Upload folder using huggingface_hub

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/README.md

@@ -0,0 +1,202 @@
+---
+base_model: lmsys/vicuna-7b-v1.5
+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 0.13.2

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": "olora",
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "fc2",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "fc1",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462e8fd6f19a7fa277b05d36159cc93721ba03871d55f4629409d9d54afef5ac
+size 1279324400

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_image_tower": "LanguageBind/LanguageBind_Image",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_video_tower": "LanguageBind/LanguageBind_Video_merge",
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "model_type": "llava",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 3072,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1f3ae420aebe35c84685ba202476196eecc571bc9d2b6e2087ae0355c211183
+size 41961648

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/runs/Oct31_20-49-46_evc29/events.out.tfevents.1730423772.evc29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:188f0fe0c4e096324a1660aebede1e032d23f39f85aafc6cc76dbe85645b1f52
+size 34925

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/special_tokens_map.json

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

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

[lora]video_llava_AG_annotations_v5_3_p02_e01/videollava-7b-lora/trainer_state.json

@@ -0,0 +1,1153 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.8588,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.8668,
+      "step": 2
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0001,
+      "loss": 0.4201,
+      "step": 3
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00013333333333333334,
+      "loss": 0.554,
+      "step": 4
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 1.3247,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002,
+      "loss": 6.0931,
+      "step": 6
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019998510240408496,
+      "loss": 1.1824,
+      "step": 7
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00019994041405510705,
+      "loss": 0.5507,
+      "step": 8
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001998659482680456,
+      "loss": 0.5103,
+      "step": 9
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0001997617272301248,
+      "loss": 0.4502,
+      "step": 10
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00019962778199420265,
+      "loss": 0.4454,
+      "step": 11
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0001994641524695193,
+      "loss": 0.381,
+      "step": 12
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 0.3121,
+      "step": 13
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019904804439875633,
+      "loss": 0.4303,
+      "step": 14
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019879568983287467,
+      "loss": 0.7679,
+      "step": 15
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0001985138989016874,
+      "loss": 0.342,
+      "step": 16
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019820275556534304,
+      "loss": 0.4291,
+      "step": 17
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019786235252959553,
+      "loss": 0.3668,
+      "step": 18
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00019749279121818235,
+      "loss": 0.3204,
+      "step": 19
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001970941817426052,
+      "loss": 0.3247,
+      "step": 20
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019666664286932198,
+      "loss": 0.2632,
+      "step": 21
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019621030198436006,
+      "loss": 0.2198,
+      "step": 22
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0001957252950553616,
+      "loss": 0.2221,
+      "step": 23
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00019521176659107142,
+      "loss": 0.2925,
+      "step": 24
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001946698695982806,
+      "loss": 0.2204,
+      "step": 25
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00019409976553623766,
+      "loss": 0.2302,
+      "step": 26
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001935016242685415,
+      "loss": 0.2067,
+      "step": 27
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019287562401253022,
+      "loss": 0.18,
+      "step": 28
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019222195128618106,
+      "loss": 0.1601,
+      "step": 29
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019154080085253666,
+      "loss": 0.1822,
+      "step": 30
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0001908323756616754,
+      "loss": 0.1766,
+      "step": 31
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0001900968867902419,
+      "loss": 0.1895,
+      "step": 32
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00018933455337855632,
+      "loss": 0.1712,
+      "step": 33
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.000188545602565321,
+      "loss": 0.1604,
+      "step": 34
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0001877302694199442,
+      "loss": 0.1379,
+      "step": 35
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00018688879687250067,
+      "loss": 0.1803,
+      "step": 36
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001860214356413501,
+      "loss": 0.1533,
+      "step": 37
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00018512844415843514,
+      "loss": 0.1647,
+      "step": 38
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018421008849228118,
+      "loss": 0.1661,
+      "step": 39
