| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 269, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.07434944237918216, | |
| "grad_norm": 2.5, | |
| "learning_rate": 1.8518518518518519e-06, | |
| "loss": 2.7059, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.14869888475836432, | |
| "grad_norm": 2.5, | |
| "learning_rate": 3.7037037037037037e-06, | |
| "loss": 2.7411, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.22304832713754646, | |
| "grad_norm": 3.078125, | |
| "learning_rate": 4.990398100856367e-06, | |
| "loss": 2.5655, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.29739776951672864, | |
| "grad_norm": 1.8984375, | |
| "learning_rate": 4.821741763807186e-06, | |
| "loss": 2.3063, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37174721189591076, | |
| "grad_norm": 1.7421875, | |
| "learning_rate": 4.456204510851957e-06, | |
| "loss": 2.1029, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.44609665427509293, | |
| "grad_norm": 1.4453125, | |
| "learning_rate": 3.924783462463541e-06, | |
| "loss": 1.9675, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5204460966542751, | |
| "grad_norm": 1.1875, | |
| "learning_rate": 3.272542485937369e-06, | |
| "loss": 1.9171, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5947955390334573, | |
| "grad_norm": 1.25, | |
| "learning_rate": 2.5547908335131704e-06, | |
| "loss": 1.8781, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6691449814126395, | |
| "grad_norm": 1.4453125, | |
| "learning_rate": 1.832392984146018e-06, | |
| "loss": 1.8382, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7434944237918215, | |
| "grad_norm": 1.4296875, | |
| "learning_rate": 1.1666074087171628e-06, | |
| "loss": 1.8145, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8178438661710037, | |
| "grad_norm": 1.2890625, | |
| "learning_rate": 6.138919252022435e-07, | |
| "loss": 1.8354, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.8921933085501859, | |
| "grad_norm": 1.3203125, | |
| "learning_rate": 2.2111614344599686e-07, | |
| "loss": 1.8125, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.966542750929368, | |
| "grad_norm": 1.453125, | |
| "learning_rate": 2.1586978482366072e-08, | |
| "loss": 1.8379, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 269, | |
| "total_flos": 4.955226157508198e+16, | |
| "train_loss": 2.0918177352961997, | |
| "train_runtime": 4098.0987, | |
| "train_samples_per_second": 0.263, | |
| "train_steps_per_second": 0.066 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 269, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 4.955226157508198e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |