| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 59, | |
| "global_step": 236, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00423728813559322, | |
| "eval_loss": 1.7249085903167725, | |
| "eval_runtime": 8.4858, | |
| "eval_samples_per_second": 11.784, | |
| "eval_steps_per_second": 5.892, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0211864406779661, | |
| "grad_norm": 0.3638346493244171, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.3688, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0423728813559322, | |
| "grad_norm": 0.24444879591464996, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 1.7376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0635593220338983, | |
| "grad_norm": 0.32083624601364136, | |
| "learning_rate": 5e-05, | |
| "loss": 1.8018, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 0.5033571720123291, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.7648, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.1059322033898305, | |
| "grad_norm": 0.5790311694145203, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 1.7307, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.1271186440677966, | |
| "grad_norm": 0.7558295130729675, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6065, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1483050847457627, | |
| "grad_norm": 0.5623775720596313, | |
| "learning_rate": 9.985471028179154e-05, | |
| "loss": 1.6408, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 0.6156546473503113, | |
| "learning_rate": 9.941968549125481e-05, | |
| "loss": 1.5529, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1906779661016949, | |
| "grad_norm": 0.7409376502037048, | |
| "learning_rate": 9.869745381355906e-05, | |
| "loss": 1.731, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.211864406779661, | |
| "grad_norm": 2.1485629081726074, | |
| "learning_rate": 9.769221256218164e-05, | |
| "loss": 1.5325, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2330508474576271, | |
| "grad_norm": 0.4415481686592102, | |
| "learning_rate": 9.64098037858483e-05, | |
| "loss": 1.2719, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "eval_loss": 1.4849549531936646, | |
| "eval_runtime": 8.6149, | |
| "eval_samples_per_second": 11.608, | |
| "eval_steps_per_second": 5.804, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2542372881355932, | |
| "grad_norm": 0.3637336194515228, | |
| "learning_rate": 9.485768031694872e-05, | |
| "loss": 1.5802, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2754237288135593, | |
| "grad_norm": 0.36982426047325134, | |
| "learning_rate": 9.304486245873972e-05, | |
| "loss": 1.6654, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.2966101694915254, | |
| "grad_norm": 0.5281253457069397, | |
| "learning_rate": 9.098188556305263e-05, | |
| "loss": 1.7937, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3177966101694915, | |
| "grad_norm": 0.4794275164604187, | |
| "learning_rate": 8.868073880316124e-05, | |
| "loss": 1.542, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.3389830508474576, | |
| "grad_norm": 0.4679938852787018, | |
| "learning_rate": 8.615479549763756e-05, | |
| "loss": 1.7178, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.3601694915254237, | |
| "grad_norm": 0.6459900736808777, | |
| "learning_rate": 8.341873539012444e-05, | |
| "loss": 1.5279, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.3813559322033898, | |
| "grad_norm": 0.774486243724823, | |
| "learning_rate": 8.048845933670273e-05, | |
| "loss": 1.5344, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.4025423728813559, | |
| "grad_norm": 0.9203367233276367, | |
| "learning_rate": 7.73809968966554e-05, | |
| "loss": 1.3637, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.423728813559322, | |
| "grad_norm": 1.7692137956619263, | |
| "learning_rate": 7.411440736367281e-05, | |
| "loss": 1.421, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.4449152542372881, | |
| "grad_norm": 0.3940534293651581, | |
| "learning_rate": 7.070767481266492e-05, | |
| "loss": 1.1592, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.4661016949152542, | |
| "grad_norm": 0.31518927216529846, | |
| "learning_rate": 6.718059777212567e-05, | |
| "loss": 1.5224, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.4872881355932203, | |
| "grad_norm": 0.4130525290966034, | |
| "learning_rate": 6.355367416322779e-05, | |
| "loss": 1.6624, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_loss": 1.4531333446502686, | |
| "eval_runtime": 8.5017, | |
| "eval_samples_per_second": 11.762, | |
| "eval_steps_per_second": 5.881, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.5084745762711864, | |
| "grad_norm": 0.4499770700931549, | |