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018326664226872065,
+      "loss": 0.1422,
+      "step": 40
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018229838658936564,
+      "loss": 0.1735,
+      "step": 41
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00018130560994785325,
+      "loss": 0.1428,
+      "step": 42
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018028860814388827,
+      "loss": 0.145,
+      "step": 43
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00017924768419510904,
+      "loss": 0.1489,
+      "step": 44
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.000178183148246803,
+      "loss": 0.1241,
+      "step": 45
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00017709531747949796,
+      "loss": 0.1148,
+      "step": 46
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001759845160144579,
+      "loss": 0.1427,
+      "step": 47
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017485107481711012,
+      "loss": 0.151,
+      "step": 48
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017369533159843369,
+      "loss": 0.1428,
+      "step": 49
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017251763071433765,
+      "loss": 0.1457,
+      "step": 50
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017131832306305965,
+      "loss": 0.1532,
+      "step": 51
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00017009776598061495,
+      "loss": 0.1244,
+      "step": 52
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0001688563231343277,
+      "loss": 0.141,
+      "step": 53
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016759436441447545,
+      "loss": 0.1126,
+      "step": 54
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00016631226582407952,
+      "loss": 0.1256,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00016501040936687443,
+      "loss": 0.1314,
+      "step": 56
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00016368918293348892,
+      "loss": 0.1278,
+      "step": 57
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.1314,
+      "step": 58
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016099020044000727,
+      "loss": 0.1268,
+      "step": 59
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00015961324854692254,
+      "loss": 0.1214,
+      "step": 60
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00015821853477207708,
+      "loss": 0.1262,
+      "step": 61
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00015680647467311557,
+      "loss": 0.1321,
+      "step": 62
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0001553774889760533,
+      "loss": 0.1386,
+      "step": 63
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015393200344991995,
+      "loss": 0.125,
+      "step": 64
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001524704487799008,
+      "loss": 0.1346,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0001509932604390136,
+      "loss": 0.1284,
+      "step": 66
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014950087855835815,
+      "loss": 0.124,
+      "step": 67
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00014799374779597867,
+      "loss": 0.1288,
+      "step": 68
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014647231720437686,
+      "loss": 0.1317,
+      "step": 69
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00014493704009671613,
+      "loss": 0.1235,
+      "step": 70
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00014338837391175582,
+      "loss": 0.1327,
+      "step": 71
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001418267800775565,
+      "loss": 0.1241,
+      "step": 72
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00014025272387399674,
+      "loss": 0.114,
+      "step": 73
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0001386666742941419,
+      "loss": 0.1277,
+      "step": 74
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013706910390450677,
+      "loss": 0.1313,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00013546048870425356,
+      "loss": 0.1123,
+      "step": 76
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013384130798336705,
+      "loss": 0.1117,
+      "step": 77
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013221204417984908,
+      "loss": 0.1139,
+      "step": 78
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0001305731827359753,
+      "loss": 0.1108,
+      "step": 79
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012892521195365678,
+      "loss": 0.1321,
+      "step": 80
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00012726862284894938,
+      "loss": 0.1105,
+      "step": 81
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001256039090057547,
+      "loss": 0.1224,
+      "step": 82
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001239315664287558,
+      "loss": 0.1289,
+      "step": 83
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.1021,
+      "step": 84
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012056599030859366,
+      "loss": 0.1076,
+      "step": 85
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011887375954529168,
+      "loss": 0.0938,
+      "step": 86
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00011717590530912763,
+      "loss": 0.112,
+      "step": 87
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011547293347902812,
+      "loss": 0.1151,
+      "step": 88
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00011376535145871684,
+      "loss": 0.1057,
+      "step": 89
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0001120536680255323,
+      "loss": 0.1132,
+      "step": 90
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011033839317883701,
+      "loss": 0.1327,
+      "step": 91
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010862003798806196,
+      "loss": 0.1259,
+      "step": 92
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00010689911444043248,
+      "loss": 0.1163,
+      "step": 93
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00010517613528842097,
+      "loss": 0.1099,
+      "step": 94
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010345161389697082,
+      "loss": 0.1187,
+      "step": 95
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010172606409053886,
+      "loss": 0.1035,
+      "step": 96
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001,
+      "loss": 0.1052,
+      "step": 97
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.827393590946116e-05,
+      "loss": 0.1144,
+      "step": 98
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.654838610302923e-05,
+      "loss": 0.1058,
+      "step": 99
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.482386471157904e-05,
+      "loss": 0.104,
+      "step": 100
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.31008855595675e-05,
+      "loss": 0.1139,
+      "step": 101
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 9.137996201193805e-05,
+      "loss": 0.0994,
+      "step": 102
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.9661606821163e-05,
+      "loss": 0.1113,
+      "step": 103
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.0933,
+      "step": 104
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.62346485412832e-05,
+      "loss": 0.1095,
+      "step": 105
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 8.452706652097186e-05,
+      "loss": 0.1193,
+      "step": 106
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.282409469087239e-05,
+      "loss": 0.1092,
+      "step": 107
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.112624045470835e-05,
+      "loss": 0.1069,
+      "step": 108
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.943400969140635e-05,
+      "loss": 0.1244,
+      "step": 109
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.774790660436858e-05,
+      "loss": 0.0923,
+      "step": 110
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.606843357124426e-05,
+      "loss": 0.1006,
+      "step": 111
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.43960909942453e-05,
+      "loss": 0.1144,
+      "step": 112
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.273137715105063e-05,
+      "loss": 0.0983,
+      "step": 113
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.107478804634325e-05,
+      "loss": 0.1156,
+      "step": 114
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 6.942681726402473e-05,
+      "loss": 0.118,
+      "step": 115
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.778795582015097e-05,
+      "loss": 0.0982,
+      "step": 116
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.615869201663296e-05,
+      "loss": 0.1091,
+      "step": 117
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.453951129574644e-05,
+      "loss": 0.1145,
+      "step": 118
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.293089609549325e-05,
+      "loss": 0.1293,
+      "step": 119
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.133332570585812e-05,
+      "loss": 0.1053,
+      "step": 120
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.9747276126003257e-05,
+      "loss": 0.1147,
+      "step": 121
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.817321992244351e-05,
+      "loss": 0.1047,
+      "step": 122
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.6611626088244194e-05,
+      "loss": 0.1078,
+      "step": 123
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.506295990328385e-05,
+      "loss": 0.102,
+      "step": 124
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 5.3527682795623146e-05,
+      "loss": 0.1208,
+      "step": 125
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.200625220402139e-05,
+      "loss": 0.1067,
+      "step": 126
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.0499121441641864e-05,
+      "loss": 0.0908,
+      "step": 127
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.900673956098644e-05,
+      "loss": 0.0943,
+      "step": 128
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.75295512200992e-05,
+      "loss": 0.1137,
+      "step": 129
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.606799655008009e-05,
+      "loss": 0.1121,
+      "step": 130
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.462251102394669e-05,
+      "loss": 0.1006,
+      "step": 131
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.099,
+      "step": 132
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.1781465227922957e-05,
+      "loss": 0.0894,
+      "step": 133
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.038675145307747e-05,
+      "loss": 0.102,
+      "step": 134
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.900979955999271e-05,
+      "loss": 0.1211,
+      "step": 135
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.7651019814126654e-05,
+      "loss": 0.1211,
+      "step": 136
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.6310817066511105e-05,
+      "loss": 0.1168,
+      "step": 137
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 3.498959063312558e-05,
+      "loss": 0.118,
+      "step": 138
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.36877341759205e-05,
+      "loss": 0.1018,
+      "step": 139
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.2405635585524565e-05,
+      "loss": 0.0907,
+      "step": 140
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.114367686567228e-05,
+      "loss": 0.1216,
+      "step": 141
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.9902234019385057e-05,
