Upload 7 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: lmsys/vicuna-7b-v1.5
+---
+
+# 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 0.10.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "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": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "o_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 sha256:1d7ad74719e233d0a1a35a51b4598cce0010f44bdbfbd584a5fe97199b64f3db
+size 639692320

config.json

@@ -0,0 +1,63 @@
+{
+  "_name_or_path": "lmsys/vicuna-7b-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_multiview_ensembler": false,
+  "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_patch_merge_type": "flat",
+  "mm_projector_lr": null,
+  "mm_projector_type": "mlp2x_gelu",
+  "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,
+  "mm_vision_tower": null,
+  "model_type": "llava_llama",
+  "multiview_ensembler_lr": 2e-05,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "mm_projector",
+      "multiview_ensembler"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "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": "float32",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_multiview_ensembler": true,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

multiview_ensembler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd7bc35ff36ca38a73ca1fe6b0a467801e3bca468ff771d1a6c6f53fdc13b1a
+size 268638294

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87bd37822580c42665a9859dc629125e90e187e48d3a6c4adb290966c20fb1e6
+size 268638294

trainer_state.json

@@ -0,0 +1,654 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9964071856287425,
+  "eval_steps": 500,
+  "global_step": 104,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0,
+      "loss": 3.02,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.0,
+      "loss": 2.8946,
+      "step": 2
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5e-05,
+      "loss": 2.9989,
+      "step": 3
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0001,
+      "loss": 3.0185,
+      "step": 4
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9948,
+      "step": 5
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.0002,
+      "loss": 2.1701,
+      "step": 6
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00019995065603657316,
+      "loss": 2.1174,
+      "step": 7
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00019980267284282717,
+      "loss": 2.067,
+      "step": 8
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00019955619646030802,
+      "loss": 1.9723,
+      "step": 9
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0001992114701314478,
+      "loss": 1.9417,
+      "step": 10
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 1.9781,
+      "step": 11
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0001982287250728689,
+      "loss": 1.8071,
+      "step": 12
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00019759167619387476,
+      "loss": 1.8272,
+      "step": 13
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 1.6803,
+      "step": 14
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0001960293685676943,
+      "loss": 1.726,
+      "step": 15
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.7271,
+      "step": 16
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00019408807689542257,
+      "loss": 1.7266,
+      "step": 17
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.00019297764858882514,
+      "loss": 1.7272,
+      "step": 18
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.00019177546256839812,
+      "loss": 1.6868,
+      "step": 19
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019048270524660196,
+      "loss": 1.5478,
+      "step": 20
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 1.5898,
+      "step": 21
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00018763066800438636,
+      "loss": 1.6766,
+      "step": 22
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0001860742027003944,
+      "loss": 1.5721,
+      "step": 23
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.00018443279255020152,
+      "loss": 1.5771,
+      "step": 24
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.00018270805742745617,
+      "loss": 1.5692,
+      "step": 25
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.5286,
+      "step": 26
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00017901550123756906,
+      "loss": 1.4898,
+      "step": 27
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00017705132427757895,
+      "loss": 1.5101,
+      "step": 28
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00017501110696304596,
+      "loss": 1.5265,
+      "step": 29
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00017289686274214118,
+      "loss": 1.4373,
+      "step": 30
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.3691,
+      "step": 31
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00016845471059286887,
+      "loss": 1.5147,
+      "step": 32
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00016613118653236518,
+      "loss": 1.4216,
+      "step": 33
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.3968,
+      "step": 34
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00016129070536529766,
+      "loss": 1.4057,
+      "step": 35
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 1.4042,
+      "step": 36
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00015620833778521307,
+      "loss": 1.3287,
+      "step": 37
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00015358267949789966,
+      "loss": 1.2654,
+      "step": 38
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00015090414157503714,
+      "loss": 1.3084,
+      "step": 39
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00014817536741017152,
+      "loss": 1.2634,
+      "step": 40
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 1.2646,
+      "step": 41
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00014257792915650728,
+      "loss": 1.29,
+      "step": 42
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00013971478906347806,
+      "loss": 1.3563,
+      "step": 43
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00013681245526846783,
+      "loss": 1.272,
+      "step": 44
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00013387379202452917,
+      "loss": 1.299,
+      "step": 45
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.3304,
+      "step": 46
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00012789911060392294,
+      "loss": 1.2768,
+      "step": 47
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0001248689887164855,
+      "loss": 1.301,
+      "step": 48
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00012181432413965428,
+      "loss": 1.1637,
+      "step": 49
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00011873813145857249,
+      "loss": 1.2437,
+      "step": 50
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 1.2699,
+      "step": 51
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00011253332335643043,
+      "loss": 1.2035,
+      "step": 52
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00010941083133185146,
+      "loss": 1.2354,
+      "step": 53
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 1.3551,
+      "step": 54
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00010314107590781284,
+      "loss": 1.1651,
+      "step": 55
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0001,
+      "loss": 1.1803,
+      "step": 56
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.685892409218717e-05,
+      "loss": 1.1379,
+      "step": 57
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.1446,
+      "step": 58
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.058916866814858e-05,
+      "loss": 1.2089,
+      "step": 59
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 8.746667664356956e-05,
+      "loss": 1.1623,
+      "step": 60
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.0943,
+      "step": 61
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.126186854142752e-05,
+      "loss": 1.2074,
+      "step": 62
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 7.818567586034577e-05,
+      "loss": 1.1739,
+      "step": 63
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 7.513101128351454e-05,
+      "loss": 1.2538,
+      "step": 64
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 7.210088939607708e-05,
+      "loss": 1.288,
+      "step": 65
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.1144,
+      "step": 66
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 6.612620797547087e-05,
+      "loss": 1.2695,
+      "step": 67
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 6.318754473153221e-05,
+      "loss": 1.205,
+      "step": 68
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 6.0285210936521955e-05,
+      "loss": 1.1551,
+      "step": 69
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.1511,
+      "step": 70
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.1414,
+      "step": 71
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 5.182463258982846e-05,
+      "loss": 1.1637,
+      "step": 72
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.909585842496287e-05,
+      "loss": 1.1339,
+      "step": 73
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.6417320502100316e-05,
+      "loss": 1.1118,
+      "step": 74
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.379166221478697e-05,
+      "loss": 1.1822,
+      "step": 75
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.2311,
+      "step": 76
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 3.8709294634702376e-05,
+      "loss": 1.1172,
+      "step": 77
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.6257601025131026e-05,
+      "loss": 1.0924,
+      "step": 78
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 3.386881346763483e-05,
+      "loss": 1.1534,
+      "step": 79
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.154528940713113e-05,
+      "loss": 1.2601,
+      "step": 80
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.0743,
+      "step": 81
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.1419,
+      "step": 82
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.4988893036954043e-05,
+      "loss": 1.0558,
+      "step": 83
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2.2948675722421086e-05,
+      "loss": 1.1382,
+      "step": 84
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.098449876243096e-05,
+      "loss": 1.1775,
+      "step": 85
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.1861,
+      "step": 86
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 1.7291942572543807e-05,
+      "loss": 1.1331,
+      "step": 87
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.5567207449798515e-05,
+      "loss": 1.142,
+      "step": 88
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.3925797299605647e-05,
+      "loss": 1.1482,
+      "step": 89
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 1.2369331995613665e-05,
+      "loss": 1.0885,
+      "step": 90
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.2005,
+      "step": 91
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 9.517294753398064e-06,
+      "loss": 1.0784,
+      "step": 92
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 8.224537431601886e-06,
+      "loss": 1.133,
+      "step": 93
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.1096,
+      "step": 94
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.911923104577455e-06,
+      "loss": 1.108,
+      "step": 95
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.9645,
+      "step": 96
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.970631432305694e-06,
+      "loss": 1.1942,
+      "step": 97
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 1.181,
+      "step": 98
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.4083238061252567e-06,
+      "loss": 1.0978,
+      "step": 99
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.771274927131139e-06,
+      "loss": 0.9967,
+      "step": 100
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.2266,
+      "step": 101
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 1.216,
+      "step": 102
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.438035396920004e-07,
+      "loss": 1.2119,
+      "step": 103
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.973271571728441e-07,
+      "loss": 1.1436,
+      "step": 104
+    },
+    {
+      "epoch": 1.0,
+      "step": 104,
+      "total_flos": 1.0478460476588032e+16,
+      "train_loss": 1.4066595842058842,
+      "train_runtime": 3219.9547,
+      "train_samples_per_second": 0.259,
+      "train_steps_per_second": 0.032
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 104,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 104,
+  "total_flos": 1.0478460476588032e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}