| "learning_rate": 5.9847982174335316e-05, | |
| "loss": 1.7216, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.5296610169491526, | |
| "grad_norm": 0.47381460666656494, | |
| "learning_rate": 5.608505776324158e-05, | |
| "loss": 1.4514, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.5508474576271186, | |
| "grad_norm": 0.5892888307571411, | |
| "learning_rate": 5.228676949903973e-05, | |
| "loss": 1.5234, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.5720338983050848, | |
| "grad_norm": 0.590027391910553, | |
| "learning_rate": 4.847519147099294e-05, | |
| "loss": 1.4497, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 0.5932203389830508, | |
| "grad_norm": 0.6537613868713379, | |
| "learning_rate": 4.46724750030062e-05, | |
| "loss": 1.5984, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.614406779661017, | |
| "grad_norm": 0.8353936672210693, | |
| "learning_rate": 4.0900719919241935e-05, | |
| "loss": 1.4847, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 0.635593220338983, | |
| "grad_norm": 1.600169062614441, | |
| "learning_rate": 3.7181846109031005e-05, | |
| "loss": 1.6274, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.6567796610169492, | |
| "grad_norm": 0.31450155377388, | |
| "learning_rate": 3.353746613749094e-05, | |
| "loss": 1.1725, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 0.6779661016949152, | |
| "grad_norm": 0.3330669403076172, | |
| "learning_rate": 2.9988759642186097e-05, | |
| "loss": 1.392, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.6991525423728814, | |
| "grad_norm": 0.35386720299720764, | |
| "learning_rate": 2.6556350245784833e-05, | |
| "loss": 1.6059, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 0.7203389830508474, | |
| "grad_norm": 0.4171987771987915, | |
| "learning_rate": 2.3260185700046294e-05, | |
| "loss": 1.6118, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.7415254237288136, | |
| "grad_norm": 0.43384310603141785, | |
| "learning_rate": 2.011942195769122e-05, | |
| "loss": 1.3333, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "eval_loss": 1.4390202760696411, | |
| "eval_runtime": 8.6381, | |
| "eval_samples_per_second": 11.577, | |
| "eval_steps_per_second": 5.788, | |
| "step": 177 | |
| }, | |
| { | |
| "epoch": 0.7627118644067796, | |
| "grad_norm": 0.5793793797492981, | |
| "learning_rate": 1.7152311845883095e-05, | |
| "loss": 1.4983, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.7838983050847458, | |
| "grad_norm": 0.6938722729682922, | |
| "learning_rate": 1.4376098988303405e-05, | |
| "loss": 1.3863, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 0.8050847457627118, | |
| "grad_norm": 0.6867596507072449, | |
| "learning_rate": 1.1806917592302762e-05, | |
| "loss": 1.6187, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.826271186440678, | |
| "grad_norm": 0.9748066663742065, | |
| "learning_rate": 9.459698683523204e-06, | |
| "loss": 1.4349, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 0.847457627118644, | |
| "grad_norm": 1.923925757408142, | |
| "learning_rate": 7.348083332917926e-06, | |
| "loss": 1.5132, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.8686440677966102, | |
| "grad_norm": 0.32460537552833557, | |
| "learning_rate": 5.484343380457125e-06, | |
| "loss": 1.3116, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 0.8898305084745762, | |
| "grad_norm": 0.40792253613471985, | |
| "learning_rate": 3.879310116241042e-06, | |
| "loss": 1.5229, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 0.9110169491525424, | |
| "grad_norm": 0.417889267206192, | |
| "learning_rate": 2.542311333496622e-06, | |
| "loss": 1.4959, | |
| "step": 215 | |
| }, | |
| { | |
| "epoch": 0.9322033898305084, | |
| "grad_norm": 0.5283035039901733, | |
| "learning_rate": 1.4811171192794627e-06, | |
| "loss": 1.5565, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.9533898305084746, | |
| "grad_norm": 0.6696847677230835, | |
| "learning_rate": 7.018946979234997e-07, | |
| "loss": 1.4598, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 0.9745762711864406, | |
| "grad_norm": 0.6265289187431335, | |
| "learning_rate": 2.0917258966953733e-07, | |
| "loss": 1.5206, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 0.9957627118644068, | |
| "grad_norm": 1.065112829208374, | |
| "learning_rate": 5.814292768108187e-09, | |
| "loss": 1.5803, | |
| "step": 235 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_loss": 1.4057904481887817, | |
| "eval_runtime": 8.627, | |
| "eval_samples_per_second": 11.592, | |
| "eval_steps_per_second": 5.796, | |
| "step": 236 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 236, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 8.267951517990912e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |