Upload Agentic-V4

README.md

@@ -0,0 +1,202 @@
+---
+base_model: Nexusflow/Athene-V2-Agent
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Nexusflow/Athene-V2-Agent",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_dropout": 0.2,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [],
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6534f304ad85cc7d48e281715fd82923fd15a5432fdb6fcb625b1c4f82abdc3f
+size 356581280

additional_config.json

@@ -0,0 +1 @@
+{"lora_dtype": null, "lorap_lr_ratio": null, "lorap_emb_lr": 1e-06}

configuration.json

@@ -0,0 +1,11 @@
+{
+    "adapter_cfg": {
+        "model_id_or_path": "/root/dataDisk/ms-swift/models",
+        "model_revision": "master",
+        "sft_type": "lora",
+        "tuner_backend": "peft",
+        "template_type": "qwen2_5",
+        "dtype": "bf16",
+        "system": ""
+    }
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "transformers_version": "4.46.3"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba9f4df36b64eee4d5f4db32a3ce052e7935fe817f4d209e5108da05bf5fbdad
+size 713436530

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575119a228f98110923ffa2dedcb50e3317251b26054355d015e0b2240d566f2
+size 15984

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc091d2c64e295da198fc50a521da2b2e71efaede488211abd625b6121c779b1
+size 15920

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b1a976c61366775f17b2f4ed938a496722f9b6544db424f2d3f492fcf2b4b9d
+size 1064

