| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 590, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 12.3125, | |
| "learning_rate": 4.8305084745762714e-05, | |
| "loss": 1.176, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 4.5625, | |
| "learning_rate": 4.6610169491525425e-05, | |
| "loss": 0.4758, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 1.0169491525423728, | |
| "grad_norm": 1.3671875, | |
| "learning_rate": 4.491525423728814e-05, | |
| "loss": 0.1471, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.3559322033898304, | |
| "grad_norm": 1.3515625, | |
| "learning_rate": 4.3220338983050854e-05, | |
| "loss": 0.0574, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.694915254237288, | |
| "grad_norm": 1.234375, | |
| "learning_rate": 4.152542372881356e-05, | |
| "loss": 0.0611, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.0338983050847457, | |
| "grad_norm": 0.76171875, | |
| "learning_rate": 3.983050847457627e-05, | |
| "loss": 0.0558, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.3728813559322033, | |
| "grad_norm": 0.91796875, | |
| "learning_rate": 3.813559322033898e-05, | |
| "loss": 0.0327, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.711864406779661, | |
| "grad_norm": 0.734375, | |
| "learning_rate": 3.644067796610169e-05, | |
| "loss": 0.032, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 3.0508474576271185, | |
| "grad_norm": 1.03125, | |
| "learning_rate": 3.474576271186441e-05, | |
| "loss": 0.0317, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 3.389830508474576, | |
| "grad_norm": 0.423828125, | |
| "learning_rate": 3.305084745762712e-05, | |
| "loss": 0.0212, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 3.7288135593220337, | |
| "grad_norm": 0.75, | |
| "learning_rate": 3.135593220338983e-05, | |
| "loss": 0.0206, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 4.067796610169491, | |
| "grad_norm": 0.625, | |
| "learning_rate": 2.9661016949152544e-05, | |
| "loss": 0.0192, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 4.406779661016949, | |
| "grad_norm": 0.625, | |
| "learning_rate": 2.7966101694915255e-05, | |
| "loss": 0.0139, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 4.745762711864407, | |
| "grad_norm": 0.63671875, | |
| "learning_rate": 2.627118644067797e-05, | |
| "loss": 0.0152, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 5.084745762711864, | |
| "grad_norm": 0.4140625, | |
| "learning_rate": 2.457627118644068e-05, | |
| "loss": 0.0138, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 5.423728813559322, | |
| "grad_norm": 0.5390625, | |
| "learning_rate": 2.2881355932203392e-05, | |
| "loss": 0.0107, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 5.762711864406779, | |
| "grad_norm": 0.578125, | |
| "learning_rate": 2.1186440677966103e-05, | |
| "loss": 0.0102, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 6.101694915254237, | |
| "grad_norm": 0.373046875, | |
| "learning_rate": 1.9491525423728814e-05, | |
| "loss": 0.011, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 6.440677966101695, | |
| "grad_norm": 0.3671875, | |
| "learning_rate": 1.7796610169491526e-05, | |
| "loss": 0.009, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 6.779661016949152, | |
| "grad_norm": 0.64453125, | |
| "learning_rate": 1.6101694915254237e-05, | |
| "loss": 0.0099, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 7.11864406779661, | |
| "grad_norm": 0.56640625, | |
| "learning_rate": 1.440677966101695e-05, | |
| "loss": 0.0082, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 7.4576271186440675, | |
| "grad_norm": 0.62890625, | |
| "learning_rate": 1.2711864406779661e-05, | |
| "loss": 0.0068, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 7.796610169491525, | |
| "grad_norm": 0.26953125, | |
| "learning_rate": 1.1016949152542374e-05, | |
| "loss": 0.0079, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 8.135593220338983, | |
| "grad_norm": 0.251953125, | |
| "learning_rate": 9.322033898305085e-06, | |
| "loss": 0.0087, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 8.474576271186441, | |
| "grad_norm": 0.5703125, | |
| "learning_rate": 7.627118644067798e-06, | |
| "loss": 0.0072, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 8.813559322033898, | |
| "grad_norm": 0.435546875, | |
| "learning_rate": 5.932203389830509e-06, | |
| "loss": 0.0078, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 9.152542372881356, | |
| "grad_norm": 0.244140625, | |
| "learning_rate": 4.23728813559322e-06, | |
| "loss": 0.0074, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 9.491525423728813, | |
| "grad_norm": 0.36328125, | |
| "learning_rate": 2.5423728813559323e-06, | |
| "loss": 0.0072, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 9.830508474576272, | |
| "grad_norm": 0.2734375, | |
| "learning_rate": 8.474576271186441e-07, | |
| "loss": 0.0084, | |
| "step": 580 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 590, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.08306100740096e+19, | |
| "train_batch_size": 64, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |