Update model files

0927_finetune_loc_family_go_data_441k_batch=18/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /mnt/petrelfs/lvying/LLM/OPUS-BioLLM/model/Meta-Llama-3-8B/
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.11.1

0927_finetune_loc_family_go_data_441k_batch=18/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/mnt/petrelfs/lvying/LLM/OPUS-BioLLM/model/Meta-Llama-3-8B/",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

0927_finetune_loc_family_go_data_441k_batch=18/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a5fbfd5ab3670e83ffbb89ded0e43974f20367dd0e5c810be4ac985582772a
+size 335604696

0927_finetune_loc_family_go_data_441k_batch=18/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/mnt/petrelfs/lvying/LLM/OPUS-BioLLM/model/Meta-Llama-3-8B/",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "device": "cuda",
+  "eos_token_id": 128001,
+  "freeze_switch_adapter": false,
+  "has_protein_encoder": true,
+  "has_switch_projector": true,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "opus_llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "switch_projector_lr": 1e-05,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 256,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "tune_switch_projector": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

0927_finetune_loc_family_go_data_441k_batch=18/non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de8d48030c0d91cf593e68209a21c56115b4aa60bc586b1aa129efdde137b0e
+size 2483161264

0927_finetune_loc_family_go_data_441k_batch=18/trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017513134851138354,
+      "grad_norm": 0.15476079861490413,
+      "learning_rate": 0.00039987444454530436,
+      "loss": 0.6968,
+      "step": 50
+    },
+    {
+      "epoch": 0.03502626970227671,
+      "grad_norm": 0.14021320810370635,
+      "learning_rate": 0.00039917603199327755,
+      "loss": 0.4743,
+      "step": 100
+    },
+    {
+      "epoch": 0.05253940455341506,
+      "grad_norm": 0.15162392445851744,
+      "learning_rate": 0.00039786717350566675,
+      "loss": 0.4469,
+      "step": 150
+    },
+    {
+      "epoch": 0.07005253940455342,
+      "grad_norm": 0.14055655319895916,
+      "learning_rate": 0.00039595188054577927,
+      "loss": 0.4285,
+      "step": 200
+    },
+    {
+      "epoch": 0.08756567425569177,
+      "grad_norm": 0.1444825139132905,
+      "learning_rate": 0.0003934360232114934,
+      "loss": 0.4253,
+      "step": 250
+    },
+    {
+      "epoch": 0.10507880910683012,
+      "grad_norm": 0.13189317919899662,
+      "learning_rate": 0.00039032731224425144,
+      "loss": 0.4177,
+      "step": 300
+    },
+    {
+      "epoch": 0.12259194395796848,
+      "grad_norm": 0.14238170187913182,
+      "learning_rate": 0.00038663527539674477,
+      "loss": 0.4051,
+      "step": 350
+    },
+    {
+      "epoch": 0.14010507880910683,
+      "grad_norm": 0.13315314129637237,
+      "learning_rate": 0.0003823712282317197,
+      "loss": 0.3988,
+      "step": 400
+    },
+    {
+      "epoch": 0.15761821366024517,
+      "grad_norm": 0.13959489286875335,
+      "learning_rate": 0.0003775482394414027,
+      "loss": 0.405,
+      "step": 450
+    },
+    {
+      "epoch": 0.17513134851138354,
+      "grad_norm": 0.1411212201963289,
+      "learning_rate": 0.0003721810907938358,
+      "loss": 0.3904,
+      "step": 500
+    },
+    {
+      "epoch": 0.19264448336252188,
+      "grad_norm": 0.12443006914890657,
+      "learning_rate": 0.00036628623182887956,
+      "loss": 0.3835,
+      "step": 550
+    },
+    {
+      "epoch": 0.21015761821366025,
+      "grad_norm": 0.1340954686999827,
+      "learning_rate": 0.0003598817294427363,
+      "loss": 0.3906,
+      "step": 600
+    },
+    {
+      "epoch": 0.2276707530647986,
+      "grad_norm": 0.13154614425093736,
+      "learning_rate": 0.0003529872125155074,
+      "loss": 0.3707,
+      "step": 650
+    },
+    {
+      "epoch": 0.24518388791593695,
+      "grad_norm": 0.12929654588874767,
+      "learning_rate": 0.00034562381175149456,
+      "loss": 0.3742,
+      "step": 700
+    },
+    {
+      "epoch": 0.2626970227670753,
+      "grad_norm": 0.11480028738526576,
+      "learning_rate": 0.00033781409491662564,
+      "loss": 0.3645,
+      "step": 750
+    },
+    {
+      "epoch": 0.28021015761821366,
+      "grad_norm": 0.12383159716041994,
+      "learning_rate": 0.00032958199767149296,
+      "loss": 0.3669,
+      "step": 800
+    },
+    {
+      "epoch": 0.29772329246935203,
+      "grad_norm": 0.1356600873929315,
+      "learning_rate": 0.0003209527502119907,
+      "loss": 0.3577,
+      "step": 850
+    },
+    {
+      "epoch": 0.31523642732049034,
+      "grad_norm": 0.13785973805201118,
+      "learning_rate": 0.00031195279994238777,
+      "loss": 0.3597,
+      "step": 900
+    },
+    {
+      "epoch": 0.3327495621716287,
+      "grad_norm": 0.12046061954753205,
+      "learning_rate": 0.00030260973041783165,
+      "loss": 0.3541,
+      "step": 950
+    },
+    {
+      "epoch": 0.3502626970227671,
+      "grad_norm": 0.058484526055223585,
+      "learning_rate": 0.0002929521768047128,
+      "loss": 0.3531,
+      "step": 1000
+    },
+    {
+      "epoch": 0.36777583187390545,
+      "grad_norm": 0.12192383903770622,
+      "learning_rate": 0.0002830097381179922,
+      "loss": 0.3447,
+      "step": 1050
+    },
+    {
+      "epoch": 0.38528896672504376,
+      "grad_norm": 0.11909889705302568,
+      "learning_rate": 0.0002728128865044706,
+      "loss": 0.3384,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4028021015761821,
+      "grad_norm": 0.11053069966602695,
+      "learning_rate": 0.00026239287385003483,
+      "loss": 0.3398,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4203152364273205,
+      "grad_norm": 0.12273273342540729,
+      "learning_rate": 0.00025178163599711513,
+      "loss": 0.3379,
+      "step": 1200
+    },
+    {
+      "epoch": 0.43782837127845886,
+      "grad_norm": 0.11940611078372608,
+      "learning_rate": 0.00024101169486591436,
+      "loss": 0.3384,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4553415061295972,
+      "grad_norm": 0.10859681689112734,
+      "learning_rate": 0.0002301160587793932,
+      "loss": 0.3239,
+      "step": 1300
+    },
+    {
+      "epoch": 0.47285464098073554,
+      "grad_norm": 0.12491438548798937,
+      "learning_rate": 0.0002191281212974998,
+      "loss": 0.3305,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4903677758318739,
+      "grad_norm": 0.10782768494412732,
+      "learning_rate": 0.00020808155887070426,
+      "loss": 0.3173,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5078809106830122,
+      "grad_norm": 0.10411783767515172,
+      "learning_rate": 0.00019701022762651428,
+      "loss": 0.3151,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5253940455341506,
+      "grad_norm": 0.11406917077104474,
+      "learning_rate": 0.0001859480596053057,
+      "loss": 0.3232,
+      "step": 1500
+    },
+    {
+      "epoch": 0.542907180385289,
+      "grad_norm": 0.11517888587338994,
+      "learning_rate": 0.00017492895876349208,
+      "loss": 0.316,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5604203152364273,
+      "grad_norm": 0.11070110338164338,
+      "learning_rate": 0.0001639866970627664,
+      "loss": 0.3064,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5779334500875657,
+      "grad_norm": 0.12063049698593797,
+      "learning_rate": 0.00015315481096388894,
+      "loss": 0.3112,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5954465849387041,
+      "grad_norm": 0.09995809461678606,
+      "learning_rate": 0.0001424664986422504,
+      "loss": 0.3022,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6129597197898424,
+      "grad_norm": 0.11455749182215415,
+      "learning_rate": 0.00013195451824023238,
+      "loss": 0.305,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6304728546409807,
+      "grad_norm": 0.10834030478250198,
+      "learning_rate": 0.00012165108746820441,
+      "loss": 0.2962,
+      "step": 1800
+    },
+    {
+      "epoch": 0.647985989492119,
+      "grad_norm": 0.10621364556767228,
+      "learning_rate": 0.000111587784861869,
+      "loss": 0.2979,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6654991243432574,
+      "grad_norm": 0.1118799170677305,
+      "learning_rate": 0.00010179545299858395,
+      "loss": 0.2907,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6830122591943958,
+      "grad_norm": 0.11751351273949141,
+      "learning_rate": 9.230410396929222e-05,
+      "loss": 0.2898,
+      "step": 1950
+    },
+    {
+      "epoch": 0.7005253940455342,
+      "grad_norm": 0.056294030420761296,
+      "learning_rate": 8.314282739577281e-05,
+      "loss": 0.2876,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7180385288966725,
+      "grad_norm": 0.09894035530217217,
+      "learning_rate": 7.433970127512766e-05,
+      "loss": 0.2848,
+      "step": 2050
+    },
+    {
+      "epoch": 0.7355516637478109,
+      "grad_norm": 0.1015527528251243,
+      "learning_rate": 6.592170592475234e-05,
+      "loss": 0.2827,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7530647985989493,
+      "grad_norm": 0.09390025624782437,
+      "learning_rate": 5.791464129153792e-05,
+      "loss": 0.2831,
+      "step": 2150
+    },
+    {
+      "epoch": 0.7705779334500875,
+      "grad_norm": 0.10342940052589422,
+      "learning_rate": 5.034304787873865e-05,
+      "loss": 0.2823,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7880910683012259,
+      "grad_norm": 0.10593183722383863,
+      "learning_rate": 4.323013153285378e-05,
+      "loss": 0.2802,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8056042031523643,
+      "grad_norm": 0.09899829565623841,
+      "learning_rate": 3.6597692321040044e-05,
+      "loss": 0.2819,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8231173380035026,
+      "grad_norm": 0.124476369769809,
+      "learning_rate": 3.0466057717036855e-05,
+      "loss": 0.2841,
+      "step": 2350
+    },
+    {
+      "epoch": 0.840630472854641,
+      "grad_norm": 0.11080210539696708,
+      "learning_rate": 2.4854020300378223e-05,
+      "loss": 0.276,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8581436077057794,
+      "grad_norm": 0.09090640706535441,
+      "learning_rate": 1.9874920978296284e-05,
+      "loss": 0.2802,
+      "step": 2450
+    },
+    {
+      "epoch": 0.8756567425569177,
+      "grad_norm": 0.10178854989054627,
+      "learning_rate": 1.5340844391036024e-05,
+      "loss": 0.2726,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8931698774080561,
+      "grad_norm": 0.0992139699628013,
+      "learning_rate": 1.1372721597923242e-05,
+      "loss": 0.2746,
+      "step": 2550
+    },
+    {
+      "epoch": 0.9106830122591943,
+      "grad_norm": 0.09904893931132518,
+      "learning_rate": 7.982714325480656e-06,
+      "loss": 0.2704,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9281961471103327,
+      "grad_norm": 0.1058715952356844,
+      "learning_rate": 5.1812124591796405e-06,
+      "loss": 0.272,
+      "step": 2650
+    },
+    {
+      "epoch": 0.9457092819614711,
+      "grad_norm": 0.12013886663190389,
+      "learning_rate": 2.976802199933548e-06,
+      "loss": 0.2752,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9632224168126094,
+      "grad_norm": 0.0984904939535453,
+      "learning_rate": 1.376239748624797e-06,
+      "loss": 0.2727,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9807355516637478,
+      "grad_norm": 0.11310530850109253,
+      "learning_rate": 3.8443059931949634e-07,
+      "loss": 0.2722,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9982486865148862,
+      "grad_norm": 0.11771859581570313,
+      "learning_rate": 4.414504632488381e-09,
+      "loss": 0.2725,
+      "step": 2850
+    },
+    {
+      "epoch": 1.0,
+      "step": 2855,
+      "total_flos": 133473370849280.0,
+      "train_loss": 0.33664647848092527,
+      "train_runtime": 41024.8638,
+      "train_samples_per_second": 10.02,
+      "train_steps_per_second": 0.07
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2855,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 133473370849280.0,
+  "train_batch_size": 18,
+  "trial_name": null,
+  "trial_params": null
+}