commit ffed210379f9ab159eb07911246ef77eb7422d69 Author: ModelHub XC Date: Thu Aug 20 14:19:18 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: Henry236/east8b-eg-lora-chunk-nilechat 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..6296c9b --- /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": [ + "gate_proj", + "k_proj", + "v_proj", + "up_proj", + "o_proj", + "q_proj", + "down_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..015217b --- /dev/null +++ b/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0384e2e4ad8025532613b260338bc9bac2742d835b96a8afadd067464b380e8f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..67addcb --- /dev/null +++ b/checkpoint-100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdabc906ae05aca8e3e2088f3522a76d91c9faa5533fd41f2c78303bed5cc78 +size 671149168 diff --git a/checkpoint-100/optimizer.pt b/checkpoint-100/optimizer.pt new file mode 100644 index 0000000..12f6fc1 --- /dev/null +++ b/checkpoint-100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd87b71b2e0b9fc12ad10db17ddc958a4541aed139dc814f2cc717f839f7522 +size 1342562339 diff --git a/checkpoint-100/rng_state.pth b/checkpoint-100/rng_state.pth new file mode 100644 index 0000000..21b2a23 --- /dev/null +++ b/checkpoint-100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecf7e046b5c99f06c4c8dbb77b5d7c2bffee07cf1db92bb2492cd71d381999ee +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..da6ff4b --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "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": 2.0245746786729984e+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..8b3a117 --- /dev/null +++ b/checkpoint-100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..5f1ab1f --- /dev/null +++ b/checkpoint-1000/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad65d5535fba017b404c661ac118b43f1adf0e8807560d87e557b0da78de1893 +size 671149168 diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt new file mode 100644 index 0000000..811e517 --- /dev/null +++ b/checkpoint-1000/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a5c54ca1641ca2d87ca9b7f4adae94cef4c36085cfa8c88fe712c6c63c1fc8 +size 1342562339 diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth new file mode 100644 index 0000000..1ad2950 --- /dev/null +++ b/checkpoint-1000/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4278cc0831892e457e06f3e444bd09705f94015bac952b8f63418271ac030aae +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..ea4100f --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.05021858215332, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2859, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 4.1063079833984375, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2947, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.8521957397460938, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3056, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.304344415664673, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2695, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.73410701751709, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3125, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.594968318939209, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2841, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.417556285858154, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2878, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.227901935577393, + "learning_rate": 8.321522974916968e-07, + "loss": 1.305, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.219496250152588, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2707, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.437847375869751, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2692, + "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": 2.0301452468895744e+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..8b3a117 --- /dev/null +++ b/checkpoint-1000/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..6a6ba78 --- /dev/null +++ b/checkpoint-1050/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:172c58608d9fe304a8f655a720fcd5744917b538403a0cf3ca1d06f12a5c6ca0 +size 671149168 diff --git a/checkpoint-1050/optimizer.pt b/checkpoint-1050/optimizer.pt new file mode 100644 index 0000000..1beabf3 --- /dev/null +++ b/checkpoint-1050/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb187972b2931ec73ca1488ef9f584402175f146b6127992e481e1f88027c97b +size 1342562339 diff --git a/checkpoint-1050/rng_state.pth b/checkpoint-1050/rng_state.pth new file mode 100644 index 0000000..e77f0b9 --- /dev/null +++ b/checkpoint-1050/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ac019a846822765c1550361ac4e771fa37c17cc9ec699e4a74864748ac0405f +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..0c9c100 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.05021858215332, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2859, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 4.1063079833984375, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2947, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.8521957397460938, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3056, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.304344415664673, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2695, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.73410701751709, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3125, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.594968318939209, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2841, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.417556285858154, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2878, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.227901935577393, + "learning_rate": 8.321522974916968e-07, + "loss": 1.305, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.219496250152588, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2707, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.437847375869751, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2692, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.303681373596191, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.2737, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 