sft_args.json

@@ -0,0 +1,275 @@
+{
+  "model_type": "qwen2_5-72b-instruct",
+  "model_id_or_path": "/root/dataDisk/ms-swift/models",
+  "model_revision": "master",
+  "full_determinism": false,
+  "sft_type": "lora",
+  "freeze_parameters": [],
+  "freeze_vit": false,
+  "freeze_parameters_ratio": 0.0,
+  "additional_trainable_parameters": [],
+  "tuner_backend": "peft",
+  "template_type": "qwen2_5",
+  "output_dir": "/root/dataDisk/ms-swift/new_train/qwen2_5-72b-instruct/v7-20241210-142056",
+  "add_output_dir_suffix": true,
+  "ddp_backend": "nccl",
+  "ddp_find_unused_parameters": null,
+  "ddp_broadcast_buffers": null,
+  "ddp_timeout": 1800,
+  "seed": 42,
+  "resume_from_checkpoint": null,
+  "resume_only_model": false,
+  "ignore_data_skip": false,
+  "dtype": "bf16",
+  "packing": false,
+  "train_backend": "transformers",
+  "tp": 1,
+  "pp": 1,
+  "min_lr": null,
+  "sequence_parallel": false,
+  "model_kwargs": {},
+  "loss_name": null,
+  "dataset": [
+    "merged_data.jsonl"
+  ],
+  "val_dataset": [],
+  "dataset_seed": 42,
+  "dataset_test_ratio": 0.01,
+  "use_loss_scale": false,
+  "loss_scale_config_path": "/root/dataDisk/.venv/lib/python3.12/site-packages/swift/llm/agent/default_loss_scale_config.json",
+  "system": "",
+  "tools_prompt": "react_en",
+  "max_length": 15000,
+  "truncation_strategy": "delete",
+  "check_dataset_strategy": "none",
+  "streaming": false,
+  "streaming_val_size": 0,
+  "streaming_buffer_size": 16384,
+  "model_name": [
+    null,
+    null
+  ],
+  "model_author": [
+    null,
+    null
+  ],
+  "quant_method": null,
+  "quantization_bit": 0,
+  "hqq_axis": 0,
+  "hqq_dynamic_config_path": null,
+  "bnb_4bit_comp_dtype": "bf16",
+  "bnb_4bit_quant_type": "nf4",
+  "bnb_4bit_use_double_quant": true,
+  "bnb_4bit_quant_storage": null,
+  "rescale_image": -1,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_regex": null,
+  "modules_to_save": [],
+  "lora_rank": 32,
+  "lora_alpha": 64,
+  "lora_dropout": 0.2,
+  "lora_bias_trainable": "none",
+  "lora_dtype": null,
+  "lora_lr_ratio": null,
+  "use_rslora": false,
+  "use_dora": false,
+  "init_lora_weights": true,
+  "fourier_n_frequency": 2000,
+  "fourier_scaling": 300.0,
+  "rope_scaling": null,
+  "boft_block_size": 4,
+  "boft_block_num": 0,
+  "boft_n_butterfly_factor": 1,
+  "boft_dropout": 0.0,
+  "vera_rank": 256,
+  "vera_projection_prng_key": 0,
+  "vera_dropout": 0.0,
+  "vera_d_initial": 0.1,
+  "adapter_act": "gelu",
+  "adapter_length": 128,
+  "use_galore": false,
+  "galore_target_modules": null,
+  "galore_rank": 128,
+  "galore_update_proj_gap": 50,
+  "galore_scale": 1.0,
+  "galore_proj_type": "std",
+  "galore_optim_per_parameter": false,
+  "galore_with_embedding": false,
+  "galore_quantization": false,
+  "galore_proj_quant": false,
+  "galore_proj_bits": 4,
+  "galore_proj_group_size": 256,
+  "galore_cos_threshold": 0.4,
+  "galore_gamma_proj": 2,
+  "galore_queue_size": 5,
+  "adalora_target_r": 8,
+  "adalora_init_r": 12,
+  "adalora_tinit": 0,
+  "adalora_tfinal": 0,
+  "adalora_deltaT": 1,
+  "adalora_beta1": 0.85,
+  "adalora_beta2": 0.85,
+  "adalora_orth_reg_weight": 0.5,
+  "ia3_feedforward_modules": [],
+  "llamapro_num_new_blocks": 4,
+  "llamapro_num_groups": null,
+  "neftune_noise_alpha": null,
+  "neftune_backend": "transformers",
+  "lisa_activated_layers": 0,
+  "lisa_step_interval": 20,
+  "reft_layer_key": null,
+  "reft_layers": null,
+  "reft_rank": 4,
+  "reft_intervention_type": "LoreftIntervention",
+  "reft_args": null,
+  "use_liger": false,
+  "gradient_checkpointing": true,
+  "vit_use_gc": true,
+  "deepspeed": null,
+  "batch_size": 1,
+  "eval_batch_size": 1,
+  "auto_find_batch_size": false,
+  "num_train_epochs": 1,
+  "max_steps": -1,
+  "optim": "adamw_torch",
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.95,
+  "adam_epsilon": 1e-08,
+  "learning_rate": 0.0003,
+  "weight_decay": 0.01,
+  "gradient_accumulation_steps": 8,
+  "max_grad_norm": 1,
+  "predict_with_generate": false,
+  "lr_scheduler_type": "cosine",
+  "lr_scheduler_kwargs": {},
+  "warmup_ratio": 0.1,
+  "warmup_steps": 0,
+  "eval_steps": 50,
+  "save_steps": 10,
+  "save_only_model": false,
+  "save_total_limit": 5,
+  "logging_steps": 1,
+  "acc_steps": 1,
+  "dataloader_num_workers": 1,
+  "dataloader_pin_memory": true,
+  "dataloader_drop_last": false,
+  "push_to_hub": false,
+  "hub_model_id": null,
+  "hub_token": null,
+  "hub_private_repo": false,
+  "hub_strategy": "every_save",
+  "test_oom_error": false,
+  "disable_tqdm": false,
+  "lazy_tokenize": false,
+  "preprocess_num_proc": 1,
+  "use_flash_attn": null,
+  "ignore_args_error": false,
