Upload folder using huggingface_hub

README.md

@@ -1,3 +1,202 @@
----
-license: apache-2.0
----
+---
+base_model: liuhaotian/llava-v1.5-13b
+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 0.12.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../../data/output_model/lora/llava-v1.5-13b",
+  "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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85e4922822ac583f7d43bb1a425f9b287441ca93b18840b9069b7ca35311b394
+size 1001466944

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "../../data/output_model/lora/llava-v1.5-13b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d424214b32f5a830e574c479951f80399efe4cf31585f2685685f8318e2be1cd
+size 62937264

trainer_state.json

@@ -0,0 +1,1020 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 165,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4e-05,
+      "loss": 0.7308,
+      "step": 1
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 8e-05,
+      "loss": 0.7,
+      "step": 2
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00012,
+      "loss": 0.6932,
+      "step": 3
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00016,
+      "loss": 0.1717,
+      "step": 4
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0002,
+      "loss": 0.1467,
+      "step": 5
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001999807240482065,
+      "loss": 0.5613,
+      "step": 6
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001999229036240723,
+      "loss": 0.6399,
+      "step": 7
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019982656101847162,
+      "loss": 0.5877,
+      "step": 8
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001996917333733128,
+      "loss": 0.6128,
+      "step": 9
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0001995184726672197,
+      "loss": 0.5388,
+      "step": 10
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00019930684569549264,
+      "loss": 0.5693,
+      "step": 11
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019905693404435773,
+      "loss": 0.5512,
+      "step": 12
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.5714,
+      "step": 13
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00019844265680898918,
+      "loss": 0.6029,
+      "step": 14
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00019807852804032305,
+      "loss": 0.6278,
+      "step": 15
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00019767658813208726,
+      "loss": 0.6119,
+      "step": 16
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 0.5703,
+      "step": 17
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00019675990923602598,
+      "loss": 0.5531,
+      "step": 18
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00019624552364536473,
+      "loss": 0.553,
+      "step": 19
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0001956940335732209,
+      "loss": 0.6646,
+      "step": 20
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.5766,
+      "step": 21
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00019448060464668783,
+      "loss": 0.6177,
+      "step": 22
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019381913359224842,
+      "loss": 0.5593,
+      "step": 23
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019312149347588037,
+      "loss": 0.5543,
+      "step": 24
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.6438,
+      "step": 25
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00019161879571171362,
+      "loss": 0.5968,
+      "step": 26
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00019081431738250814,
+      "loss": 0.5542,
+      "step": 27
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00018997482840522217,
+      "loss": 0.6355,
+      "step": 28
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.6028,
+      "step": 29
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0001881921264348355,
+      "loss": 0.5958,
+      "step": 30
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00018724960070727972,
+      "loss": 0.5749,
+      "step": 31
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0001862734385977792,
+      "loss": 0.5875,
+      "step": 32
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00018526401643540922,
+      "loss": 0.5472,
+      "step": 33
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00018422172337162867,
+      "loss": 0.5826,
+      "step": 34
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00018314696123025454,
+      "loss": 0.6219,
+      "step": 35
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00018204014435255135,
+      "loss": 0.574,
+      "step": 36
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.556,
+      "step": 37
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00017973206537727073,
+      "loss": 0.666,
+      "step": 38
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00017853169308807448,
+      "loss": 0.6155,
+      "step": 39
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001773010453362737,
+      "loss": 0.6071,
+      "step": 40
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001760405965600031,
+      "loss": 0.5707,
+      "step": 41
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001747508326862597,
+      "loss": 0.5269,
+      "step": 42
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00017343225094356855,
+      "loss": 0.6333,
+      "step": 43
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00017208535967029188,
+      "loss": 0.5913,
+      "step": 44
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.5305,
+      "step": 45
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.0001693087362545636,
+      "loss": 0.5925,
+      "step": 46
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001678800745532942,
+      "loss": 0.6115,
+      "step": 47
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00016642524379112817,
+      "loss": 0.5821,
+      "step": 48
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.5774,
+      "step": 49
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00016343932841636456,
+      "loss": 0.6432,
+      "step": 50
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.00016190939493098344,
+      "loss": 0.6022,
+      "step": 51
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.00016035559419535716,
+      "loss": 0.6649,
+      "step": 52
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.6162,
+      "step": 53
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.00015717879602276122,
+      "loss": 0.6176,
+      "step": 54
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 0.252,
+      "step": 55
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.00015391383229110007,
+      "loss": 0.4463,
+      "step": 56
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 0.0001522498564715949,
+      "loss": 0.3958,
+      "step": 57
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 0.00015056573733779848,
+      "loss": 0.3796,
+      "step": 58
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00014886212414969553,
+      "loss": 0.4192,
+      "step": 59
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0001471396736825998,
+      "loss": 0.3784,
+      "step": 60
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.1074,
+      "step": 61
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001436409240673342,
+      "loss": 0.4203,
+      "step": 62
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.0001418659737537428,
+      "loss": 0.3724,
+      "step": 63
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001400748833103141,
+      "loss": 0.3961,
+      "step": 64
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 0.000138268343236509,
+      "loss": 0.3634,
+      "step": 65
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.000136447049987915,
+      "loss": 0.4205,
+      "step": 66
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001346117057077493,
+      "loss": 0.3778,
+      "step": 67
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 0.00013276301795616936,
+      "loss": 0.3271,
+      "step": 68
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.368,
+      "step": 69
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 0.00012902846772544624,
+      "loss": 0.3912,
+      "step": 70
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 0.00012714404498650743,
+      "loss": 0.3353,
+      "step": 71
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0001252491577015158,
+      "loss": 0.3486,
+      "step": 72
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.4001,
+      "step": 73
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 0.00012143091530650508,
+      "loss": 0.338,
+      "step": 74
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 0.00011950903220161285,
+      "loss": 0.3944,
+      "step": 75
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00011757962799343547,
+      "loss": 0.3361,
+      "step": 76
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.3868,
+      "step": 77
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 0.00011370123416819682,
+      "loss": 0.3375,
+      "step": 78
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00011175373974578378,
+      "loss": 0.3797,
+      "step": 79
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 0.0001098017140329561,
+      "loss": 0.3836,
+      "step": 80
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.3387,
+      "step": 81
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 0.0001058870803651189,
+      "loss": 0.3692,
+      "step": 82
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.00010392598157590688,
+      "loss": 0.3511,
+      "step": 83
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00010196336924606283,
+      "loss": 0.3645,
+      "step": 84
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 0.0001,
+      "loss": 0.3675,
+      "step": 85
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 9.803663075393718e-05,
+      "loss": 0.3701,
+      "step": 86
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 9.607401842409317e-05,
+      "loss": 0.3464,
+      "step": 87
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 9.411291963488109e-05,
+      "loss": 0.3673,
+      "step": 88
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.3182,
+      "step": 89
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.019828596704394e-05,
+      "loss": 0.4204,
+      "step": 90
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 8.824626025421626e-05,
+      "loss": 0.3609,
+      "step": 91
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 8.629876583180321e-05,
+      "loss": 0.3071,
+      "step": 92
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.3639,
+      "step": 93
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 8.242037200656455e-05,
+      "loss": 0.4159,
+      "step": 94
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.344,
+      "step": 95
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 7.856908469349495e-05,
+      "loss": 0.3988,
+      "step": 96
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.3804,
+      "step": 97
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 7.47508422984842e-05,
+      "loss": 0.3491,
+      "step": 98
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 7.285595501349258e-05,
+      "loss": 0.3185,
+      "step": 99
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 7.097153227455379e-05,
+      "loss": 0.3368,
+      "step": 100
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.4159,
+      "step": 101
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 6.723698204383066e-05,
+      "loss": 0.1037,
+      "step": 102
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 6.538829429225069e-05,
+      "loss": 0.3056,
+      "step": 103
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 6.355295001208504e-05,
+      "loss": 0.3471,
+      "step": 104
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.3285,
+      "step": 105
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 5.992511668968592e-05,
+      "loss": 0.3353,
+      "step": 106
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 5.8134026246257225e-05,
+      "loss": 0.323,
+      "step": 107
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 5.6359075932665775e-05,
+      "loss": 0.3711,
+      "step": 108
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.3837,
+      "step": 109
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.286032631740023e-05,