4.166017532348633, + "learning_rate": 2.906855485332305e-07, + "loss": 1.25, + "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": 2.1323582680006656e+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..8b3a117 --- /dev/null +++ b/checkpoint-1050/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..e79b1af --- /dev/null +++ b/checkpoint-1100/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d96543476b08e4eb62d71b04d4f777a1d4b03192f3143c6567a7adb72f25ffc1 +size 671149168 diff --git a/checkpoint-1100/optimizer.pt b/checkpoint-1100/optimizer.pt new file mode 100644 index 0000000..d786a9d --- /dev/null +++ b/checkpoint-1100/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb9414c47cfbc2fe7ed123d34ff7f059e77b2857280fa737ce639978485d964 +size 1342562339 diff --git a/checkpoint-1100/rng_state.pth b/checkpoint-1100/rng_state.pth new file mode 100644 index 0000000..baa3702 --- /dev/null +++ b/checkpoint-1100/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cf163052b7c8fe1a57ad4f4852615ab8eee4f151df31b7e92c5ee06a95da6b1 +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..115bb98 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.05021858215332, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2859, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 4.1063079833984375, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2947, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.8521957397460938, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3056, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.304344415664673, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2695, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.73410701751709, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3125, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.594968318939209, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2841, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.417556285858154, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2878, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.227901935577393, + "learning_rate": 8.321522974916968e-07, + "loss": 1.305, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.219496250152588, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2707, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.437847375869751, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2692, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.303681373596191, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.2737, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 4.166017532348633, + "learning_rate": 2.906855485332305e-07, + "loss": 1.25, + "step": 1040 + }, + { + "epoch": 1.8402777777777777, + "grad_norm": 3.7296154499053955, + "learning_rate": 1.975176196540185e-07, + "loss": 1.2739, + "step": 1060 + }, + { + "epoch": 1.875, + "grad_norm": 4.139808654785156, + "learning_rate": 1.2200896627521718e-07, + "loss": 1.2893, + "step": 1080 + }, + { + "epoch": 1.9097222222222223, + "grad_norm": 3.9217822551727295, + "learning_rate": 6.443724232808146e-08, + "loss": 1.2558, + "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": 2.2324590769648435e+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..8b3a117 --- /dev/null +++ b/checkpoint-1100/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..3c9c19f --- /dev/null +++ b/checkpoint-1150/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b501920d99dbb3c3c3213b877fbd5e3b3b8b16e293eaefb6fc97680bb459594a +size 671149168 diff --git a/checkpoint-1150/optimizer.pt b/checkpoint-1150/optimizer.pt new file mode 100644 index 0000000..fc03364 --- /dev/null +++ b/checkpoint-1150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f06270876bb57ae9f47380bdbf8dac3269554a8df8d073214f1b5d49afea4eb +size 1342562339 diff --git a/checkpoint-1150/rng_state.pth b/checkpoint-1150/rng_state.pth new file mode 100644 index 0000000..3b1eee4 --- /dev/null +++ b/checkpoint-1150/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:343714913f998eccbc8cb136e02926cb492b399a62fe6e8d95391c5456fde9fd +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..01fea00 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.05021858215332, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2859, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 4.1063079833984375, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2947, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.8521957397460938, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3056, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.304344415664673, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2695, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.73410701751709, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3125, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.594968318939209, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2841, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.417556285858154, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2878, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.227901935577393, + "learning_rate": 8.321522974916968e-07, + "loss": 1.305, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.219496250152588, + "learning_rate": 6.724022138834341e-07, + "loss": 1.2707, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.437847375869751, + "learning_rate": 5.285652009556075e-07, + "loss": 1.2692, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.303681373596191, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.2737, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 4.166017532348633, + "learning_rate": 2.906855485332305e-07, + "loss": 1.25, + "step": 1040 + }, + { + "epoch": 1.8402777777777777, + "grad_norm": 3.7296154499053955, + "learning_rate": 1.975176196540185e-07, + "loss": 1.2739, + "step": 1060 + }, + { + "epoch": 1.875, + "grad_norm": 4.139808654785156, + "learning_rate": 1.2200896627521718e-07, + "loss": 1.2893, + "step": 1080 + }, + { + "epoch": 1.9097222222222223, + "grad_norm": 3.9217822551727295, + "learning_rate": 6.443724232808146e-08, + "loss": 1.2558, + "step": 1100 + }, + { + "epoch": 1.9444444444444444, + "grad_norm": 4.743123531341553, + "learning_rate": 2.501414560839577e-08, + "loss": 1.2425, + "step": 