+  "check_model_is_latest": true,
+  "logging_dir": "/root/dataDisk/ms-swift/new_train/qwen2_5-72b-instruct/v7-20241210-142056/runs",
+  "report_to": [
+    "all"
+  ],
+  "acc_strategy": "token",
+  "save_on_each_node": false,
+  "evaluation_strategy": "steps",
+  "save_strategy": "steps",
+  "save_safetensors": true,
+  "gpu_memory_fraction": null,
+  "include_num_input_tokens_seen": false,
+  "local_repo_path": null,
+  "custom_register_path": null,
+  "custom_dataset_info": null,
+  "device_map_config": null,
+  "device_max_memory": [],
+  "max_new_tokens": 2048,
+  "do_sample": null,
+  "temperature": null,
+  "top_k": null,
+  "top_p": null,
+  "repetition_penalty": null,
+  "num_beams": 1,
+  "fsdp": "",
+  "fsdp_config": null,
+  "sequence_parallel_size": 1,
+  "model_layer_cls_name": null,
+  "metric_warmup_step": 0,
+  "fsdp_num": 1,
+  "per_device_train_batch_size": null,
+  "per_device_eval_batch_size": null,
+  "eval_strategy": null,
+  "self_cognition_sample": 0,
+  "train_dataset_mix_ratio": 0.0,
+  "train_dataset_mix_ds": [
+    "ms-bench"
+  ],
+  "train_dataset_sample": -1,
+  "val_dataset_sample": null,
+  "safe_serialization": null,
+  "only_save_model": null,
+  "neftune_alpha": null,
+  "deepspeed_config_path": null,
+  "model_cache_dir": null,
+  "lora_dropout_p": null,
+  "lora_target_modules": [],
+  "lora_target_regex": null,
+  "lora_modules_to_save": [],
+  "boft_target_modules": [],
+  "boft_modules_to_save": [],
+  "vera_target_modules": [],
+  "vera_modules_to_save": [],
+  "ia3_target_modules": [],
+  "ia3_modules_to_save": [],
+  "custom_train_dataset_path": [],
+  "custom_val_dataset_path": [],
+  "device_map_config_path": null,
+  "push_hub_strategy": null,
+  "rlhf_type": "orpo",
+  "ref_model_type": null,
+  "ref_model_id_or_path": null,
+  "ref_model_revision": null,
+  "beta": 0.1,
+  "label_smoothing": 0.0,
+  "loss_type": null,
+  "rpo_alpha": 1.0,
+  "cpo_alpha": 1.0,
+  "simpo_gamma": 1,
+  "desirable_weight": 1.0,
+  "undesirable_weight": 1.0,
+  "reward_model_id_or_path": null,
+  "reward_model_type": null,
+  "reward_model_revision": null,
+  "local_rollout_forward_batch_size": 64,
+  "whiten_rewards": false,
+  "kl_coef": 0.05,
+  "cliprange": 0.2,
+  "vf_coef": 0.1,
+  "cliprange_value": 0.2,
+  "gamma": 1.0,
+  "lam": 0.95,
+  "num_sample_generations": 10,
+  "ref_model_free": true,
+  "use_self_cognition": false,
+  "is_multimodal": false,
+  "is_vision": false,
+  "lora_use_embedding": false,
+  "lora_use_all": false,
+  "lora_m2s_use_embedding": false,
+  "lora_m2s_use_ln": false,
+  "torch_dtype": "torch.bfloat16",
+  "fp16": false,
+  "bf16": true,
+  "rank": 0,
+  "local_rank": 0,
+  "world_size": 2,
+  "local_world_size": 2,
+  "bnb_4bit_compute_dtype": "torch.bfloat16",
+  "load_in_4bit": false,
+  "load_in_8bit": false,
+  "train_sampler_random": true,
+  "train_type": "orpo",
+  "training_args": "ORPOConfig(output_dir='/root/dataDisk/ms-swift/new_train/qwen2_5-72b-instruct/v7-20241210-142056', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=1, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=8, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0003, weight_decay=0.01, adam_beta1=0.9, adam_beta2=0.95, adam_epsilon=1e-08, max_grad_norm=1, num_train_epochs=1, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs={}, warmup_ratio=0.1, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/dataDisk/ms-swift/new_train/qwen2_5-72b-instruct/v7-20241210-142056/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=1, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=10, save_total_limit=5, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend='nccl', tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=50, dataloader_num_workers=1, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/dataDisk/ms-swift/new_train/qwen2_5-72b-instruct/v7-20241210-142056', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard', 'wandb'], ddp_find_unused_parameters=False, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=False, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy=None, push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=False, include_num_input_tokens_seen=False, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=False, max_length=None, max_prompt_length=None, max_completion_length=None, beta=0.1, disable_dropout=True, label_pad_token_id=-100, padding_value=None, truncation_mode='keep_end', generate_during_eval=False, is_encoder_decoder=None, model_init_kwargs=None, dataset_num_proc=None, acc_strategy='token', loss_name=None, additional_saved_files=[], train_sampler_random=True, metric_warmup_step=0, train_dataset_sample=-1)"
+}

