+    },
+    {
+      "epoch": 0.7891891891891892,
+      "grad_norm": 0.2644682824611664,
+      "learning_rate": 2.1621621621621623e-06,
+      "loss": 1.121,
+      "step": 146
+    },
+    {
+      "epoch": 0.7945945945945946,
+      "grad_norm": 0.2919802665710449,
+      "learning_rate": 2.1081081081081085e-06,
+      "loss": 1.1779,
+      "step": 147
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.2681489586830139,
+      "learning_rate": 2.054054054054054e-06,
+      "loss": 1.1651,
+      "step": 148
+    },
+    {
+      "epoch": 0.8054054054054054,
+      "grad_norm": 0.24865786731243134,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.1272,
+      "step": 149
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.26049530506134033,
+      "learning_rate": 1.945945945945946e-06,
+      "loss": 1.1299,
+      "step": 150
+    },
+    {
+      "epoch": 0.8162162162162162,
+      "grad_norm": 0.2903294265270233,
+      "learning_rate": 1.8918918918918922e-06,
+      "loss": 1.1751,
+      "step": 151
+    },
+    {
+      "epoch": 0.8216216216216217,
+      "grad_norm": 0.274706095457077,
+      "learning_rate": 1.8378378378378381e-06,
+      "loss": 1.1493,
+      "step": 152
+    },
+    {
+      "epoch": 0.827027027027027,
+      "grad_norm": 0.2549731433391571,
+      "learning_rate": 1.783783783783784e-06,
+      "loss": 1.1345,
+      "step": 153
+    },
+    {
+      "epoch": 0.8324324324324325,
+      "grad_norm": 0.26216205954551697,
+      "learning_rate": 1.72972972972973e-06,
+      "loss": 1.1316,
+      "step": 154
+    },
+    {
+      "epoch": 0.8378378378378378,
+      "grad_norm": 0.26119425892829895,
+      "learning_rate": 1.675675675675676e-06,
+      "loss": 1.132,
+      "step": 155
+    },
+    {
+      "epoch": 0.8432432432432433,
+      "grad_norm": 0.26794594526290894,
+      "learning_rate": 1.6216216216216219e-06,
+      "loss": 1.1532,
+      "step": 156
+    },
+    {
+      "epoch": 0.8486486486486486,
+      "grad_norm": 0.2842087745666504,
+      "learning_rate": 1.5675675675675678e-06,
+      "loss": 1.0995,
+      "step": 157
+    },
+    {
+      "epoch": 0.8540540540540541,
+      "grad_norm": 0.26724207401275635,
+      "learning_rate": 1.5135135135135137e-06,
+      "loss": 1.102,
+      "step": 158
+    },
+    {
+      "epoch": 0.8594594594594595,
+      "grad_norm": 0.2525201737880707,
+      "learning_rate": 1.4594594594594596e-06,
+      "loss": 1.095,
+      "step": 159
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.2626565098762512,
+      "learning_rate": 1.4054054054054056e-06,
+      "loss": 1.1435,
+      "step": 160
+    },
+    {
+      "epoch": 0.8702702702702703,
+      "grad_norm": 0.2600706219673157,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 1.1316,
+      "step": 161
+    },
+    {
+      "epoch": 0.8756756756756757,
+      "grad_norm": 0.2661210596561432,
+      "learning_rate": 1.2972972972972974e-06,
+      "loss": 1.1423,
+      "step": 162
+    },
+    {
+      "epoch": 0.8810810810810811,
+      "grad_norm": 0.2888488173484802,
+      "learning_rate": 1.2432432432432434e-06,
+      "loss": 1.1384,
+      "step": 163
+    },
+    {
+      "epoch": 0.8864864864864865,
+      "grad_norm": 0.25049468874931335,
+      "learning_rate": 1.1891891891891893e-06,
+      "loss": 1.1257,
+      "step": 164
+    },
+    {
+      "epoch": 0.8918918918918919,
+      "grad_norm": 0.2596016526222229,
+      "learning_rate": 1.1351351351351352e-06,
+      "loss": 1.139,
+      "step": 165
+    },
+    {
+      "epoch": 0.8972972972972973,
+      "grad_norm": 0.26817384362220764,
+      "learning_rate": 1.0810810810810812e-06,
+      "loss": 1.1399,
+      "step": 166
+    },
+    {
+      "epoch": 0.9027027027027027,
+      "grad_norm": 0.27717313170433044,
+      "learning_rate": 1.027027027027027e-06,
+      "loss": 1.1356,
+      "step": 167
+    },
+    {
+      "epoch": 0.9081081081081082,
+      "grad_norm": 0.27815675735473633,
+      "learning_rate": 9.72972972972973e-07,
+      "loss": 1.0882,
+      "step": 168
+    },
+    {
+      "epoch": 0.9135135135135135,
+      "grad_norm": 0.26827895641326904,
+      "learning_rate": 9.189189189189191e-07,
+      "loss": 1.1382,
+      "step": 169
+    },
+    {
+      "epoch": 0.918918918918919,
+      "grad_norm": 0.26916950941085815,
+      "learning_rate": 8.64864864864865e-07,
+      "loss": 1.1633,
+      "step": 170
+    },
+    {
+      "epoch": 0.9243243243243243,
+      "grad_norm": 0.2528124451637268,
+      "learning_rate": 8.108108108108109e-07,
+      "loss": 1.13,
+      "step": 171
+    },
+    {
+      "epoch": 0.9297297297297298,
+      "grad_norm": 0.2664795219898224,
+      "learning_rate": 7.567567567567569e-07,
+      "loss": 1.1121,
+      "step": 172
+    },
+    {
+      "epoch": 0.9351351351351351,
+      "grad_norm": 0.257194846868515,
+      "learning_rate": 7.027027027027028e-07,
+      "loss": 1.1416,
+      "step": 173
+    },
+    {
+      "epoch": 0.9405405405405406,
+      "grad_norm": 0.2620390057563782,
+      "learning_rate": 6.486486486486487e-07,
+      "loss": 1.1354,
+      "step": 174
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.25638052821159363,
+      "learning_rate": 5.945945945945947e-07,
+      "loss": 1.15,
+      "step": 175
+    },
+    {
+      "epoch": 0.9513513513513514,
+      "grad_norm": 0.25654318928718567,
+      "learning_rate": 5.405405405405406e-07,
+      "loss": 1.114,
+      "step": 176
+    },
+    {
+      "epoch": 0.9567567567567568,
+      "grad_norm": 0.3269580006599426,
+      "learning_rate": 4.864864864864865e-07,
+      "loss": 1.1254,
+      "step": 177
+    },
+    {
+      "epoch": 0.9621621621621622,
+      "grad_norm": 0.26131343841552734,
+      "learning_rate": 4.324324324324325e-07,
+      "loss": 1.0901,
+      "step": 178
+    },
+    {
+      "epoch": 0.9675675675675676,
+      "grad_norm": 0.2583537697792053,
+      "learning_rate": 3.7837837837837843e-07,
+      "loss": 1.1467,
+      "step": 179
+    },
+    {
+      "epoch": 0.972972972972973,
+      "grad_norm": 0.2696709930896759,
+      "learning_rate": 3.2432432432432436e-07,
+      "loss": 1.1198,
+      "step": 180
+    },
+    {
+      "epoch": 0.9783783783783784,
+      "grad_norm": 0.2895946502685547,
+      "learning_rate": 2.702702702702703e-07,
+      "loss": 1.1572,
+      "step": 181
+    },
+    {
+      "epoch": 0.9837837837837838,
+      "grad_norm": 0.25485262274742126,
+      "learning_rate": 2.1621621621621625e-07,
+      "loss": 1.152,
+      "step": 182
+    },
+    {
+      "epoch": 0.9891891891891892,
+      "grad_norm": 0.262500524520874,
+      "learning_rate": 1.6216216216216218e-07,
+      "loss": 1.1578,
+      "step": 183
+    },
+    {
+      "epoch": 0.9945945945945946,
+      "grad_norm": 0.26408693194389343,
+      "learning_rate": 1.0810810810810812e-07,
+      "loss": 1.1164,
+      "step": 184
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2597890794277191,
+      "learning_rate": 5.405405405405406e-08,
+      "loss": 1.1132,
+      "step": 185
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 185,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 3.3279459925898035e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}