1120 + }, + { + "epoch": 1.9791666666666665, + "grad_norm": 3.773953914642334, + "learning_rate": 3.884639339534202e-09, + "loss": 1.2672, + "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": 2.3346113282408448e+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..8b3a117 --- /dev/null +++ b/checkpoint-1150/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..b29c8b3 --- /dev/null +++ b/checkpoint-150/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0897df63f0df2caecc3c70b588e92ed35cfd0114e6e27d62d2c126936863129e +size 671149168 diff --git a/checkpoint-150/optimizer.pt b/checkpoint-150/optimizer.pt new file mode 100644 index 0000000..02f154f --- /dev/null +++ b/checkpoint-150/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5ad50bc7713cbc192692422748d9524ea675db4b68cf4758b16767939bd18f7 +size 1342562339 diff --git a/checkpoint-150/rng_state.pth b/checkpoint-150/rng_state.pth new file mode 100644 index 0000000..e2cfbce --- /dev/null +++ b/checkpoint-150/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10f31c644c2d511c761b5bd2c8684f0f912aec2103790ef57a54a08b8f096fa0 +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..650f1e0 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "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": 3.036042545990861e+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..8b3a117 --- /dev/null +++ b/checkpoint-150/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..942cbd8 --- /dev/null +++ b/checkpoint-200/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7abfa66030147aa0fe79d035104fbe78832cf964244fecea8245c35f4cfdf3d2 +size 671149168 diff --git a/checkpoint-200/optimizer.pt b/checkpoint-200/optimizer.pt new file mode 100644 index 0000000..36a5f21 --- /dev/null +++ b/checkpoint-200/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f307072335a43afcf42af433cb09d7bdefd880ffa1b6480338223448cd059fe +size 1342562339 diff --git a/checkpoint-200/rng_state.pth b/checkpoint-200/rng_state.pth new file mode 100644 index 0000000..8ccdb04 --- /dev/null +++ b/checkpoint-200/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3151996a186da03e4c8625aa7f0249a788b27e975e6bf0cb629deb9cb88ba461 +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..5e1f6e1 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "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": 4.06966378046423e+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..8b3a117 --- /dev/null +++ b/checkpoint-200/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..3745211 --- /dev/null +++ b/checkpoint-250/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731536ffeb885f97904c273b371cac6b2eddc2b051d048c19ddd8f5e06fcd83f +size 671149168 diff --git a/checkpoint-250/optimizer.pt b/checkpoint-250/optimizer.pt new file mode 100644 index 0000000..6dcde2e --- /dev/null +++ b/checkpoint-250/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1de18f1098206d304c2e9e07f4927ca3994559c65c01bd8ec9e0f979201001ed +size 1342562339 diff --git a/checkpoint-250/rng_state.pth b/checkpoint-250/rng_state.pth new file mode 100644 index 0000000..898a624 --- /dev/null +++ b/checkpoint-250/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c031523b0980faf8edd373e82ee5dc3f8288a80c8a568acac8e6cf4d092b86e5 +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..044a763 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "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": 5.081978742453043e+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..8b3a117 --- /dev/null +++ b/checkpoint-250/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..c7de240 --- /dev/null +++ b/checkpoint-300/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bb7e452e1d676bb7d4e209dfdc28b554fad740e42fda13ff78e86b0ab4f3d39 +size 671149168 diff --git a/checkpoint-300/optimizer.pt b/checkpoint-300/optimizer.pt new file mode 100644 index 0000000..65d6275 --- /dev/null +++ b/checkpoint-300/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6621085fe286d89148020abc3913d26baf56b155272592de852923e37b9f4347 +size 1342562339 diff --git a/checkpoint-300/rng_state.pth b/checkpoint-300/rng_state.pth new file mode 100644 index 0000000..8b3362c --- /dev/null +++ b/checkpoint-300/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bc2fe4ee96d58ba6b266dc96e2302937c506f638eecc5aededcda6fd229ff7 +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..43172ee --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "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": 6.083391964328755e+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..8b3a117 --- /dev/null +++ b/checkpoint-300/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..b6f119e --- /dev/null +++ b/checkpoint-350/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b0bd364dec64af366ebb1c36f9b8cf13de195a029dd763e459716cd8b8c94df +size 671149168 diff --git a/checkpoint-350/optimizer.pt b/checkpoint-350/optimizer.pt new file mode 100644 index 0000000..4f3c8d9 --- /dev/null +++ b/checkpoint-350/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5278ab79115164e58644b6a50ffc9a940b1bae987a55b0087e935b16180813b +size 1342562339 diff --git a/checkpoint-350/rng_state.pth b/checkpoint-350/rng_state.pth new file mode 100644 index 0000000..3bb3c18 --- /dev/null +++ b/checkpoint-350/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb35f8c0b6073305f53c45f10e720934126c019098b502ffb71b91fc13c32f56 +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..fbd5616 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "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": 7.084179072752026e+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..8b3a117 --- /dev/null +++ b/checkpoint-350/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..ffdf60d --- /dev/null +++ b/checkpoint-400/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb52e3e2982303126409f001c7437a14712867a443f87896af5866999b093751 +size 671149168 diff --git a/checkpoint-400/optimizer.pt b/checkpoint-400/optimizer.pt new file mode 100644 index 0000000..dc6f8e9 --- /dev/null +++ b/checkpoint-400/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4193bb650e5fc9c7a8f7834df6905ab330fb597ea2e4bce38d682ad395ad6fe1 +size 1342562339 diff --git a/checkpoint-400/rng_state.pth