+      "loss": 0.1286,
+      "step": 110
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 5.113787585030454e-05,
+      "loss": 0.2039,
+      "step": 111
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 4.943426266220156e-05,
+      "loss": 0.1764,
+      "step": 112
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 0.232,
+      "step": 113
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.6086167708899975e-05,
+      "loss": 0.2015,
+      "step": 114
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.1638,
+      "step": 115
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 4.282120397723879e-05,
+      "loss": 0.1782,
+      "step": 116
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.1994,
+      "step": 117
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 3.964440580464286e-05,
+      "loss": 0.0777,
+      "step": 118
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 3.8090605069016595e-05,
+      "loss": 0.2262,
+      "step": 119
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 3.6560671583635467e-05,
+      "loss": 0.2092,
+      "step": 120
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.1873,
+      "step": 121
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 3.357475620887186e-05,
+      "loss": 0.1743,
+      "step": 122
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 3.211992544670582e-05,
+      "loss": 0.0757,
+      "step": 123
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 3.069126374543643e-05,
+      "loss": 0.1746,
+      "step": 124
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.1928,
+      "step": 125
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 2.7914640329708118e-05,
+      "loss": 0.1704,
+      "step": 126
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.6567749056431467e-05,
+      "loss": 0.1621,
+      "step": 127
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 2.5249167313740308e-05,
+      "loss": 0.1666,
+      "step": 128
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.1965,
+      "step": 129
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.26989546637263e-05,
+      "loss": 0.2116,
+      "step": 130
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.146830691192553e-05,
+      "loss": 0.1428,
+      "step": 131
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.02679346227293e-05,
+      "loss": 0.1969,
+      "step": 132
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.1912,
+      "step": 133
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.795985564744864e-05,
+      "loss": 0.1869,
+      "step": 134
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.1589,
+      "step": 135
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 1.5778276628371357e-05,
+      "loss": 0.1504,
+      "step": 136
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.1817,
+      "step": 137
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.3726561402220817e-05,
+      "loss": 0.1935,
+      "step": 138
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.2750399292720283e-05,
+      "loss": 0.1756,
+      "step": 139
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 1.1807873565164506e-05,
+      "loss": 0.1584,
+      "step": 140
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.1821,
+      "step": 141
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.0025171594777871e-05,
+      "loss": 0.2201,
+      "step": 142
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.185682617491863e-06,
+      "loss": 0.1844,
+      "step": 143
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 8.381204288286415e-06,
+      "loss": 0.1498,
+      "step": 144
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.189,
+      "step": 145
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 6.878506524119643e-06,
+      "loss": 0.1518,
+      "step": 146
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 6.180866407751595e-06,
+      "loss": 0.1542,
+      "step": 147
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.519395353312196e-06,
+      "loss": 0.168,
+      "step": 148
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.1886,
+      "step": 149
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.305966426779118e-06,
+      "loss": 0.1844,
+      "step": 150
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 3.7544763546352834e-06,
+      "loss": 0.1995,
+      "step": 151
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 3.240090763974024e-06,
+      "loss": 0.1679,
+      "step": 152
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 0.176,
+      "step": 153
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2.3234118679127615e-06,
+      "loss": 0.1808,
+      "step": 154
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.1669,
+      "step": 155
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.5573431910108405e-06,
+      "loss": 0.1934,
+      "step": 156
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.1536,
+      "step": 157
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 9.43065955642275e-07,
+      "loss": 0.1367,
+      "step": 158
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 6.931543045073708e-07,
+      "loss": 0.1517,
+      "step": 159
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 4.815273327803182e-07,
+      "loss": 0.1471,
+      "step": 160
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.1823,
+      "step": 161
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 1.7343898152841765e-07,
+      "loss": 0.1613,
+      "step": 162
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 7.709637592770991e-08,
+      "loss": 0.1318,
+      "step": 163
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.9275951793518154e-08,
+      "loss": 0.1763,
+      "step": 164
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0,
+      "loss": 0.0875,
+      "step": 165
+    },
+    {
+      "epoch": 3.0,
+      "step": 165,
+      "total_flos": 303952207151104.0,
+      "train_loss": 0.36774244087212016,
+      "train_runtime": 8148.5593,
+      "train_samples_per_second": 2.577,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 165,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50000,
+  "total_flos": 303952207151104.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}