trainer_state.json

@@ -0,0 +1,433 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.060836501901140684,
+  "eval_steps": 50,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003041825095057034,
+      "grad_norm": 0.2263541966676712,
+      "learning_rate": 9.090909090909091e-06,
+      "log_odds_chosen": 0.0022868067026138306,
+      "log_odds_ratio": -0.6926867961883545,
+      "logits/chosen": -2.233539581298828,
+      "logits/rejected": -2.2098608016967773,
+      "logps/chosen": -0.7675836682319641,
+      "logps/rejected": -0.7697547078132629,
+      "loss": 0.85230005,
+      "memory(GiB)": 243.33,
+      "nll_loss": 0.7675836682319641,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.07675836980342865,
+      "rewards/margins": 0.00021709827706217766,
+      "rewards/rejected": -0.07697547227144241,
+      "step": 1,
+      "train_speed(iter/s)": 0.010532
+    },
+    {
+      "epoch": 0.006083650190114068,
+      "grad_norm": 0.21064028143882751,
+      "learning_rate": 1.8181818181818182e-05,
+      "log_odds_chosen": 0.411478191614151,
+      "log_odds_ratio": -0.5463609099388123,
+      "logits/chosen": -2.2685160636901855,
+      "logits/rejected": -2.260843515396118,
+      "logps/chosen": -0.9355340003967285,
+      "logps/rejected": -1.236234188079834,
+      "loss": 0.87318134,
+      "memory(GiB)": 243.33,
+      "nll_loss": 0.9355340003967285,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.09355340152978897,
+      "rewards/margins": 0.030070019885897636,
+      "rewards/rejected": -0.12362341582775116,
+      "step": 2,
+      "train_speed(iter/s)": 0.009734
+    },
+    {
+      "epoch": 0.009125475285171103,
+      "grad_norm": 0.19250068068504333,
+      "learning_rate": 2.727272727272727e-05,
+      "log_odds_chosen": 0.3938485383987427,
+      "log_odds_ratio": -0.5777455568313599,
+      "logits/chosen": -1.993510365486145,
+      "logits/rejected": -1.9485821723937988,
+      "logps/chosen": -0.6979267001152039,
+      "logps/rejected": -0.9728450775146484,
+      "loss": 0.75437951,
+      "memory(GiB)": 243.33,
+      "nll_loss": 0.6979267597198486,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.06979266554117203,
+      "rewards/margins": 0.027491841465234756,
+      "rewards/rejected": -0.09728450328111649,
+      "step": 3,
+      "train_speed(iter/s)": 0.01152
+    },
+    {
+      "epoch": 0.012167300380228136,
+      "grad_norm": 0.20081621408462524,
+      "learning_rate": 3.6363636363636364e-05,
+      "log_odds_chosen": 0.0849333107471466,
+      "log_odds_ratio": -0.6586424112319946,
+      "logits/chosen": -2.3017446994781494,
+      "logits/rejected": -2.300307512283325,
+      "logps/chosen": -0.7535954713821411,
+      "logps/rejected": -0.8145345449447632,
+      "loss": 0.85012603,
+      "memory(GiB)": 315.51,
+      "nll_loss": 0.7535954713821411,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.0753595381975174,
+      "rewards/margins": 0.006093906704336405,
+      "rewards/rejected": -0.08145345002412796,
+      "step": 4,
+      "train_speed(iter/s)": 0.011285
+    },
+    {
+      "epoch": 0.015209125475285171,
+      "grad_norm": 0.20968054234981537,
+      "learning_rate": 4.545454545454545e-05,
+      "log_odds_chosen": 0.2265796959400177,
+      "log_odds_ratio": -0.605457067489624,
+      "logits/chosen": -2.132286548614502,
+      "logits/rejected": -2.0954604148864746,
+      "logps/chosen": -0.7475967407226562,
+      "logps/rejected": -0.9037913680076599,
+      "loss": 0.83076566,
+      "memory(GiB)": 349.51,
+      "nll_loss": 0.747596800327301,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.07475967705249786,
+      "rewards/margins": 0.015619462355971336,
+      "rewards/rejected": -0.09037913382053375,
+      "step": 5,
+      "train_speed(iter/s)": 0.01019
+    },
+    {
+      "epoch": 0.018250950570342206,
+      "grad_norm": 0.28389012813568115,
+      "learning_rate": 5.454545454545454e-05,
+      "log_odds_chosen": 0.07245179265737534,
+      "log_odds_ratio": -0.6642654538154602,
+      "logits/chosen": -2.207275867462158,
+      "logits/rejected": -2.194154977798462,
+      "logps/chosen": -0.7644542455673218,
+      "logps/rejected": -0.811606228351593,
+      "loss": 0.80996728,
+      "memory(GiB)": 304.24,
+      "nll_loss": 0.7644542455673218,
+      "rewards/accuracies": 0.625,
+      "rewards/chosen": -0.07644543051719666,
+      "rewards/margins": 0.004715194460004568,
+      "rewards/rejected": -0.08116061985492706,
+      "step": 6,
+      "train_speed(iter/s)": 0.010519
+    },
+    {
+      "epoch": 0.02129277566539924,
+      "grad_norm": 0.2204827517271042,
+      "learning_rate": 6.363636363636363e-05,
+      "log_odds_chosen": 0.0014549940824508667,
+      "log_odds_ratio": -0.6934571266174316,
+      "logits/chosen": -2.2422585487365723,
+      "logits/rejected": -2.2558586597442627,
+      "logps/chosen": -0.7055240869522095,
+      "logps/rejected": -0.7079155445098877,
+      "loss": 0.80136919,
+      "memory(GiB)": 376.14,
+      "nll_loss": 0.7055240869522095,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": -0.07055240869522095,
+      "rewards/margins": 0.0002391412854194641,
+      "rewards/rejected": -0.07079154998064041,
+      "step": 7,
+      "train_speed(iter/s)": 0.010453
+    },
+    {
+      "epoch": 0.024334600760456272,
+      "grad_norm": 0.18603529036045074,
+      "learning_rate": 7.272727272727273e-05,
+      "log_odds_chosen": 0.2205890268087387,
+      "log_odds_ratio": -0.6130101084709167,
+      "logits/chosen": -2.1775014400482178,
+      "logits/rejected": -2.1533212661743164,
+      "logps/chosen": -0.6938110589981079,
+      "logps/rejected": -0.8382289409637451,
+      "loss": 0.73867655,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.6938109993934631,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.06938110291957855,
+      "rewards/margins": 0.01444179005920887,
+      "rewards/rejected": -0.08382289111614227,
+      "step": 8,
+      "train_speed(iter/s)": 0.010026
+    },
+    {
+      "epoch": 0.02737642585551331,
+      "grad_norm": 0.2093774527311325,
+      "learning_rate": 8.18181818181818e-05,
+      "log_odds_chosen": 0.28880590200424194,
+      "log_odds_ratio": -0.5970734357833862,
+      "logits/chosen": -2.231719970703125,
+      "logits/rejected": -2.1949002742767334,
+      "logps/chosen": -0.6275652647018433,
+      "logps/rejected": -0.8133708834648132,
+      "loss": 0.73195064,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.627565324306488,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.06275652348995209,
+      "rewards/margins": 0.018580568954348564,
+      "rewards/rejected": -0.0813370943069458,
+      "step": 9,
+      "train_speed(iter/s)": 0.010471
+    },
+    {
+      "epoch": 0.030418250950570342,
+      "grad_norm": 0.17292404174804688,
+      "learning_rate": 9.09090909090909e-05,
+      "log_odds_chosen": 0.1367553025484085,
+      "log_odds_ratio": -0.6314333081245422,
+      "logits/chosen": -2.193378448486328,
+      "logits/rejected": -2.2005226612091064,
+      "logps/chosen": -0.712138831615448,
+      "logps/rejected": -0.7979795932769775,
+      "loss": 0.72619164,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.7121387720108032,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.07121387869119644,
+      "rewards/margins": 0.00858408585190773,
+      "rewards/rejected": -0.07979796826839447,
+      "step": 10,
+      "train_speed(iter/s)": 0.010603
+    },
+    {
+      "epoch": 0.033460076045627375,
+      "grad_norm": 0.18145819008350372,