b/checkpoint-400/rng_state.pth new file mode 100644 index 0000000..6b16aac --- /dev/null +++ b/checkpoint-400/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:235eea77d85f83e0e1c97f22edbdf217f18c45fd382d67f20ee2ee2b43a0b34b +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..b7dea3d --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "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": 8.095260222937498e+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..8b3a117 --- /dev/null +++ b/checkpoint-400/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..60a0dee --- /dev/null +++ b/checkpoint-450/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fc2e97d1ddd03239f34b06abba0028f4348595595a71981c1d0a87c4832b1ca +size 671149168 diff --git a/checkpoint-450/optimizer.pt b/checkpoint-450/optimizer.pt new file mode 100644 index 0000000..bde41d7 --- /dev/null +++ b/checkpoint-450/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9293a378e805d2e1f137e91cdaafcfbc26a1f1cf34e72ba46c0f24bc8d0b058 +size 1342562339 diff --git a/checkpoint-450/rng_state.pth b/checkpoint-450/rng_state.pth new file mode 100644 index 0000000..d82343a --- /dev/null +++ b/checkpoint-450/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1f2cfdb5f12710a509fd8ba1350dff75febd348c1956e80478d900d68c2fc3 +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..2a2a1a9 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "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": 9.108551185308058e+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..8b3a117 --- /dev/null +++ b/checkpoint-450/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..4ee9645 --- /dev/null +++ b/checkpoint-50/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da4b25104ff522006d753e0b6c701e99867d8ffe3ce0df70f012ec465e20a56a +size 671149168 diff --git a/checkpoint-50/optimizer.pt b/checkpoint-50/optimizer.pt new file mode 100644 index 0000000..a0e8955 --- /dev/null +++ b/checkpoint-50/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7041c3eafc65e8a2f731944c274912dbe1df455946ee9cae9aa61d10a14c7d9 +size 1342562339 diff --git a/checkpoint-50/rng_state.pth b/checkpoint-50/rng_state.pth new file mode 100644 index 0000000..19684aa --- /dev/null +++ b/checkpoint-50/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6701bb6a5f8dee189f8865b4a12b90ebec07664aed9c76b7abd0eec52a19e5 +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..ce4ed31 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "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": 1.0042491475132416e+16, + "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..8b3a117 --- /dev/null +++ b/checkpoint-50/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..51cbe90 --- /dev/null +++ b/checkpoint-500/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e65c01b177ce61bd77b4bed70c3dbf1bbe98a3e80e9dfc60b9b3b690a250b678 +size 671149168 diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt new file mode 100644 index 0000000..21a3306 --- /dev/null +++ b/checkpoint-500/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8b93dbc3a2dc9fb305d9106187ad05385288f2bee606c80216bd312156e840 +size 1342562339 diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth new file mode 100644 index 0000000..e4f716e --- /dev/null +++ b/checkpoint-500/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c111be700bd625ddd4031d7545b334b5fd65295c7a4c8f8d8c6be4a072cd520b +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..3d66e37 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "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": 1.0155339217384243e+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..8b3a117 --- /dev/null +++ b/checkpoint-500/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..635a514 --- /dev/null +++ b/checkpoint-550/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ecccfce1d111872f2f7719a9320ca622f27f55a71240523747a2421edc6633d +size 671149168 diff --git a/checkpoint-550/optimizer.pt b/checkpoint-550/optimizer.pt new file mode 100644 index 0000000..ac617db --- /dev/null +++ b/checkpoint-550/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d395b93b4002c991087756c7843091ac40f10ed3af5c7ab3ceb3f9ae396d349 +size 1342562339 diff --git a/checkpoint-550/rng_state.pth b/checkpoint-550/rng_state.pth new file mode 100644 index 0000000..aa87a30 --- /dev/null +++ b/checkpoint-550/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20cac53312687e07976490e175da77d65ce8cd1241a3ca51e5f8de32a19eca68 +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..3b0cbef --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "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": 1.1179789731289498e+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..8b3a117 --- /dev/null +++ b/checkpoint-550/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..111b8ce --- /dev/null +++ b/checkpoint-600/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cbe76ea09ea22d27e1ae52a3735c1f4fa7eb2be388ef3dbb7e655ca3cf5d2d1 +size 671149168 diff --git a/checkpoint-600/optimizer.pt b/checkpoint-600/optimizer.pt new file mode 100644 index 0000000..698703c --- /dev/null +++ b/checkpoint-600/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a28937592c4e4b94d3643ed29c2fff33c75a3e1ad22f84026e6ad1cf4cd665 +size 1342562339 diff --git a/checkpoint-600/rng_state.pth b/checkpoint-600/rng_state.pth new file mode 100644 index 0000000..d008ab9 --- /dev/null +++ b/checkpoint-600/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea8fb47b6727a889f793c21bdd18554c8f82a41b1c65800ddcff55e6b284b2a9 +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..f9beaac --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "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": 1.21838915579904e+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..8b3a117 --- /dev/null +++ b/checkpoint-600/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..638696e --- /dev/null +++ b/checkpoint-650/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbb766355b8018b21ad9e355531ac8e2b894641c5ede4b89a4da9a35c2acf0bb +size 671149168 diff --git a/checkpoint-650/optimizer.pt b/checkpoint-650/optimizer.pt new file mode 100644 index 0000000..1d389c2 --- /dev/null +++ b/checkpoint-650/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b46114ae3b9cef66c16be2946c7b4e43ffecbb443900efe36a6cf8be13e8485 +size 1342562339 diff --git a/checkpoint-650/rng_state.pth b/checkpoint-650/rng_state.pth new file mode 100644 index 0000000..8b5f6fe --- /dev/null +++ b/checkpoint-650/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bc5157a3be03bd39e08a3125945225f4325ec78ff122d957f95b82c3036aa31 +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..65d552b --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "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": 1.3181032476308275e+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..8b3a117 --- /dev/null +++ b/checkpoint-650/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..cd4997d --- /dev/null +++ b/checkpoint-700/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9092156affdd909e21c3983be49f53592c232fa8f750696e88df9679eb4a990 +size 671149168 diff --git a/checkpoint-700/optimizer.pt b/checkpoint-700/optimizer.pt new file mode 100644 index 0000000..30f00f2 --- /dev/null +++ b/checkpoint-700/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8403e26f62a0b9b05b1f046b39464593c7018a18097af28623bd5d910c189d97 +size 1342562339 diff --git a/checkpoint-700/rng_state.pth b/checkpoint-700/rng_state.pth new file mode 100644 index 0000000..297323d --- /dev/null +++ b/checkpoint-700/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94fd6aca0688ff615ab1a312ba24c78e00370ffc243ff45eff813e558fc4da31 +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..b622b46 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "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": 1.4182593018996326e+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..8b3a117 --- /dev/null +++ b/checkpoint-700/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..c41ef9e --- /dev/null +++ b/checkpoint-750/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7697a042ea6ca82edbc7430406a2a96b05491538bf2d92b82f9837af83498e0 +size 671149168 diff --git a/checkpoint-750/optimizer.pt b/checkpoint-750/optimizer.pt new file mode 100644 index 0000000..f8afafb --- /dev/null +++ b/checkpoint-750/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afff8bb22272245293401f0ba5f78f78cddb3d4959ffbd9028c1624462e6154e +size 1342562339 diff --git a/checkpoint-750/rng_state.pth b/checkpoint-750/rng_state.pth new file mode 100644 index 0000000..7efbf63 --- /dev/null +++ b/checkpoint-750/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb3dd9f50e8e8f4479cfbd8d4af91b1c99a46b9ca50e344852d776865320bbdd +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..47bf9f0 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "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": 1.5214299082909286e+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..8b3a117 --- /dev/null +++ b/checkpoint-750/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..e070cf9 --- /dev/null +++ b/checkpoint-800/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e5d55b269bcb46c12cef3e088059c08e25c0118541a48547b3203e9463dfba8 +size 671149168 diff --git a/checkpoint-800/optimizer.pt b/checkpoint-800/optimizer.pt new file mode 100644 index 0000000..d25b542 --- /dev/null +++ b/checkpoint-800/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae39930dc504ae044dc581cc83afd032ceb4ab63614864e9042330e55a496770 +size 1342562339 diff --git a/checkpoint-800/rng_state.pth b/checkpoint-800/rng_state.pth new file mode 100644 index 0000000..65c9c62 --- /dev/null +++ b/checkpoint-800/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8887cd46d707ab5821e2d9ee31dfb6c3acf198828cd4dcc53e7b36435d59d73a +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..307dcf2 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "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": 1.6239302049860813e+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..8b3a117 --- /dev/null +++ b/checkpoint-800/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..5b96350 --- /dev/null +++ b/checkpoint-850/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eaeee94e82343c62ca411ae026df3d887c1763791aba8c272fc97b3523793fd +size 671149168 diff --git a/checkpoint-850/optimizer.pt b/checkpoint-850/optimizer.pt new file mode 100644 index 0000000..dd1a37c --- /dev/null +++ b/checkpoint-850/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff3043827a6abbcfa59b939a0ce6954aa64205d0468e4f847ead4e9ed74b74b +size 1342562339 diff --git a/checkpoint-850/rng_state.pth b/checkpoint-850/rng_state.pth new file mode 100644 index 0000000..0a6dbe1 --- /dev/null +++ b/checkpoint-850/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86df9ab8127b3b8a1504a2a4baf4c93bb15544c8b7216e1b9387a03ccc1964ef +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..a0a9a78 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.05021858215332, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2859, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 4.1063079833984375, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2947, + "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": 1.7272076189663232e+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..8b3a117 --- /dev/null +++ b/checkpoint-850/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..3656424 --- /dev/null +++ b/checkpoint-900/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ad11b6be738802493c532a3bd719c0a64f972c6d5cff3a356c51a8125ea776b +size 671149168 diff --git a/checkpoint-900/optimizer.pt b/checkpoint-900/optimizer.pt new file mode 100644 index 0000000..4e620d4 --- /dev/null +++ b/checkpoint-900/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e32ede118e77506117d0f1536e15a9c390421d948bbcb8b8d5359cff81876ff +size 1342562339 diff --git a/checkpoint-900/rng_state.pth b/checkpoint-900/rng_state.pth new file mode 100644 index 0000000..c4e7b7f --- /dev/null +++ b/checkpoint-900/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9924cd6f76d8e7f84b2c2dad6817477419ecb7441d19b8afa48c9446541171a9 +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..29ca0bf --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.05021858215332, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2859, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 