| { | |
| "best_metric": 0.7856930494308472, | |
| "best_model_checkpoint": "/ML-A100/team/mm/eamon/self_instruction/seed_ppl/qwen4B_models/qwen_4B_d1_iter2_model/checkpoint-100", | |
| "epoch": 2.0, | |
| "eval_steps": 100, | |
| "global_step": 136, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.14705882352941177, | |
| "grad_norm": 1.1161658260127314, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.438, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.29411764705882354, | |
| "grad_norm": 1.141386114916924, | |
| "learning_rate": 5e-05, | |
| "loss": 1.2455, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4411764705882353, | |
| "grad_norm": 0.908747056691058, | |
| "learning_rate": 4.908874981298057e-05, | |
| "loss": 0.8748, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5882352941176471, | |
| "grad_norm": 1.160724824332908, | |
| "learning_rate": 4.642142940418973e-05, | |
| "loss": 0.8399, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7352941176470589, | |
| "grad_norm": 1.7354204311716015, | |
| "learning_rate": 4.2192486471335585e-05, | |
| "loss": 0.8371, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8823529411764706, | |
| "grad_norm": 0.989621687985043, | |
| "learning_rate": 3.671021101749476e-05, | |
| "loss": 0.8346, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.0294117647058822, | |
| "grad_norm": 1.4467052607165527, | |
| "learning_rate": 3.0374261005275607e-05, | |
| "loss": 0.85, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 1.022122556125995, | |
| "learning_rate": 2.3646527285364565e-05, | |
| "loss": 0.8218, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3235294117647058, | |
| "grad_norm": 1.168833164765407, | |
| "learning_rate": 1.7017461746600506e-05, | |
| "loss": 0.8021, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.4705882352941178, | |
| "grad_norm": 0.4995411891529773, | |
| "learning_rate": 1.0970323365940444e-05, | |
| "loss": 0.6978, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.4705882352941178, | |
| "eval_loss": 0.7856930494308472, | |
| "eval_runtime": 12.019, | |
| "eval_samples_per_second": 10.067, | |
| "eval_steps_per_second": 1.331, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6176470588235294, | |
| "grad_norm": 1.6403596296455754, | |
| "learning_rate": 5.945948621809091e-06, | |
| "loss": 0.7205, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7647058823529411, | |
| "grad_norm": 0.8006724271557235, | |
| "learning_rate": 2.310614508226078e-06, | |
| "loss": 0.787, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9117647058823528, | |
| "grad_norm": 1.7764723276974967, | |
| "learning_rate": 3.293369364618465e-07, | |
| "loss": 0.7046, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "step": 136, | |
| "total_flos": 21111522983936.0, | |
| "train_loss": 0.8778598624117234, | |
| "train_runtime": 458.5184, | |
| "train_samples_per_second": 4.746, | |
| "train_steps_per_second": 0.297 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 136, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 21111522983936.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |