commit 70234cd1db37eb0961e2a3d08228ce79c4e5693c Author: ModelHub XC Date: Mon Aug 24 01:37:17 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Henry236/east8b-eg-lora-chunk-llama Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/adapter_config.json b/adapter_config.json new file mode 100644 index 0000000..25ed829 --- /dev/null +++ b/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "o_proj", + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/adapter_model.safetensors b/adapter_model.safetensors new file mode 100644 index 0000000..616cf76 --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e750594165491d27182ef42fe92c6feb72b82c04069cca03dd2d8f04a2606e +size 671149168 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..a3b591c --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,7 @@ +{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|begin_of_text|>' + '<|start_header_id|>system<|end_header_id|> + +' + system_message + '<|eot_id|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|> + +' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|> + +' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %} \ No newline at end of file diff --git a/checkpoint-100/README.md b/checkpoint-100/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-100/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-100/adapter_config.json b/checkpoint-100/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-100/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-100/adapter_model.safetensors b/checkpoint-100/adapter_model.safetensors new file mode 100644 index 0000000..3c8b494 --- /dev/null +++ b/checkpoint-100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123b1534a1743c6cfba2e9a8142901a711d0438b182ad3e74b47b234dbcaebf0 +size 671149168 diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100644 index 0000000..25ae9c9 --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f0e34a3a0fe94c765086a33d66c020b1ee58ca3508cb85c0022a33e361d69f +size 1342562339 diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth new file mode 100644 index 0000000..12be500 --- /dev/null +++ b/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69cd0e551b2edc97dee6a11534d4c0ef4f3d7dac904bff9b22dc1ed9a1012d40 +size 14645 diff --git a/checkpoint-100/scheduler.pt b/checkpoint-100/scheduler.pt new file mode 100644 index 0000000..5b592f2 --- /dev/null +++ b/checkpoint-100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a965538a990c1bee6cafb2ee94e4c27c3d42d8dd819e2e80a5cad5750681c87 +size 1465 diff --git a/checkpoint-100/trainer_state.json b/checkpoint-100/trainer_state.json new file mode 100644 index 0000000..ebce01b --- /dev/null +++ b/checkpoint-100/trainer_state.json @@ -0,0 +1,69 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.1736111111111111, + "eval_steps": 500, + "global_step": 100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.005165161647309e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-100/training_args.bin b/checkpoint-100/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-1000/README.md b/checkpoint-1000/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-1000/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-1000/adapter_config.json b/checkpoint-1000/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-1000/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1000/adapter_model.safetensors b/checkpoint-1000/adapter_model.safetensors new file mode 100644 index 0000000..4273636 --- /dev/null +++ b/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ecc93e71d3befd64a899e4d2a96a45602154e6d4126bb4c4dd69cf340046e0 +size 671149168 diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000..7a36fe4 --- /dev/null +++ b/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9056d42facfaaa295b68f3776c3e00fb50c6c88ba6ecbdfc3a51f07f14e8240a +size 1342562339 diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000..ebd947d --- /dev/null +++ b/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1791c0a7260af6628debd3dc2e8cca9005a37f7e4dd60fa56d2547eaaab30b09 +size 14645 diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt new file mode 100644 index 0000000..54c4178 --- /dev/null +++ b/checkpoint-1000/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3faa60702eeec70c307ffab2e710a51a22e86b2f89bbb3effe498e101641bee8 +size 1465 diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json new file mode 100644 index 0000000..83f5639 --- /dev/null +++ b/checkpoint-1000/trainer_state.json @@ -0,0 +1,384 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.7361111111111112, + "eval_steps": 500, + "global_step": 1000, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.193453788757324, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2816, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.9958441257476807, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2989, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 4.101428985595703, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3146, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.387007236480713, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2792, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.733682870864868, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3185, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.3572065830230713, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2915, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.337113380432129, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2886, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.326784133911133, + "learning_rate": 8.321522974916968e-07, + "loss": 1.3046, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.501497268676758, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2783, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.4914722442626953, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2741, + "step": 1000 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.0074265361167155e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-1050/README.md b/checkpoint-1050/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-1050/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-1050/adapter_config.json b/checkpoint-1050/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-1050/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1050/adapter_model.safetensors b/checkpoint-1050/adapter_model.safetensors new file mode 100644 index 0000000..946ad7f --- /dev/null +++ b/checkpoint-1050/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72e4770bcb62b1500b4e600d15dfd0c75defd43873fbbe0e2b245280ca20658 +size 671149168 diff --git a/checkpoint-1050/optimizer.pt b/checkpoint-1050/optimizer.pt new file mode 100644 index 0000000..57c0841 --- /dev/null +++ b/checkpoint-1050/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22005337ca7d831ed1afd530372835005fdf71403f0fd1550ad00d340eeaa2b9 +size 1342562339 diff --git a/checkpoint-1050/rng_state.pth b/checkpoint-1050/rng_state.pth new file mode 100644 index 0000000..c7829b4 --- /dev/null +++ b/checkpoint-1050/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a46b22b3cc4f199582996cf55c7028978107dc1fe818085d1d1a4d270aa9497c +size 14645 diff --git a/checkpoint-1050/scheduler.pt b/checkpoint-1050/scheduler.pt new file mode 100644 index 0000000..0d92c59 --- /dev/null +++ b/checkpoint-1050/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:abe9abb5efc489b294c297766a8ae2c71262b2cf1b3df1555b36fda19a8e7406 +size 1465 diff --git a/checkpoint-1050/trainer_state.json b/checkpoint-1050/trainer_state.json new file mode 100644 index 0000000..b3d088f --- /dev/null +++ b/checkpoint-1050/trainer_state.json @@ -0,0 +1,398 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.8229166666666665, + "eval_steps": 500, + "global_step": 1050, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.193453788757324, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2816, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.9958441257476807, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2989, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 4.101428985595703, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3146, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.387007236480713, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2792, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.733682870864868, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3185, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.3572065830230713, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2915, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.337113380432129, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2886, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.326784133911133, + "learning_rate": 8.321522974916968e-07, + "loss": 1.3046, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.501497268676758, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2783, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.4914722442626953, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2741, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.376003742218018, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.279, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 4.257233619689941, + "learning_rate": 2.906855485332305e-07, + "loss": 1.2538, + "step": 1040 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.108497820932178e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1050/training_args.bin b/checkpoint-1050/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-1050/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-1100/README.md b/checkpoint-1100/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-1100/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-1100/adapter_config.json b/checkpoint-1100/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-1100/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1100/adapter_model.safetensors b/checkpoint-1100/adapter_model.safetensors new file mode 100644 index 0000000..157bb59 --- /dev/null +++ b/checkpoint-1100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d00ecced49bde0a2bc956224cafe3b32a4899c97e5e53d3de21e3cede3845d +size 671149168 diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000..172d705 --- /dev/null +++ b/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:732ac338f3cf07142696f711badfef134977bcb3ead829ebc4eb22db2cf4149f +size 1342562339 diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth new file mode 100644 index 0000000..4129f78 --- /dev/null +++ b/checkpoint-1100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f166523cfe0c7568950a7a790ad35225be87259a4e0fa195ec2741ec0bd84d5 +size 14645 diff --git a/checkpoint-1100/scheduler.pt b/checkpoint-1100/scheduler.pt new file mode 100644 index 0000000..60a47de --- /dev/null +++ b/checkpoint-1100/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315c6a6de3128d29cfc459c9f1551c37f38030611e281b0aa330fe139ba0892f +size 1465 diff --git a/checkpoint-1100/trainer_state.json b/checkpoint-1100/trainer_state.json new file mode 100644 index 0000000..53d8bf4 --- /dev/null +++ b/checkpoint-1100/trainer_state.json @@ -0,0 +1,419 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.9097222222222223, + "eval_steps": 500, + "global_step": 1100, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.193453788757324, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2816, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.9958441257476807, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2989, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 4.101428985595703, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3146, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.387007236480713, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2792, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.733682870864868, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3185, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.3572065830230713, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2915, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.337113380432129, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2886, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.326784133911133, + "learning_rate": 8.321522974916968e-07, + "loss": 1.3046, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.501497268676758, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2783, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.4914722442626953, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2741, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.376003742218018, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.279, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 4.257233619689941, + "learning_rate": 2.906855485332305e-07, + "loss": 1.2538, + "step": 1040 + }, + { + "epoch": 1.8402777777777777, + "grad_norm": 3.9241201877593994, + "learning_rate": 1.975176196540185e-07, + "loss": 1.2794, + "step": 1060 + }, + { + "epoch": 1.875, + "grad_norm": 4.226406574249268, + "learning_rate": 1.2200896627521718e-07, + "loss": 1.2932, + "step": 1080 + }, + { + "epoch": 1.9097222222222223, + "grad_norm": 4.021918296813965, + "learning_rate": 6.443724232808146e-08, + "loss": 1.262, + "step": 1100 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.2074900407835034e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1100/training_args.bin b/checkpoint-1100/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-1100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-1150/README.md b/checkpoint-1150/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-1150/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-1150/adapter_config.json b/checkpoint-1150/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-1150/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-1150/adapter_model.safetensors b/checkpoint-1150/adapter_model.safetensors new file mode 100644 index 0000000..0f1a8ef --- /dev/null +++ b/checkpoint-1150/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6e649d23c4df73746357a23b10428d6cd25bb42f6331251485b5a595c245680 +size 671149168 diff --git a/checkpoint-1150/optimizer.pt b/checkpoint-1150/optimizer.pt new file mode 100644 index 0000000..4be9175 --- /dev/null +++ b/checkpoint-1150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d24b2c893e57c0ff70e5450184bd4e2a2aee749a97287c8f30d0f551caf070f +size 1342562339 diff --git a/checkpoint-1150/rng_state.pth b/checkpoint-1150/rng_state.pth new file mode 100644 index 0000000..b9775b5 --- /dev/null +++ b/checkpoint-1150/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f20cad884897e9c557b848e15a51b18e6c8489fcb5600739b7d98d6c460a17e +size 14645 diff --git a/checkpoint-1150/scheduler.pt b/checkpoint-1150/scheduler.pt new file mode 100644 index 0000000..d432e90 --- /dev/null +++ b/checkpoint-1150/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28b81089eb143a676da720978f118caf9eee0a372736c9ef6f38cdec3dd8d997 +size 1465 diff --git a/checkpoint-1150/trainer_state.json b/checkpoint-1150/trainer_state.json new file mode 100644 index 0000000..7fd8fb5 --- /dev/null +++ b/checkpoint-1150/trainer_state.json @@ -0,0 +1,433 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.9965277777777777, + "eval_steps": 500, + "global_step": 1150, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.193453788757324, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2816, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.9958441257476807, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2989, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 4.101428985595703, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3146, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.387007236480713, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2792, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.733682870864868, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3185, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.3572065830230713, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2915, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.337113380432129, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2886, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.326784133911133, + "learning_rate": 8.321522974916968e-07, + "loss": 1.3046, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.501497268676758, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2783, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.4914722442626953, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2741, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.376003742218018, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.279, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 4.257233619689941, + "learning_rate": 2.906855485332305e-07, + "loss": 1.2538, + "step": 1040 + }, + { + "epoch": 1.8402777777777777, + "grad_norm": 3.9241201877593994, + "learning_rate": 1.975176196540185e-07, + "loss": 1.2794, + "step": 1060 + }, + { + "epoch": 1.875, + "grad_norm": 4.226406574249268, + "learning_rate": 1.2200896627521718e-07, + "loss": 1.2932, + "step": 1080 + }, + { + "epoch": 1.9097222222222223, + "grad_norm": 4.021918296813965, + "learning_rate": 6.443724232808146e-08, + "loss": 1.262, + "step": 1100 + }, + { + "epoch": 1.9444444444444444, + "grad_norm": 5.649799346923828, + "learning_rate": 2.501414560839577e-08, + "loss": 1.2514, + "step": 1120 + }, + { + "epoch": 1.9791666666666665, + "grad_norm": 3.755774974822998, + "learning_rate": 3.884639339534202e-09, + "loss": 1.271, + "step": 1140 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.3084839821724877e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-1150/training_args.bin b/checkpoint-1150/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-1150/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-150/README.md b/checkpoint-150/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-150/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-150/adapter_config.json b/checkpoint-150/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-150/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-150/adapter_model.safetensors b/checkpoint-150/adapter_model.safetensors new file mode 100644 index 0000000..6da6479 --- /dev/null +++ b/checkpoint-150/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7b3c091cc71db1555f02e15d0784a3ffaf482c622a293f8de6809cf59c91f3 +size 671149168 diff --git a/checkpoint-150/optimizer.pt b/checkpoint-150/optimizer.pt new file mode 100644 index 0000000..46f5438 --- /dev/null +++ b/checkpoint-150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bcefd1c64077242e0070090123dd32b42f48d497da34cae8f5369988566999b1 +size 1342562339 diff --git a/checkpoint-150/rng_state.pth b/checkpoint-150/rng_state.pth new file mode 100644 index 0000000..5945956 --- /dev/null +++ b/checkpoint-150/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4d1d2d9971cbb6c2efd3f6d7c32d010bd117280fd908a3053d0f60f1927ea47 +size 14645 diff --git a/checkpoint-150/scheduler.pt b/checkpoint-150/scheduler.pt new file mode 100644 index 0000000..9bc80d4 --- /dev/null +++ b/checkpoint-150/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e5c3b1f4b3d2abec87ff5069b5d5df261c03ab9fab7ada1150395aac7685dc6 +size 1465 diff --git a/checkpoint-150/trainer_state.json b/checkpoint-150/trainer_state.json new file mode 100644 index 0000000..cc4413b --- /dev/null +++ b/checkpoint-150/trainer_state.json @@ -0,0 +1,83 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.2604166666666667, + "eval_steps": 500, + "global_step": 150, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 3.005989100273664e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-150/training_args.bin b/checkpoint-150/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-150/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-200/README.md b/checkpoint-200/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-200/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-200/adapter_config.json b/checkpoint-200/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-200/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-200/adapter_model.safetensors b/checkpoint-200/adapter_model.safetensors new file mode 100644 index 0000000..80c216d --- /dev/null +++ b/checkpoint-200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a88f5bcfb36778bcfc1b97b9e3212bc5248626088d0d41e844405d099439218 +size 671149168 diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000..5555cfe --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f578b853fa34d58c5ec7d8ddac1daead60e12695e71e75710c6192fc062b7726 +size 1342562339 diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth new file mode 100644 index 0000000..2051ffa --- /dev/null +++ b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc4e0ced003b5013da8539696df1959d3cff952d018e97a1cbe4005fa1e8a4ef +size 14645 diff --git a/checkpoint-200/scheduler.pt b/checkpoint-200/scheduler.pt new file mode 100644 index 0000000..fb2732f --- /dev/null +++ b/checkpoint-200/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dacf44b20691c6fc535bf16b0ef4e66f3a5b3cb2170a2da905fbebeb4c5a46ff +size 1465 diff --git a/checkpoint-200/trainer_state.json b/checkpoint-200/trainer_state.json new file mode 100644 index 0000000..20c2cd3 --- /dev/null +++ b/checkpoint-200/trainer_state.json @@ -0,0 +1,104 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.3472222222222222, + "eval_steps": 500, + "global_step": 200, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 4.031728671286886e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-200/training_args.bin b/checkpoint-200/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-250/README.md b/checkpoint-250/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-250/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-250/adapter_config.json b/checkpoint-250/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-250/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-250/adapter_model.safetensors b/checkpoint-250/adapter_model.safetensors new file mode 100644 index 0000000..33c42c3 --- /dev/null +++ b/checkpoint-250/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:790c9d1e0e8bd98feab2d37fa648b09d29d7d2d73e8e7b1241b596d85c97a5af +size 671149168 diff --git a/checkpoint-250/optimizer.pt b/checkpoint-250/optimizer.pt new file mode 100644 index 0000000..7d0b0bf --- /dev/null +++ b/checkpoint-250/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010fa69d2addf135b03ef8201f394904a5d0a76849db3d8bcd663d6723794051 +size 1342562339 diff --git a/checkpoint-250/rng_state.pth b/checkpoint-250/rng_state.pth new file mode 100644 index 0000000..63108f7 --- /dev/null +++ b/checkpoint-250/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff21f0aad1ed5420ebfda78faf43946392315a455210edabca911af56674cec7 +size 14645 diff --git a/checkpoint-250/scheduler.pt b/checkpoint-250/scheduler.pt new file mode 100644 index 0000000..59e9fe4 --- /dev/null +++ b/checkpoint-250/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12bc768c5ceac0892205b61d77c6800d899da633a32337206aa415df9749b66a +size 1465 diff --git a/checkpoint-250/trainer_state.json b/checkpoint-250/trainer_state.json new file mode 100644 index 0000000..fe92140 --- /dev/null +++ b/checkpoint-250/trainer_state.json @@ -0,0 +1,118 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.4340277777777778, + "eval_steps": 500, + "global_step": 250, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 5.029771929580339e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-250/training_args.bin b/checkpoint-250/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-250/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-300/README.md b/checkpoint-300/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-300/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-300/adapter_config.json b/checkpoint-300/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-300/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-300/adapter_model.safetensors b/checkpoint-300/adapter_model.safetensors new file mode 100644 index 0000000..56713d0 --- /dev/null +++ b/checkpoint-300/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55a72307315a69d622c7ede6f9a0629ad9f53d661f2943666bddcfd9e5da6a9e +size 671149168 diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000..93a069d --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8ab581fe88133fafd9aabdcaa8167afe145af232139a6f773ec53d236086312 +size 1342562339 diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth new file mode 100644 index 0000000..b5d51e3 --- /dev/null +++ b/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac8c1581ab76c3f7bf7a2880e65d71eb618d8c2c1aa9b1572d5761adcf47e8e +size 14645 diff --git a/checkpoint-300/scheduler.pt b/checkpoint-300/scheduler.pt new file mode 100644 index 0000000..a782478 --- /dev/null +++ b/checkpoint-300/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8011544f8969ccf121f310e7c9677b774202f770f03769833c73ecbfadde40a4 +size 1465 diff --git a/checkpoint-300/trainer_state.json b/checkpoint-300/trainer_state.json new file mode 100644 index 0000000..522d8c5 --- /dev/null +++ b/checkpoint-300/trainer_state.json @@ -0,0 +1,139 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.5208333333333334, + "eval_steps": 500, + "global_step": 300, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 6.016103183292826e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-300/training_args.bin b/checkpoint-300/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-350/README.md b/checkpoint-350/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-350/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-350/adapter_config.json b/checkpoint-350/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-350/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-350/adapter_model.safetensors b/checkpoint-350/adapter_model.safetensors new file mode 100644 index 0000000..7810756 --- /dev/null +++ b/checkpoint-350/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e65c97ab3e97c2b5b07497fb9ff23a013f6296e2663c749d5b39b57d3fc6161e +size 671149168 diff --git a/checkpoint-350/optimizer.pt b/checkpoint-350/optimizer.pt new file mode 100644 index 0000000..62a197a --- /dev/null +++ b/checkpoint-350/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f69d07b8f9a7c4c99d5a66d5c14d378db2e7ebd65b6641efb36da7fa2291bb8 +size 1342562339 diff --git a/checkpoint-350/rng_state.pth b/checkpoint-350/rng_state.pth new file mode 100644 index 0000000..90165db --- /dev/null +++ b/checkpoint-350/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ad1631a0ad068ec449f6eede716e58462ecbcd22d0c54c2727b1eed07ff963b +size 14645 diff --git a/checkpoint-350/scheduler.pt b/checkpoint-350/scheduler.pt new file mode 100644 index 0000000..144e670 --- /dev/null +++ b/checkpoint-350/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6d13f122fa4e9259c6cf2ccd0d4a831e7733be6388a9b01a859d975eb74082 +size 1465 diff --git a/checkpoint-350/trainer_state.json b/checkpoint-350/trainer_state.json new file mode 100644 index 0000000..ed3e6b2 --- /dev/null +++ b/checkpoint-350/trainer_state.json @@ -0,0 +1,153 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.6076388888888888, + "eval_steps": 500, + "global_step": 350, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 7.00188198395904e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-350/training_args.bin b/checkpoint-350/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-350/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-400/README.md b/checkpoint-400/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-400/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-400/adapter_config.json b/checkpoint-400/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-400/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-400/adapter_model.safetensors b/checkpoint-400/adapter_model.safetensors new file mode 100644 index 0000000..f6aea9a --- /dev/null +++ b/checkpoint-400/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d237781370545b3dcbcdbe435120bf4a17c07691c07a13636741147a09a926 +size 671149168 diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt new file mode 100644 index 0000000..7602716 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c446779bdef7b93b78515dd5f517c62a6a630e42e4acdc0243bb60787b9b2227 +size 1342562339 diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth new file mode 100644 index 0000000..2a4eb0a --- /dev/null +++ b/checkpoint-400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:132dc1388181d24199cf5863c838c52e57935757160a52521ca7cdc17c1827d0 +size 14645 diff --git a/checkpoint-400/scheduler.pt b/checkpoint-400/scheduler.pt new file mode 100644 index 0000000..fe9d5cc --- /dev/null +++ b/checkpoint-400/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cc7f2c390b57e07da00163d66a7f2ae7ece3e78a62f304c58c0f81ef0baa87 +size 1465 diff --git a/checkpoint-400/trainer_state.json b/checkpoint-400/trainer_state.json new file mode 100644 index 0000000..0b17ec7 --- /dev/null +++ b/checkpoint-400/trainer_state.json @@ -0,0 +1,174 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.6944444444444444, + "eval_steps": 500, + "global_step": 400, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 8.001122223852749e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-400/training_args.bin b/checkpoint-400/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-450/README.md b/checkpoint-450/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-450/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-450/adapter_config.json b/checkpoint-450/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-450/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-450/adapter_model.safetensors b/checkpoint-450/adapter_model.safetensors new file mode 100644 index 0000000..d6bc5ae --- /dev/null +++ b/checkpoint-450/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c301753f53c340ef3a061e74923c746097d42a63834198e78be8f2d5dd7ae90a +size 671149168 diff --git a/checkpoint-450/optimizer.pt b/checkpoint-450/optimizer.pt new file mode 100644 index 0000000..ec2de17 --- /dev/null +++ b/checkpoint-450/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2e5e38e89980e0167afbc2499be7e000cabdb041a175605c7c1193d7913065 +size 1342562339 diff --git a/checkpoint-450/rng_state.pth b/checkpoint-450/rng_state.pth new file mode 100644 index 0000000..cc3a80f --- /dev/null +++ b/checkpoint-450/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8afc2a53fd4e86647d6935c89c905fc4720d1e07a0408187f11ca89dc2c9964 +size 14645 diff --git a/checkpoint-450/scheduler.pt b/checkpoint-450/scheduler.pt new file mode 100644 index 0000000..4b1258a --- /dev/null +++ b/checkpoint-450/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384bc6e7c7dc78761d777acc2ec342f72b87fe7d2483bfdf597b557007de8a7d +size 1465 diff --git a/checkpoint-450/trainer_state.json b/checkpoint-450/trainer_state.json new file mode 100644 index 0000000..5932310 --- /dev/null +++ b/checkpoint-450/trainer_state.json @@ -0,0 +1,188 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.78125, + "eval_steps": 500, + "global_step": 450, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9.001890917174477e+16, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-450/training_args.bin b/checkpoint-450/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-450/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-50/README.md b/checkpoint-50/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-50/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-50/adapter_config.json b/checkpoint-50/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-50/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-50/adapter_model.safetensors b/checkpoint-50/adapter_model.safetensors new file mode 100644 index 0000000..f5c9c0a --- /dev/null +++ b/checkpoint-50/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f4b0493988953b3831be0b8a311f3072ed1cea9b209c98449f0c46c3200158e +size 671149168 diff --git a/checkpoint-50/optimizer.pt b/checkpoint-50/optimizer.pt new file mode 100644 index 0000000..a682943 --- /dev/null +++ b/checkpoint-50/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2770c9e1c71d926dc67023c383c19fc8b921256f8fff4b618786b48d85824f4 +size 1342562339 diff --git a/checkpoint-50/rng_state.pth b/checkpoint-50/rng_state.pth new file mode 100644 index 0000000..c0247c9 --- /dev/null +++ b/checkpoint-50/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a28bbf7031c7d4300b29724f0e2d963da827e75404483114e5db92f34354f891 +size 14645 diff --git a/checkpoint-50/scheduler.pt b/checkpoint-50/scheduler.pt new file mode 100644 index 0000000..1365fdd --- /dev/null +++ b/checkpoint-50/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:429753af91844c8e723460e500b16300ef22bee5be6ffdf96a0f5e7a4101ca3a +size 1465 diff --git a/checkpoint-50/trainer_state.json b/checkpoint-50/trainer_state.json new file mode 100644 index 0000000..7f24bcd --- /dev/null +++ b/checkpoint-50/trainer_state.json @@ -0,0 +1,48 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.08680555555555555, + "eval_steps": 500, + "global_step": 50, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 9945259738988544.0, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-50/training_args.bin b/checkpoint-50/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-50/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-500/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-500/adapter_config.json b/checkpoint-500/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-500/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-500/adapter_model.safetensors b/checkpoint-500/adapter_model.safetensors new file mode 100644 index 0000000..b36fbf8 --- /dev/null +++ b/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7bbcfb7bd4c347badf2ab74965d0fcb88582c88752c9f32f8364ef424d52713 +size 671149168 diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100644 index 0000000..f156341 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:543932e5169866a977d42cc57ea239e435552a72745e845d6197fdfa387f7bb5 +size 1342562339 diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth new file mode 100644 index 0000000..ed4fd1a --- /dev/null +++ b/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ac1d92134c5bc2926f90121a9973190cd1d259e5f9544e913dd23b3fc74aa0f +size 14645 diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt new file mode 100644 index 0000000..f14c49a --- /dev/null +++ b/checkpoint-500/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56d00b3dceef9b6f5ecba6ca112aac49209cb479316e5bd5c0651dae9c1ba9b3 +size 1465 diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json new file mode 100644 index 0000000..2b583ca --- /dev/null +++ b/checkpoint-500/trainer_state.json @@ -0,0 +1,209 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.8680555555555556, + "eval_steps": 500, + "global_step": 500, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.003400211332137e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-550/README.md b/checkpoint-550/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-550/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-550/adapter_config.json b/checkpoint-550/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-550/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-550/adapter_model.safetensors b/checkpoint-550/adapter_model.safetensors new file mode 100644 index 0000000..f2d3915 --- /dev/null +++ b/checkpoint-550/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:397a48dfc211e8f0acdf1d658ac49308ae364bcb11c333096d0df1e53a749f93 +size 671149168 diff --git a/checkpoint-550/optimizer.pt b/checkpoint-550/optimizer.pt new file mode 100644 index 0000000..0e9b04c --- /dev/null +++ b/checkpoint-550/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53b3ec371a5f1e416651c602e653ec4a284e66022f03f21ccd0f1fc86e448eac +size 1342562339 diff --git a/checkpoint-550/rng_state.pth b/checkpoint-550/rng_state.pth new file mode 100644 index 0000000..888a3bc --- /dev/null +++ b/checkpoint-550/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b128e6268caaa0b3e34d032cc7966c1b63612f211b2481ef2c955eb26157561e +size 14645 diff --git a/checkpoint-550/scheduler.pt b/checkpoint-550/scheduler.pt new file mode 100644 index 0000000..a344f2f --- /dev/null +++ b/checkpoint-550/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95f0ec44226045e10b9e9885bb6dcc32b6fb20b4e398697125d5903dc06a3dc3 +size 1465 diff --git a/checkpoint-550/trainer_state.json b/checkpoint-550/trainer_state.json new file mode 100644 index 0000000..a4d2a68 --- /dev/null +++ b/checkpoint-550/trainer_state.json @@ -0,0 +1,223 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 0.9548611111111112, + "eval_steps": 500, + "global_step": 550, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.1050239491938714e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-550/training_args.bin b/checkpoint-550/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-550/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-600/README.md b/checkpoint-600/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-600/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-600/adapter_config.json b/checkpoint-600/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-600/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-600/adapter_model.safetensors b/checkpoint-600/adapter_model.safetensors new file mode 100644 index 0000000..c993d04 --- /dev/null +++ b/checkpoint-600/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2aef1741443f6f72cbecaaf2ef8579d9b84e39aae1ee8f028f07f63b2cc1e873 +size 671149168 diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000..959394c --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b4495a7191580b8f8225b3cbeaa6e3ca469ef7577b12907fd567504e8e8dfae +size 1342562339 diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth new file mode 100644 index 0000000..9d1a1cb --- /dev/null +++ b/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da0f0661d9ab7ef7c096b10ee812914978fbf6533d06b52045207f0376aa74f6 +size 14645 diff --git a/checkpoint-600/scheduler.pt b/checkpoint-600/scheduler.pt new file mode 100644 index 0000000..9d84cb1 --- /dev/null +++ b/checkpoint-600/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97e41312b87b4204123e46e88d3bc7c857cfb3fbe531078e169cc10e0d939469 +size 1465 diff --git a/checkpoint-600/trainer_state.json b/checkpoint-600/trainer_state.json new file mode 100644 index 0000000..f2c09ac --- /dev/null +++ b/checkpoint-600/trainer_state.json @@ -0,0 +1,244 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0416666666666667, + "eval_steps": 500, + "global_step": 600, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.2045060107462246e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-600/training_args.bin b/checkpoint-600/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-650/README.md b/checkpoint-650/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-650/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-650/adapter_config.json b/checkpoint-650/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-650/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-650/adapter_model.safetensors b/checkpoint-650/adapter_model.safetensors new file mode 100644 index 0000000..8f64a50 --- /dev/null +++ b/checkpoint-650/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0619899638b585f2e9709bbaa5aadc3938b7596da6dc75b64689821f8e8134a9 +size 671149168 diff --git a/checkpoint-650/optimizer.pt b/checkpoint-650/optimizer.pt new file mode 100644 index 0000000..2ef93ca --- /dev/null +++ b/checkpoint-650/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe09756a599c78029ac4f29ce764cccecb7db28c0713d8bbf625e4951d30031d +size 1342562339 diff --git a/checkpoint-650/rng_state.pth b/checkpoint-650/rng_state.pth new file mode 100644 index 0000000..f015875 --- /dev/null +++ b/checkpoint-650/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23aba45e509ad8c4ca2b9712bda0b9fb3465d5909197dafad30a72b1de234f1c +size 14645 diff --git a/checkpoint-650/scheduler.pt b/checkpoint-650/scheduler.pt new file mode 100644 index 0000000..3d8d688 --- /dev/null +++ b/checkpoint-650/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:701963ab8d7d1849c052af5fce88023fdda6f713e5072a25a5a4aa822ce8b58b +size 1465 diff --git a/checkpoint-650/trainer_state.json b/checkpoint-650/trainer_state.json new file mode 100644 index 0000000..842bf27 --- /dev/null +++ b/checkpoint-650/trainer_state.json @@ -0,0 +1,258 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.1284722222222223, + "eval_steps": 500, + "global_step": 650, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.30292920395989e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-650/training_args.bin b/checkpoint-650/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-650/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-700/README.md b/checkpoint-700/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-700/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-700/adapter_config.json b/checkpoint-700/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-700/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-700/adapter_model.safetensors b/checkpoint-700/adapter_model.safetensors new file mode 100644 index 0000000..856d1bb --- /dev/null +++ b/checkpoint-700/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9310221bb57e6c68f7bc0f84d674ab14a7c905fb41de77679dbda8a70409f9a6 +size 671149168 diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt new file mode 100644 index 0000000..ca43071 --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36be2bffb6780de8a84b19a48280d1bd87b2d783f1d187c6a2ce3ae3898f012e +size 1342562339 diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth new file mode 100644 index 0000000..0f993bf --- /dev/null +++ b/checkpoint-700/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fbd368c45c97ef13f6be65c594d10dd0cf1bccfa04665c8493e9f8734ceb788 +size 14645 diff --git a/checkpoint-700/scheduler.pt b/checkpoint-700/scheduler.pt new file mode 100644 index 0000000..0e67b96 --- /dev/null +++ b/checkpoint-700/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f96c27cd0f37d375f25ee4ddc217cab5525667adb393b37449a4bbaa0d7f3f00 +size 1465 diff --git a/checkpoint-700/trainer_state.json b/checkpoint-700/trainer_state.json new file mode 100644 index 0000000..7fcc1f4 --- /dev/null +++ b/checkpoint-700/trainer_state.json @@ -0,0 +1,279 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.2152777777777777, + "eval_steps": 500, + "global_step": 700, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.402033755930624e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-700/training_args.bin b/checkpoint-700/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-750/README.md b/checkpoint-750/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-750/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-750/adapter_config.json b/checkpoint-750/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-750/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-750/adapter_model.safetensors b/checkpoint-750/adapter_model.safetensors new file mode 100644 index 0000000..abc4b39 --- /dev/null +++ b/checkpoint-750/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b84b709472b27cbbcea60c903eb334bb1b393a1b7aa3b770030da9fdaefeb64 +size 671149168 diff --git a/checkpoint-750/optimizer.pt b/checkpoint-750/optimizer.pt new file mode 100644 index 0000000..b57ead2 --- /dev/null +++ b/checkpoint-750/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f6b55c2bf3edf329e14e0e1b988989e52714782e7457cb6578105e5afbce38 +size 1342562339 diff --git a/checkpoint-750/rng_state.pth b/checkpoint-750/rng_state.pth new file mode 100644 index 0000000..c6df52c --- /dev/null +++ b/checkpoint-750/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64b8dba71c215994ef0994d9a500ff423f7558010af3ed9b84a2fde1226ccd0f +size 14645 diff --git a/checkpoint-750/scheduler.pt b/checkpoint-750/scheduler.pt new file mode 100644 index 0000000..cd6206b --- /dev/null +++ b/checkpoint-750/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72b6be6f074d6123936480d0df9f32aebfcd8ee4d1f99a6b9b9459f1d72f8bd7 +size 1465 diff --git a/checkpoint-750/trainer_state.json b/checkpoint-750/trainer_state.json new file mode 100644 index 0000000..da55a36 --- /dev/null +++ b/checkpoint-750/trainer_state.json @@ -0,0 +1,293 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.3020833333333333, + "eval_steps": 500, + "global_step": 750, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.5041012977395302e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-750/training_args.bin b/checkpoint-750/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-750/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-800/README.md b/checkpoint-800/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-800/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-800/adapter_config.json b/checkpoint-800/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-800/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-800/adapter_model.safetensors b/checkpoint-800/adapter_model.safetensors new file mode 100644 index 0000000..b61b909 --- /dev/null +++ b/checkpoint-800/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae9e126a10d6b451655a0935ff652625f50c8c00c9b06c9276256ec436ef0978 +size 671149168 diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt new file mode 100644 index 0000000..75a956e --- /dev/null +++ b/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5103af92f604a194454883e0144cc1c4ac012559efaec7f033e41f34e0cd688 +size 1342562339 diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth new file mode 100644 index 0000000..37d2a65 --- /dev/null +++ b/checkpoint-800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378520128124c5e6be269058e927701edef3461195517b0e8becfe895028aa2c +size 14645 diff --git a/checkpoint-800/scheduler.pt b/checkpoint-800/scheduler.pt new file mode 100644 index 0000000..8f798aa --- /dev/null +++ b/checkpoint-800/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9712944284fb0cb3480a911521785b37cb130aaba60e1725920cf9c7ae6093ea +size 1465 diff --git a/checkpoint-800/trainer_state.json b/checkpoint-800/trainer_state.json new file mode 100644 index 0000000..fa246e3 --- /dev/null +++ b/checkpoint-800/trainer_state.json @@ -0,0 +1,314 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.3888888888888888, + "eval_steps": 500, + "global_step": 800, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.6055114204233728e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-800/training_args.bin b/checkpoint-800/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-850/README.md b/checkpoint-850/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-850/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-850/adapter_config.json b/checkpoint-850/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-850/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-850/adapter_model.safetensors b/checkpoint-850/adapter_model.safetensors new file mode 100644 index 0000000..d71329d --- /dev/null +++ b/checkpoint-850/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4018256e505fc796c685e19d5d6186bc83c445c1bb01184532114cb5de33bb5 +size 671149168 diff --git a/checkpoint-850/optimizer.pt b/checkpoint-850/optimizer.pt new file mode 100644 index 0000000..e8af4bb --- /dev/null +++ b/checkpoint-850/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1ce651302fe134a8666aac6427025f7cf1c39fdf4d2e4513b0ee05815c27bc6 +size 1342562339 diff --git a/checkpoint-850/rng_state.pth b/checkpoint-850/rng_state.pth new file mode 100644 index 0000000..acb9b80 --- /dev/null +++ b/checkpoint-850/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49fe1ce4f4c68599e1f31d3769e439b74012fc8d400e1df7e692f6d848467ceb +size 14645 diff --git a/checkpoint-850/scheduler.pt b/checkpoint-850/scheduler.pt new file mode 100644 index 0000000..dc7ef30 --- /dev/null +++ b/checkpoint-850/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d281893a88f586c1ef75eec259a2f50ece352b0e745fc416bb39ce4f50c0f3b +size 1465 diff --git a/checkpoint-850/trainer_state.json b/checkpoint-850/trainer_state.json new file mode 100644 index 0000000..0650a26 --- /dev/null +++ b/checkpoint-850/trainer_state.json @@ -0,0 +1,328 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.4756944444444444, + "eval_steps": 500, + "global_step": 850, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.193453788757324, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2816, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.9958441257476807, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2989, + "step": 840 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.70766183018922e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-850/training_args.bin b/checkpoint-850/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-850/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-900/README.md b/checkpoint-900/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-900/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-900/adapter_config.json b/checkpoint-900/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-900/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-900/adapter_model.safetensors b/checkpoint-900/adapter_model.safetensors new file mode 100644 index 0000000..9966592 --- /dev/null +++ b/checkpoint-900/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dfb732ea87c26692b87a90775b0f05a5919016ff33b96ed728644c8e7356ca1 +size 671149168 diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt new file mode 100644 index 0000000..312dba1 --- /dev/null +++ b/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6406d6531dc89c8d6306e1a72efd25ff10878b3dcff692df6ec7603f673ddc3 +size 1342562339 diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth new file mode 100644 index 0000000..c812e3a --- /dev/null +++ b/checkpoint-900/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56530805422ecf7a4063e84b605ff5d07a4cfb18c2980b86cf3531255480a530 +size 14645 diff --git a/checkpoint-900/scheduler.pt b/checkpoint-900/scheduler.pt new file mode 100644 index 0000000..752ac2c --- /dev/null +++ b/checkpoint-900/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa8717b84ecd3aafdf025100adb33e29dbdd998c3eda4e83725edc4c9c48219 +size 1465 diff --git a/checkpoint-900/trainer_state.json b/checkpoint-900/trainer_state.json new file mode 100644 index 0000000..a444455 --- /dev/null +++ b/checkpoint-900/trainer_state.json @@ -0,0 +1,349 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.5625, + "eval_steps": 500, + "global_step": 900, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.193453788757324, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2816, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.9958441257476807, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2989, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 4.101428985595703, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3146, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.387007236480713, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2792, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.733682870864868, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3185, + "step": 900 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.807725808950313e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-900/training_args.bin b/checkpoint-900/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/checkpoint-950/README.md b/checkpoint-950/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/checkpoint-950/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/checkpoint-950/adapter_config.json b/checkpoint-950/adapter_config.json new file mode 100644 index 0000000..2515d87 --- /dev/null +++ b/checkpoint-950/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj", + "o_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/checkpoint-950/adapter_model.safetensors b/checkpoint-950/adapter_model.safetensors new file mode 100644 index 0000000..4c0034b --- /dev/null +++ b/checkpoint-950/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eff8c3a80b5c2391b8b27c6d731816158e1a304e78703ffcd3abd67665703d65 +size 671149168 diff --git a/checkpoint-950/optimizer.pt b/checkpoint-950/optimizer.pt new file mode 100644 index 0000000..b47375f --- /dev/null +++ b/checkpoint-950/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f1c60f160e86a9dd6fb7633e2759189dbf56cc6ec746c3d144c9cc6e0bab7b9 +size 1342562339 diff --git a/checkpoint-950/rng_state.pth b/checkpoint-950/rng_state.pth new file mode 100644 index 0000000..de77ff6 --- /dev/null +++ b/checkpoint-950/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f1f8fbdd15a2ba729b7f3c80f53a508c1dfab5765f4aa7952d8018981d2bb5 +size 14645 diff --git a/checkpoint-950/scheduler.pt b/checkpoint-950/scheduler.pt new file mode 100644 index 0000000..f68e810 --- /dev/null +++ b/checkpoint-950/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96b0deceec755ce9e150cc4f2fb1d1ed2f491e7dd6980aa723ae9f45f4ebfb3 +size 1465 diff --git a/checkpoint-950/trainer_state.json b/checkpoint-950/trainer_state.json new file mode 100644 index 0000000..6d000a1 --- /dev/null +++ b/checkpoint-950/trainer_state.json @@ -0,0 +1,363 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.6493055555555556, + "eval_steps": 500, + "global_step": 950, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4759202003479004, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5561, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.5604989528656006, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3957, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9377268552780151, + "learning_rate": 5.086206896551724e-06, + "loss": 2.217, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7941242456436157, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0366, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.2135872840881348, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9154, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.290032148361206, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8946, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.4187541007995605, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7858, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.115030288696289, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7133, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290724754333496, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7567, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.318016767501831, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6653, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.37850284576416, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6518, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.5013656616210938, + "learning_rate": 9.656212814111567e-06, + "loss": 1.669, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.0407257080078125, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6393, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.709101915359497, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6274, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9556779861450195, + "learning_rate": 9.249676511588e-06, + "loss": 1.6256, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9455294609069824, + "learning_rate": 9.082186599639429e-06, + "loss": 1.61, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.631028413772583, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5928, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5670149326324463, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5608, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.519019365310669, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5496, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.059999942779541, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5339, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.882279872894287, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5109, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.6647043228149414, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5076, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.2523193359375, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5043, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.349648952484131, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4809, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.5382089614868164, + "learning_rate": 6.990191353373876e-06, + "loss": 