4.1063079833984375, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2947, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.8521957397460938, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3056, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.304344415664673, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2695, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.73410701751709, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3125, + "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": 1.8281960358248448e+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..8b3a117 --- /dev/null +++ b/checkpoint-900/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..89e1d81 --- /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": [ + "q_proj", + "k_proj", + "up_proj", + "down_proj", + "v_proj", + "o_proj", + "gate_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..a350c90 --- /dev/null +++ b/checkpoint-950/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d712e33dfebc881ecd9d8322dad86566e819e8c2f0131a0a48b13a128707b47f +size 671149168 diff --git a/checkpoint-950/optimizer.pt b/checkpoint-950/optimizer.pt new file mode 100644 index 0000000..8e9f0a8 --- /dev/null +++ b/checkpoint-950/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e144467aef98051260254e53d4361a6e8e9391de619eb0cb93b3b811e81c679b +size 1342562339 diff --git a/checkpoint-950/rng_state.pth b/checkpoint-950/rng_state.pth new file mode 100644 index 0000000..5c05bef --- /dev/null +++ b/checkpoint-950/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9291f97af333b74f5afd5c98c44f35c52472647dd78c4ead34f8a02e9480b928 +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..e395400 --- /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": 3.1068832874298096, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.675, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.46288800239563, + "learning_rate": 3.362068965517242e-06, + "loss": 2.4759, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 2.1140520572662354, + "learning_rate": 5.086206896551724e-06, + "loss": 2.3011, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.9008077383041382, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0724, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.368029832839966, + "learning_rate": 8.53448275862069e-06, + "loss": 1.9312, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.3201775550842285, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8941, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.499159812927246, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7747, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.1269280910491943, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7052, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.290123224258423, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7429, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3117945194244385, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6598, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.6141538619995117, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6429, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4996819496154785, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6566, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.8781185150146484, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6255, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.8994524478912354, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6064, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.9606640338897705, + "learning_rate": 9.249676511588e-06, + "loss": 1.6141, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 2.9091055393218994, + "learning_rate": 9.082186599639429e-06, + "loss": 1.598, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.523542642593384, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5779, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.5727219581604004, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5475, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.4910247325897217, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5346, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.080043077468872, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5282, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 3.0990397930145264, + "learning_rate": 8.033773333867498e-06, + "loss": 1.4993, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7828781604766846, + "learning_rate": 7.78729910840572e-06, + "loss": 1.4994, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.1256909370422363, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5023, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.1738061904907227, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4671, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.4600017070770264, + "learning_rate": 6.990191353373876e-06, + "loss": 1.466, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.556324005126953, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4407, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.1536033153533936, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4485, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 3.01642107963562, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4672, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.864258050918579, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4258, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 2.967533826828003, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3619, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.2055039405822754, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.3592, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.8909292221069336, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3359, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 3.0267176628112793, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3424, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.415727138519287, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3435, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.6791961193084717, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3391, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.3228704929351807, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3054, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.616981267929077, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.312, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.216521739959717, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3334, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.408073425292969, + "learning_rate": 2.871652321931161e-06, + "loss": 1.317, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.9930851459503174, + "learning_rate": 2.601335888909005e-06, + "loss": 1.3089, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 4.05021858215332, + "learning_rate": 2.339839617423318e-06, + "loss": 1.2859, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 4.1063079833984375, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.2947, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.8521957397460938, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3056, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.304344415664673, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.2695, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.73410701751709, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3125, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.594968318939209, + "learning_rate": 1.196985645464921e-06, + "loss": 1.2841, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.417556285858154, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.2878, + "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": 1.9311640760991744e+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..8b3a117 --- /dev/null +++ b/checkpoint-950/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b7a49036ffa878b9a140914bd9c626a64799b3d62685205c325df45890d951f +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..6296c9b --- /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": [ + "gate_proj", + "k_proj", + "v_proj", + "up_proj", + "o_proj", + "q_proj", + "down_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..015217b --- /dev/null +++ b/last-checkpoint/adapter_model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0384e2e4ad8025532613b260338bc9bac2742d835b96a8afadd067464b380e8f +size 671149168 diff --git a/last-checkpoint/optimizer.pt b/last-checkpoint/optimizer.pt new file mode 100644 index 0000000..4a8d97d --- /dev/null +++ b/last-checkpoint/optimizer.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecaa1169d420793d5fcdf1973256b8c8b018a778447c396ed07f99320683bae8 +size 1342562339 diff --git a/last-checkpoint/rng_state.pth b/last-checkpoint/rng_state.pth new file mode 100644 index 0000000..a705019 --- /dev/null +++ b/last-checkpoint/rng_state.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0651173aaf98aa036913f324c7701d6ff94f31fb68dba0b9b12a4499798b10a9 +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..39e9cc5 --- /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": 2.54878306388855, + "learning_rate": 1.6379310344827587e-06, + "loss": 2.5199, + "step": 20 + }, + { + "epoch": 0.06944444444444445, + "grad_norm": 2.2638280391693115, + "learning_rate": 3.362068965517242e-06, + "loss": 2.3584, + "step": 40 + }, + { + "epoch": 0.10416666666666667, + "grad_norm": 1.9315502643585205, + "learning_rate": 5.086206896551724e-06, + "loss": 2.1832, + "step": 60 + }, + { + "epoch": 0.1388888888888889, + "grad_norm": 1.7287458181381226, + "learning_rate": 6.810344827586207e-06, + "loss": 2.0124, + "step": 80 + }, + { + "epoch": 0.1736111111111111, + "grad_norm": 2.1096012592315674, + "learning_rate": 8.53448275862069e-06, + "loss": 1.8975, + "step": 100 + }, + { + "epoch": 0.20833333333333334, + "grad_norm": 2.182361125946045, + "learning_rate": 9.999793100349294e-06, + "loss": 1.8837, + "step": 120 + }, + { + "epoch": 0.24305555555555555, + "grad_norm": 2.6428465843200684, + "learning_rate": 9.987843743451796e-06, + "loss": 1.7797, + "step": 140 + }, + { + "epoch": 0.2777777777777778, + "grad_norm": 2.0262956619262695, + "learning_rate": 9.957553516178782e-06, + "loss": 1.7065, + "step": 160 + }, + { + "epoch": 0.3125, + "grad_norm": 2.2093276977539062, + "learning_rate": 9.909033799150947e-06, + "loss": 1.7603, + "step": 180 + }, + { + "epoch": 0.3472222222222222, + "grad_norm": 2.3105509281158447, + "learning_rate": 9.842463004902127e-06, + "loss": 1.6663, + "step": 200 + }, + { + "epoch": 0.3819444444444444, + "grad_norm": 2.660855770111084, + "learning_rate": 9.758085921836076e-06, + "loss": 1.6556, + "step": 220 + }, + { + "epoch": 0.4166666666666667, + "grad_norm": 2.4641621112823486, + "learning_rate": 9.656212814111567e-06, + "loss": 1.6587, + "step": 240 + }, + { + "epoch": 0.4513888888888889, + "grad_norm": 2.65177583694458, + "learning_rate": 9.53721828076571e-06, + "loss": 1.6424, + "step": 260 + }, + { + "epoch": 0.4861111111111111, + "grad_norm": 2.779574394226074, + "learning_rate": 9.401539878270545e-06, + "loss": 1.6302, + "step": 280 + }, + { + "epoch": 0.5208333333333334, + "grad_norm": 2.8638408184051514, + "learning_rate": 9.249676511588e-06, + "loss": 1.6312, + "step": 300 + }, + { + "epoch": 0.5555555555555556, + "grad_norm": 3.208831787109375, + "learning_rate": 9.082186599639429e-06, + "loss": 1.6097, + "step": 320 + }, + { + "epoch": 0.5902777777777778, + "grad_norm": 2.5734481811523438, + "learning_rate": 8.899686021935554e-06, + "loss": 1.5967, + "step": 340 + }, + { + "epoch": 0.625, + "grad_norm": 2.6115477085113525, + "learning_rate": 8.702845853917242e-06, + "loss": 1.5803, + "step": 360 + }, + { + "epoch": 0.6597222222222222, + "grad_norm": 2.46243953704834, + "learning_rate": 8.492389899334572e-06, + "loss": 1.5576, + "step": 380 + }, + { + "epoch": 0.6944444444444444, + "grad_norm": 3.08601975440979, + "learning_rate": 8.269092028737885e-06, + "loss": 1.5434, + "step": 400 + }, + { + "epoch": 0.7291666666666666, + "grad_norm": 2.877305030822754, + "learning_rate": 8.033773333867498e-06, + "loss": 1.5266, + "step": 420 + }, + { + "epoch": 0.7638888888888888, + "grad_norm": 2.7357547283172607, + "learning_rate": 7.78729910840572e-06, + "loss": 1.518, + "step": 440 + }, + { + "epoch": 0.7986111111111112, + "grad_norm": 3.0699241161346436, + "learning_rate": 7.530575666193283e-06, + "loss": 1.5126, + "step": 460 + }, + { + "epoch": 