| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.9915254237288136, |
| "eval_steps": 500, |
| "global_step": 78, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.025423728813559324, |
| "grad_norm": 0.08035527647801548, |
| "learning_rate": 1.25e-06, |
| "loss": 0.4007, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.1271186440677966, |
| "grad_norm": 0.05733009561118041, |
| "learning_rate": 6.25e-06, |
| "loss": 0.4134, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.2542372881355932, |
| "grad_norm": 0.061316952771613246, |
| "learning_rate": 9.979871469976197e-06, |
| "loss": 0.4061, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.3813559322033898, |
| "grad_norm": 0.0706914793637617, |
| "learning_rate": 9.755282581475769e-06, |
| "loss": 0.4018, |
| "step": 15 |
| }, |
| { |
| "epoch": 0.5084745762711864, |
| "grad_norm": 0.06306250853537879, |
| "learning_rate": 9.292243968009332e-06, |
| "loss": 0.4068, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.635593220338983, |
| "grad_norm": 0.05396739437655817, |
| "learning_rate": 8.613974319136959e-06, |
| "loss": 0.388, |
| "step": 25 |
| }, |
| { |
| "epoch": 0.7627118644067796, |
| "grad_norm": 0.055943979296443166, |
| "learning_rate": 7.754484907260513e-06, |
| "loss": 0.3379, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.8898305084745762, |
| "grad_norm": 0.06643011122771461, |
| "learning_rate": 6.7568741204067145e-06, |
| "loss": 0.3801, |
| "step": 35 |
| }, |
| { |
| "epoch": 0.9915254237288136, |
| "eval_loss": 0.42687076330184937, |
| "eval_runtime": 29.2208, |
| "eval_samples_per_second": 18.788, |
| "eval_steps_per_second": 4.723, |
| "step": 39 |
| }, |
| { |
| "epoch": 1.0254237288135593, |
| "grad_norm": 0.1257204507458321, |
| "learning_rate": 5.671166329088278e-06, |
| "loss": 0.4294, |
| "step": 40 |
| }, |
| { |
| "epoch": 1.152542372881356, |
| "grad_norm": 0.061247984812326635, |
| "learning_rate": 4.551803455482833e-06, |
| "loss": 0.3162, |
| "step": 45 |
| }, |
| { |
| "epoch": 1.2796610169491525, |
| "grad_norm": 0.06297833414755911, |
| "learning_rate": 3.4549150281252635e-06, |
| "loss": 0.3145, |
| "step": 50 |
| }, |
| { |
| "epoch": 1.4067796610169492, |
| "grad_norm": 0.06687382967843461, |
| "learning_rate": 2.43550361297047e-06, |
| "loss": 0.2941, |
| "step": 55 |
| }, |
| { |
| "epoch": 1.5338983050847457, |
| "grad_norm": 0.06683369207674608, |
| "learning_rate": 1.544686755065677e-06, |
| "loss": 0.3145, |
| "step": 60 |
| }, |
| { |
| "epoch": 1.6610169491525424, |
| "grad_norm": 0.0813495468013659, |
| "learning_rate": 8.271337313934869e-07, |
| "loss": 0.2945, |
| "step": 65 |
| }, |
| { |
| "epoch": 1.788135593220339, |
| "grad_norm": 0.07371530295761193, |
| "learning_rate": 3.18825646801314e-07, |
| "loss": 0.3056, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.9152542372881356, |
| "grad_norm": 0.06581699726337101, |
| "learning_rate": 4.52511911603265e-08, |
| "loss": 0.2775, |
| "step": 75 |
| }, |
| { |
| "epoch": 1.9915254237288136, |
| "eval_loss": 0.443694531917572, |
| "eval_runtime": 28.5624, |
| "eval_samples_per_second": 19.221, |
| "eval_steps_per_second": 4.832, |
| "step": 78 |
| }, |
| { |
| "epoch": 1.9915254237288136, |
| "step": 78, |
| "total_flos": 1.99474976032555e+17, |
| "train_loss": 0.34869656616296524, |
| "train_runtime": 1209.7175, |
| "train_samples_per_second": 3.118, |
| "train_steps_per_second": 0.064 |
| } |
| ], |
| "logging_steps": 5, |
| "max_steps": 78, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "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": 1.99474976032555e+17, |
| "train_batch_size": 1, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