+      "learning_rate": 9.999999999999999e-05,
+      "log_odds_chosen": 0.39647987484931946,
+      "log_odds_ratio": -0.5509629249572754,
+      "logits/chosen": -1.9035614728927612,
+      "logits/rejected": -1.8070275783538818,
+      "logps/chosen": -0.6602268218994141,
+      "logps/rejected": -0.9264889359474182,
+      "loss": 0.63924813,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.6602268218994141,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.06602267920970917,
+      "rewards/margins": 0.026626210659742355,
+      "rewards/rejected": -0.09264889359474182,
+      "step": 11,
+      "train_speed(iter/s)": 0.011075
+    },
+    {
+      "epoch": 0.03650190114068441,
+      "grad_norm": 0.1996176391839981,
+      "learning_rate": 0.00010909090909090908,
+      "log_odds_chosen": -0.008832626044750214,
+      "log_odds_ratio": -0.6989511251449585,
+      "logits/chosen": -2.1484761238098145,
+      "logits/rejected": -2.1583542823791504,
+      "logps/chosen": -0.5783950686454773,
+      "logps/rejected": -0.5806748867034912,
+      "loss": 0.66453189,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.5783950686454773,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.05783950537443161,
+      "rewards/margins": 0.0002279849722981453,
+      "rewards/rejected": -0.05806749314069748,
+      "step": 12,
+      "train_speed(iter/s)": 0.011198
+    },
+    {
+      "epoch": 0.03954372623574144,
+      "grad_norm": 0.18517741560935974,
+      "learning_rate": 0.00011818181818181817,
+      "log_odds_chosen": 0.1502607762813568,
+      "log_odds_ratio": -0.6237398386001587,
+      "logits/chosen": -2.078707695007324,
+      "logits/rejected": -2.0867443084716797,
+      "logps/chosen": -0.6652951240539551,
+      "logps/rejected": -0.7532068490982056,
+      "loss": 0.71045852,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.6652951240539551,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.0665295198559761,
+      "rewards/margins": 0.008791167289018631,
+      "rewards/rejected": -0.07532068341970444,
+      "step": 13,
+      "train_speed(iter/s)": 0.011144
+    },
+    {
+      "epoch": 0.04258555133079848,
+      "grad_norm": 0.460842102766037,
+      "learning_rate": 0.00012727272727272725,
+      "log_odds_chosen": 0.08848065137863159,
+      "log_odds_ratio": -0.6523964405059814,
+      "logits/chosen": -2.0903429985046387,
+      "logits/rejected": -2.071244716644287,
+      "logps/chosen": -0.5602254867553711,
+      "logps/rejected": -0.6098269820213318,
+      "loss": 0.62673962,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.5602255463600159,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.05602255091071129,
+      "rewards/margins": 0.004960143007338047,
+      "rewards/rejected": -0.06098269298672676,
+      "step": 14,
+      "train_speed(iter/s)": 0.011223
+    },
+    {
+      "epoch": 0.045627376425855515,
+      "grad_norm": 0.201682448387146,
+      "learning_rate": 0.00013636363636363634,
+      "log_odds_chosen": 0.0586659274995327,
+      "log_odds_ratio": -0.6654743552207947,
+      "logits/chosen": -2.460188388824463,
+      "logits/rejected": -2.4563236236572266,
+      "logps/chosen": -0.3543914556503296,
+      "logps/rejected": -0.3674345910549164,
+      "loss": 0.49967062,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.3543914258480072,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.0354391448199749,
+      "rewards/margins": 0.0013043158687651157,
+      "rewards/rejected": -0.03674346208572388,
+      "step": 15,
+      "train_speed(iter/s)": 0.011535
+    },
+    {
+      "epoch": 0.048669201520912544,
+      "grad_norm": 0.20425710082054138,
+      "learning_rate": 0.00014545454545454546,
+      "log_odds_chosen": 0.06445352733135223,
+      "log_odds_ratio": -0.6619336009025574,
+      "logits/chosen": -1.9317834377288818,
+      "logits/rejected": -1.9417508840560913,
+      "logps/chosen": -0.5264174938201904,
+      "logps/rejected": -0.5525864958763123,
+      "loss": 0.62982225,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.5264174938201904,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.05264175310730934,
+      "rewards/margins": 0.0026168967597186565,
+      "rewards/rejected": -0.055258650332689285,
+      "step": 16,
+      "train_speed(iter/s)": 0.011487
+    },
+    {
+      "epoch": 0.05171102661596958,
+      "grad_norm": 0.19479066133499146,
+      "learning_rate": 0.00015454545454545452,
+      "log_odds_chosen": 0.05428645759820938,
+      "log_odds_ratio": -0.6680891513824463,
+      "logits/chosen": -2.0513648986816406,
+      "logits/rejected": -2.0547256469726562,
+      "logps/chosen": -0.5574195384979248,
+      "logps/rejected": -0.5769228935241699,
+      "loss": 0.65339994,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.5574195384979248,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.05574195832014084,
+      "rewards/margins": 0.001950339414179325,
+      "rewards/rejected": -0.05769229307770729,
+      "step": 17,
+      "train_speed(iter/s)": 0.011193
+    },
+    {
+      "epoch": 0.05475285171102662,
+      "grad_norm": 0.20096692442893982,
+      "learning_rate": 0.0001636363636363636,
+      "log_odds_chosen": 0.11649945378303528,
+      "log_odds_ratio": -0.6375795006752014,
+      "logits/chosen": -1.979109764099121,
+      "logits/rejected": -1.9783812761306763,
+      "logps/chosen": -0.6062220335006714,
+      "logps/rejected": -0.6605215072631836,
+      "loss": 0.61762023,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.6062220931053162,
+      "rewards/accuracies": 0.875,
+      "rewards/chosen": -0.0606222040951252,
+      "rewards/margins": 0.005429944489151239,
+      "rewards/rejected": -0.06605214625597,
+      "step": 18,
+      "train_speed(iter/s)": 0.010973
+    },
+    {
+      "epoch": 0.05779467680608365,
+      "grad_norm": 0.22299402952194214,
+      "learning_rate": 0.00017272727272727272,
+      "log_odds_chosen": 0.275879442691803,
+      "log_odds_ratio": -0.5872041583061218,
+      "logits/chosen": -1.7563273906707764,
+      "logits/rejected": -1.7962664365768433,
+      "logps/chosen": -0.5380970239639282,
+      "logps/rejected": -0.7168144583702087,
+      "loss": 0.62556648,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.5380970239639282,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.05380970239639282,
+      "rewards/margins": 0.017871743068099022,
+      "rewards/rejected": -0.071681447327137,
+      "step": 19,
+      "train_speed(iter/s)": 0.010995
+    },
+    {
+      "epoch": 0.060836501901140684,
+      "grad_norm": 0.19399508833885193,
+      "learning_rate": 0.0001818181818181818,
+      "log_odds_chosen": -0.016166899353265762,
+      "log_odds_ratio": -0.702415943145752,
+      "logits/chosen": -2.1521270275115967,
+      "logits/rejected": -2.151902914047241,
+      "logps/chosen": -0.41145703196525574,
+      "logps/rejected": -0.4066007733345032,
+      "loss": 0.49458012,
+      "memory(GiB)": 337.96,
+      "nll_loss": 0.41145703196525574,
+      "rewards/accuracies": 0.375,
+      "rewards/chosen": -0.041145700961351395,
+      "rewards/margins": -0.000485624885186553,
+      "rewards/rejected": -0.040660079568624496,
+      "step": 20,
+      "train_speed(iter/s)": 0.011065
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 328,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.570806552906957e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474087e8f80a856e73387c2f5cce01ee5d955732f9ded1e4682050c9ae86c816
+size 7672