0.8333333333333334, + "grad_norm": 3.164865255355835, + "learning_rate": 7.26454700860997e-06, + "loss": 1.4973, + "step": 480 + }, + { + "epoch": 0.8680555555555556, + "grad_norm": 3.363128662109375, + "learning_rate": 6.990191353373876e-06, + "loss": 1.504, + "step": 500 + }, + { + "epoch": 0.9027777777777778, + "grad_norm": 3.5045032501220703, + "learning_rate": 6.708517537523264e-06, + "loss": 1.4595, + "step": 520 + }, + { + "epoch": 0.9375, + "grad_norm": 3.302361488342285, + "learning_rate": 6.420561307807713e-06, + "loss": 1.4815, + "step": 540 + }, + { + "epoch": 0.9722222222222222, + "grad_norm": 2.9132392406463623, + "learning_rate": 6.12738151212918e-06, + "loss": 1.4925, + "step": 560 + }, + { + "epoch": 1.0069444444444444, + "grad_norm": 3.870426654815674, + "learning_rate": 5.830056206037482e-06, + "loss": 1.4602, + "step": 580 + }, + { + "epoch": 1.0416666666666667, + "grad_norm": 3.9702446460723877, + "learning_rate": 5.529678688597081e-06, + "loss": 1.3977, + "step": 600 + }, + { + "epoch": 1.0763888888888888, + "grad_norm": 3.6180670261383057, + "learning_rate": 5.2273534822017105e-06, + "loss": 1.4009, + "step": 620 + }, + { + "epoch": 1.1111111111111112, + "grad_norm": 3.728706121444702, + "learning_rate": 4.924192271119554e-06, + "loss": 1.3649, + "step": 640 + }, + { + "epoch": 1.1458333333333333, + "grad_norm": 2.9779577255249023, + "learning_rate": 4.621309813703385e-06, + "loss": 1.3779, + "step": 660 + }, + { + "epoch": 1.1805555555555556, + "grad_norm": 4.165585517883301, + "learning_rate": 4.319819843296952e-06, + "loss": 1.3897, + "step": 680 + }, + { + "epoch": 1.2152777777777777, + "grad_norm": 3.635356903076172, + "learning_rate": 4.020830972910433e-06, + "loss": 1.3946, + "step": 700 + }, + { + "epoch": 1.25, + "grad_norm": 3.2752726078033447, + "learning_rate": 3.7254426187239567e-06, + "loss": 1.3435, + "step": 720 + }, + { + "epoch": 1.2847222222222223, + "grad_norm": 3.6443591117858887, + "learning_rate": 3.4347409574088896e-06, + "loss": 1.3629, + "step": 740 + }, + { + "epoch": 1.3194444444444444, + "grad_norm": 4.365672588348389, + "learning_rate": 3.149794932132331e-06, + "loss": 1.3711, + "step": 760 + }, + { + "epoch": 1.3541666666666667, + "grad_norm": 4.400868892669678, + "learning_rate": 2.871652321931161e-06, + "loss": 1.347, + "step": 780 + }, + { + "epoch": 1.3888888888888888, + "grad_norm": 2.929353713989258, + "learning_rate": 2.601335888909005e-06, + "loss": 1.358, + "step": 800 + }, + { + "epoch": 1.4236111111111112, + "grad_norm": 3.9870338439941406, + "learning_rate": 2.339839617423318e-06, + "loss": 1.3254, + "step": 820 + }, + { + "epoch": 1.4583333333333333, + "grad_norm": 3.580916404724121, + "learning_rate": 2.0881250590915316e-06, + "loss": 1.3363, + "step": 840 + }, + { + "epoch": 1.4930555555555556, + "grad_norm": 3.867156505584717, + "learning_rate": 1.8471177970560712e-06, + "loss": 1.3519, + "step": 860 + }, + { + "epoch": 1.5277777777777777, + "grad_norm": 3.1973142623901367, + "learning_rate": 1.6177040425095664e-06, + "loss": 1.3078, + "step": 880 + }, + { + "epoch": 1.5625, + "grad_norm": 3.530712604522705, + "learning_rate": 1.40072737599522e-06, + "loss": 1.3631, + "step": 900 + }, + { + "epoch": 1.5972222222222223, + "grad_norm": 3.1694910526275635, + "learning_rate": 1.196985645464921e-06, + "loss": 1.3391, + "step": 920 + }, + { + "epoch": 1.6319444444444444, + "grad_norm": 4.059397220611572, + "learning_rate": 1.0072280325013185e-06, + "loss": 1.3277, + "step": 940 + }, + { + "epoch": 1.6666666666666665, + "grad_norm": 4.044768810272217, + "learning_rate": 8.321522974916968e-07, + "loss": 1.3542, + "step": 960 + }, + { + "epoch": 1.7013888888888888, + "grad_norm": 4.220571994781494, + "learning_rate": 6.724022138834341e-07, + "loss": 1.3201, + "step": 980 + }, + { + "epoch": 1.7361111111111112, + "grad_norm": 3.351271390914917, + "learning_rate": 5.285652009556075e-07, + "loss": 1.3154, + "step": 1000 + }, + { + "epoch": 1.7708333333333335, + "grad_norm": 4.178652286529541, + "learning_rate": 4.0117016381130636e-07, + "loss": 1.3207, + "step": 1020 + }, + { + "epoch": 1.8055555555555556, + "grad_norm": 4.209657669067383, + "learning_rate": 2.906855485332305e-07, + "loss": 1.293, + "step": 1040 + }, + { + "epoch": 1.8402777777777777, + "grad_norm": 3.878786563873291, + "learning_rate": 1.975176196540185e-07, + "loss": 1.3221, + "step": 1060 + }, + { + "epoch": 1.875, + "grad_norm": 3.886103868484497, + "learning_rate": 1.2200896627521718e-07, + "loss": 1.3304, + "step": 1080 + }, + { + "epoch": 1.9097222222222223, + "grad_norm": 3.7067108154296875, + "learning_rate": 6.443724232808146e-08, + "loss": 1.3055, + "step": 1100 + }, + { + "epoch": 1.9444444444444444, + "grad_norm": 4.1525983810424805, + "learning_rate": 2.501414560839577e-08, + "loss": 1.2896, + "step": 1120 + }, + { + "epoch": 1.9791666666666665, + "grad_norm": 3.4590396881103516, + "learning_rate": 3.884639339534202e-09, + "loss": 1.3044, + "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": 2.3329226634294067e+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..6c2d13b --- /dev/null +++ b/last-checkpoint/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:310c1f2cb78984f98d19821c929435f62970616e8f03bda114499f414070bac5 +size 6033 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..5251ced --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a220cd297907b7fbd7e7e36e5fe0298d2282bf4ace764cddc4994831a9cb0b +size 4977222960 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..7f3081a --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:779e83edc56ebd098de56e28ddfa65fa9fb9cdbb9bce1e27e868bdf32c82d55f +size 4999802720 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..5689dbd --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:982fa4bab4542f3318900f250de34cbf2e6d93809b22e523ede3fcde0ca1b968 +size 4915916176 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..80915b6 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d29dcfb2a2801cb0ed319e86e19051e84e3533396a34dc5031bfe6a79b53185 +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..6c2d13b --- /dev/null +++ b/training_args.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:310c1f2cb78984f98d19821c929435f62970616e8f03bda114499f414070bac5 +size 6033