+      "loss": 0.1035,
+      "step": 142
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 2.8681676936940393e-05,
+      "loss": 0.1081,
+      "step": 143
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.7482369285662378e-05,
+      "loss": 0.1028,
+      "step": 144
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 2.6304668401566335e-05,
+      "loss": 0.0987,
+      "step": 145
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.514892518288988e-05,
+      "loss": 0.1022,
+      "step": 146
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.401548398554213e-05,
+      "loss": 0.1031,
+      "step": 147
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.290468252050204e-05,
+      "loss": 0.1217,
+      "step": 148
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.181685175319702e-05,
+      "loss": 0.085,
+      "step": 149
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.0752315804890977e-05,
+      "loss": 0.1038,
+      "step": 150
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.971139185611176e-05,
+      "loss": 0.1002,
+      "step": 151
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.8694390052146737e-05,
+      "loss": 0.1011,
+      "step": 152
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 1.7701613410634365e-05,
+      "loss": 0.1064,
+      "step": 153
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.6733357731279377e-05,
+      "loss": 0.0882,
+      "step": 154
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.5789911507718826e-05,
+      "loss": 0.0919,
+      "step": 155
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.4871555841564887e-05,
+      "loss": 0.0962,
+      "step": 156
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.3978564358649927e-05,
+      "loss": 0.1143,
+      "step": 157
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.311120312749935e-05,
+      "loss": 0.1157,
+      "step": 158
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2269730580055805e-05,
+      "loss": 0.0837,
+      "step": 159
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.0962,
+      "step": 160
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.0665446621443708e-05,
+      "loss": 0.1027,
+      "step": 161
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.903113209758096e-06,
+      "loss": 0.0992,
+      "step": 162
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 9.1676243383246e-06,
+      "loss": 0.0911,
+      "step": 163
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.45919914746337e-06,
+      "loss": 0.0762,
+      "step": 164
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.778048713818975e-06,
+      "loss": 0.0984,
+      "step": 165
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.124375987469767e-06,
+      "loss": 0.1009,
+      "step": 166
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 6.498375731458528e-06,
+      "loss": 0.0996,
+      "step": 167
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.900234463762366e-06,
+      "loss": 0.1051,
+      "step": 168
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.3301304017194135e-06,
+      "loss": 0.0947,
+      "step": 169
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.788233408928589e-06,
+      "loss": 0.0923,
+      "step": 170
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.27470494463843e-06,
+      "loss": 0.0924,
+      "step": 171
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.789698015639953e-06,
+      "loss": 0.0985,
+      "step": 172
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.3333571306780497e-06,
+      "loss": 0.1121,
+      "step": 173
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.905818257394799e-06,
+      "loss": 0.0973,
+      "step": 174
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 2.5072087818176382e-06,
+      "loss": 0.1112,
+      "step": 175
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.137647470404469e-06,
+      "loss": 0.1,
+      "step": 176
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 1.797244434656975e-06,
+      "loss": 0.1001,
+      "step": 177
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.48610109831262e-06,
+      "loss": 0.1005,
+      "step": 178
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 1.2043101671253554e-06,
+      "loss": 0.0925,
+      "step": 179
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 9.519556012436815e-07,
+      "loss": 0.0943,
+      "step": 180
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.291125901946027e-07,
+      "loss": 0.0937,
+      "step": 181
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 5.358475304807375e-07,
+      "loss": 0.1082,
+      "step": 182
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.7221800579735346e-07,
+      "loss": 0.0971,
+      "step": 183
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 2.382727698752474e-07,
+      "loss": 0.1189,
+      "step": 184
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.340517319543877e-07,
+      "loss": 0.1026,
+      "step": 185
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.958594489295921e-08,
+      "loss": 0.1053,
+      "step": 186
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 1.4897595915053242e-08,
+      "loss": 0.095,
+      "step": 187
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 0.0843,
+      "step": 188
+    },
+    {
+      "epoch": 1.0,
+      "step": 188,
+      "total_flos": 2.199699904832471e+17,
+      "train_loss": 0.1986531609312651,
+      "train_runtime": 11599.3664,
+      "train_samples_per_second": 0.259,
+      "train_steps_per_second": 0.016
+    }
+  ],
+  "max_steps": 188,
+  "num_train_epochs": 1,
+  "total_flos": 2.199699904832471e+17,
+  "trial_name": null,
+  "trial_params": null
+}