1.4808, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.7552590370178223, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4482, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.215052366256714, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4627, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.1179182529449463, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4731, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.928844451904297, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4354, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.2214365005493164, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3671, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3545398712158203, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.373, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 4.0173234939575195, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3456, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.150284767150879, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3462, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.555105209350586, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3409, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7820332050323486, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3522, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.446506977081299, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3083, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.7315480709075928, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3234, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.601447105407715, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3384, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.626559257507324, + "learning_rate": 2.871652321931161e-06, + "loss": 1.3196, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 3.092618227005005, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3185, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.193453788757324, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2816, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.9958441257476807, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2989, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 4.101428985595703, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3146, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.387007236480713, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2792, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.733682870864868, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3185, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.3572065830230713, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2915, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.337113380432129, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2886, + "step": 940 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 1.9095429053782426e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/checkpoint-950/training_args.bin b/checkpoint-950/training_args.bin new file mode 100644 index 0000000..27fdcbe --- /dev/null +++ b/checkpoint-950/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3ced39871fa7c7a88f826b09e41064daaac1ea0284f0a8b3036f748ab90c43e +size 6033 diff --git a/config.json b/config.json new file mode 100644 index 0000000..640d98b --- /dev/null +++ b/config.json @@ -0,0 +1,29 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": 128001, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "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, + "tie_word_embeddings": false, + "transformers_version": "4.57.6", + "use_cache": true, + "vocab_size": 128320 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..bab1302 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": 128001, + "transformers_version": "4.57.6" +} diff --git a/last-checkpoint/README.md b/last-checkpoint/README.md new file mode 100644 index 0000000..bacf84a --- /dev/null +++ b/last-checkpoint/README.md @@ -0,0 +1,207 @@ +--- +base_model: biaofu-xmu/EAST-8B +library_name: peft +pipeline_tag: text-generation +tags: +- base_model:adapter:biaofu-xmu/EAST-8B +- lora +- transformers +--- + +# Model Card for Model ID + + + + + +## Model Details + +### Model Description + + + + + +- **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] + + + +- **Repository:** [More Information Needed] +- **Paper [optional]:** [More Information Needed] +- **Demo [optional]:** [More Information Needed] + +## Uses + + + +### Direct Use + + + +[More Information Needed] + +### Downstream Use [optional] + + + +[More Information Needed] + +### Out-of-Scope Use + + + +[More Information Needed] + +## Bias, Risks, and Limitations + + + +[More Information Needed] + +### Recommendations + + + +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 + + + +[More Information Needed] + +### Training Procedure + + + +#### Preprocessing [optional] + +[More Information Needed] + + +#### Training Hyperparameters + +- **Training regime:** [More Information Needed] + +#### Speeds, Sizes, Times [optional] + + + +[More Information Needed] + +## Evaluation + + + +### Testing Data, Factors & Metrics + +#### Testing Data + + + +[More Information Needed] + +#### Factors + + + +[More Information Needed] + +#### Metrics + + + +[More Information Needed] + +### Results + +[More Information Needed] + +#### Summary + + + +## Model Examination [optional] + + + +[More Information Needed] + +## Environmental Impact + + + +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] + + + +**BibTeX:** + +[More Information Needed] + +**APA:** + +[More Information Needed] + +## Glossary [optional] + + + +[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 0.19.1 \ No newline at end of file diff --git a/last-checkpoint/adapter_config.json b/last-checkpoint/adapter_config.json new file mode 100644 index 0000000..25ed829 --- /dev/null +++ b/last-checkpoint/adapter_config.json @@ -0,0 +1,48 @@ +{ + "alora_invocation_tokens": null, + "alpha_pattern": {}, + "arrow_config": null, + "auto_mapping": null, + "base_model_name_or_path": "biaofu-xmu/EAST-8B", + "bias": "none", + "corda_config": null, + "ensure_weight_tying": false, + "eva_config": null, + "exclude_modules": null, + "fan_in_fan_out": false, + "inference_mode": true, + "init_lora_weights": true, + "layer_replication": null, + "layers_pattern": null, + "layers_to_transform": null, + "loftq_config": {}, + "lora_alpha": 128, + "lora_bias": false, + "lora_dropout": 0.05, + "lora_ga_config": null, + "megatron_config": null, + "megatron_core": "megatron.core", + "modules_to_save": null, + "peft_type": "LORA", + "peft_version": "0.19.1", + "qalora_group_size": 16, + "r": 64, + "rank_pattern": {}, + "revision": null, + "target_modules": [ + "o_proj", + "down_proj", + "gate_proj", + "up_proj", + "v_proj", + "k_proj", + "q_proj" + ], + "target_parameters": null, + "task_type": "CAUSAL_LM", + "trainable_token_indices": null, + "use_bdlora": null, + "use_dora": false, + "use_qalora": false, + "use_rslora": false +} \ No newline at end of file diff --git a/last-checkpoint/adapter_model.safetensors b/last-checkpoint/adapter_model.safetensors new file mode 100644 index 0000000..616cf76 --- /dev/null +++ b/last-checkpoint/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4e750594165491d27182ef42fe92c6feb72b82c04069cca03dd2d8f04a2606e +size 671149168 diff --git a/last-checkpoint/optimizer.pt b/last-checkpoint/optimizer.pt new file mode 100644 index 0000000..6fdc4fe --- /dev/null +++ b/last-checkpoint/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0002b660110e7b2699a3fa0feac5e8efa2b49bccd3370b49c7850fe981be7580 +size 1342562339 diff --git a/last-checkpoint/rng_state.pth b/last-checkpoint/rng_state.pth new file mode 100644 index 0000000..75071b5 --- /dev/null +++ b/last-checkpoint/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4eb04a9a627e830bdc88791995ecedb7cdd156fcc5757d95562154800b116fd2 +size 14645 diff --git a/last-checkpoint/scheduler.pt b/last-checkpoint/scheduler.pt new file mode 100644 index 0000000..d432e90 --- /dev/null +++ b/last-checkpoint/scheduler.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28b81089eb143a676da720978f118caf9eee0a372736c9ef6f38cdec3dd8d997 +size 1465 diff --git a/last-checkpoint/trainer_state.json b/last-checkpoint/trainer_state.json new file mode 100644 index 0000000..5447597 --- /dev/null +++ b/last-checkpoint/trainer_state.json @@ -0,0 +1,433 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.9965277777777777, + "eval_steps": 500, + "global_step": 1150, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.034722222222222224, + "grad_norm": 2.4707443714141846, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5661, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.0097849369049072, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3797, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9553152322769165, + "learning_rate": 5.086206896551724e-06, + "loss": 2.241, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.8024173974990845, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0635, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.215123176574707, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9409, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.2895090579986572, + "learning_rate": 9.999793100349294e-06, + "loss": 1.9394, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.780405044555664, + "learning_rate": 9.987843743451796e-06, + "loss": 1.8307, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.183285713195801, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7575, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.269092082977295, + "learning_rate": 9.909033799150947e-06, + "loss": 1.8066, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.379218578338623, + "learning_rate": 9.842463004902127e-06, + "loss": 1.7141, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.7214298248291016, + "learning_rate": 9.758085921836076e-06, + "loss": 1.71, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.449744462966919, + "learning_rate": 9.656212814111567e-06, + "loss": 1.7129, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 3.360551118850708, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6855, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 3.03425669670105, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6934, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 3.087336301803589, + "learning_rate": 9.249676511588e-06, + "loss": 1.6952, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.6650753021240234, + "learning_rate": 9.082186599639429e-06, + "loss": 1.6734, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.713989496231079, + "learning_rate": 8.899686021935554e-06, + "loss": 1.6516, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.6662213802337646, + "learning_rate": 8.702845853917242e-06, + "loss": 1.6282, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.6345484256744385, + "learning_rate": 8.492389899334572e-06, + "loss": 1.6137, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 2.9651432037353516, + "learning_rate": 8.269092028737885e-06, + "loss": 1.6086, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.811237335205078, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5801, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.8691394329071045, + "learning_rate": 7.78729910840572e-06, + "loss": 1.5673, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 2.8986737728118896, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5777, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.5703928470611572, + "learning_rate": 7.26454700860997e-06, + "loss": 1.5584, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.996887445449829, + "learning_rate": 6.990191353373876e-06, + "loss": 1.5649, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.5608773231506348, + "learning_rate": 6.708517537523264e-06, + "loss": 1.518, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.395473003387451, + "learning_rate": 6.420561307807713e-06, + "loss": 1.5457, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 2.847874164581299, + "learning_rate": 6.12738151212918e-06, + "loss": 1.5655, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.7648465633392334, + "learning_rate": 5.830056206037482e-06, + "loss": 1.5093, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.106715440750122, + "learning_rate": 5.529678688597081e-06, + "loss": 1.4521, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.3356199264526367, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.461, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.7472050189971924, + "learning_rate": 4.924192271119554e-06, + "loss": 1.4325, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0159659385681152, + "learning_rate": 4.621309813703385e-06, + "loss": 1.44, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.520766258239746, + "learning_rate": 4.319819843296952e-06, + "loss": 1.4462, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.7417140007019043, + "learning_rate": 4.020830972910433e-06, + "loss": 1.4551, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.331568479537964, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.4033, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.6196417808532715, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.4319, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.271605491638184, + "learning_rate": 3.149794932132331e-06, + "loss": 1.4318, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.33790922164917, + "learning_rate": 2.871652321931161e-06, + "loss": 1.4123, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9214086532592773, + "learning_rate": 2.601335888909005e-06, + "loss": 1.4245, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 3.770592212677002, + "learning_rate": 2.339839617423318e-06, + "loss": 1.3763, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.762789726257324, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.4043, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.8584647178649902, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.4174, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.3003017902374268, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.3779, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.60571551322937, + "learning_rate": 1.40072737599522e-06, + "loss": 1.4303, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.2599637508392334, + "learning_rate": 1.196985645464921e-06, + "loss": 1.3981, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.389312267303467, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.3968, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.148715972900391, + "learning_rate": 8.321522974916968e-07, + "loss": 1.422, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.725743770599365, + "learning_rate": 6.724022138834341e-07, + "loss": 1.3997, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.287371873855591, + "learning_rate": 5.285652009556075e-07, + "loss": 1.3733, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.199480056762695, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.3904, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 3.8616933822631836, + "learning_rate": 2.906855485332305e-07, + "loss": 1.3662, + "step": 1040 + }, + { + "epoch": 1.8402777777777777, + "grad_norm": 3.60861873626709, + "learning_rate": 1.975176196540185e-07, + "loss": 1.3885, + "step": 1060 + }, + { + "epoch": 1.875, + "grad_norm": 4.208493709564209, + "learning_rate": 1.2200896627521718e-07, + "loss": 1.3956, + "step": 1080 + }, + { + "epoch": 1.9097222222222223, + "grad_norm": 3.6999189853668213, + "learning_rate": 6.443724232808146e-08, + "loss": 1.3784, + "step": 1100 + }, + { + "epoch": 1.9444444444444444, + "grad_norm": 5.089156627655029, + "learning_rate": 2.501414560839577e-08, + "loss": 1.3576, + "step": 1120 + }, + { + "epoch": 1.9791666666666665, + "grad_norm": 3.6565749645233154, + "learning_rate": 3.884639339534202e-09, + "loss": 1.37, + "step": 1140 + } + ], + "logging_steps": 20, + "max_steps": 1152, + "num_input_tokens_seen": 0, + "num_train_epochs": 2, + "save_steps": 50, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": false + }, + "attributes": {} + } + }, + "total_flos": 2.2986760990910054e+17, + "train_batch_size": 4, + "trial_name": null, + "trial_params": null +} diff --git a/last-checkpoint/training_args.bin b/last-checkpoint/training_args.bin new file mode 100644 index 0000000..ea08f40 --- /dev/null +++ b/last-checkpoint/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102a13affd8ac871acf39042cd8fde0b6a32b5f1e572e375a7f24c7c91e4b55a +size 6033 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..dac9426 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38722ca692aa807290b7c44d8d97085e4bba4d9b0d9f427e2b2b721351b4dd2d +size 4977222960 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..559741e --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b302895dd7ae448801baf74b221ff93223bbd80ade3b2a7ecab7a8d49f83237 +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..093bd6c --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9946bc209d126442999cfecdffd198a7a890d269d9b4c84d63994c138423496 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..a5bdccd --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccea180f40991bbca8e0c1e173933d4df2b41474f51161ca1d19d4096536a33d +size 1168663096 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..55f36a5 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,299 @@ +{ + "metadata": { + "total_parameters": 8030785536, + "total_size": 16061571072 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00001-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..6631bbf --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,27 @@ +{ + "additional_special_tokens": [ + "<|end-of-read|>", + "<|end-of-write|>" + ], + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..ccae08e --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edc01071ea813bba1c85943ccabb16dbd408ba02c9bd781dffc66467be8be3c3 +size 17209138 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..31003a7 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2085 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_248|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_249|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_250|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128256": { + "content": "<|end-of-read|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128257": { + "content": "<|end-of-write|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "<|end-of-read|>", + "<|end-of-write|>" + ], + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 1000000000000000019884624838656, + "pad_token": "<|eot_id|>", + "padding_side": "left", + "split_special_tokens": false, + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/training_args.bin b/training_args.bin new file mode 100644 index 0000000..ea08f40 --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:102a13affd8ac871acf39042cd8fde0b6a32b5f1e572e375a7f24c7c91e4b55a +size 6033