| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.48, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008, | |
| "grad_norm": 1.6839892864227295, | |
| "learning_rate": 4e-05, | |
| "loss": 1.301, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.016, | |
| "grad_norm": 1.386156678199768, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3643, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.024, | |
| "grad_norm": 0.9964010715484619, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1346, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.032, | |
| "grad_norm": 0.9237359166145325, | |
| "learning_rate": 0.00016, | |
| "loss": 1.2865, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "grad_norm": 0.4482671618461609, | |
| "learning_rate": 0.0002, | |
| "loss": 1.0312, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.048, | |
| "grad_norm": 0.395876407623291, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 0.9728, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.056, | |
| "grad_norm": 0.6330752968788147, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 1.0906, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.064, | |
| "grad_norm": 0.39497730135917664, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 1.0165, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.072, | |
| "grad_norm": 0.3924015462398529, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 1.0005, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "grad_norm": 0.3233727216720581, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 1.0234, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.088, | |
| "grad_norm": 0.5036228895187378, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 0.8657, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.096, | |
| "grad_norm": 0.8032389283180237, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 0.8278, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.104, | |
| "grad_norm": 0.3186076283454895, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 0.877, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.112, | |
| "grad_norm": 0.3362283408641815, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 0.8952, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "grad_norm": 0.3292746841907501, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 0.8007, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.128, | |
| "grad_norm": 0.5558376908302307, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9349, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.136, | |
| "grad_norm": 0.3033958375453949, | |
| "learning_rate": 0.00015636363636363637, | |
| "loss": 0.7249, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.144, | |
| "grad_norm": 0.301546186208725, | |
| "learning_rate": 0.00015272727272727275, | |
| "loss": 0.8493, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.152, | |
| "grad_norm": 0.2765434980392456, | |
| "learning_rate": 0.0001490909090909091, | |
| "loss": 0.782, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "grad_norm": 0.2590007483959198, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 0.6518, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.168, | |
| "grad_norm": 0.3257710039615631, | |
| "learning_rate": 0.00014181818181818184, | |
| "loss": 0.956, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.176, | |
| "grad_norm": 0.2133684605360031, | |
| "learning_rate": 0.0001381818181818182, | |
| "loss": 0.5397, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.184, | |
| "grad_norm": 0.22465167939662933, | |
| "learning_rate": 0.00013454545454545455, | |
| "loss": 0.7032, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.192, | |
| "grad_norm": 0.24608904123306274, | |
| "learning_rate": 0.00013090909090909093, | |
| "loss": 0.8161, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "grad_norm": 0.29115498065948486, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 0.7039, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.208, | |
| "grad_norm": 0.3457951545715332, | |
| "learning_rate": 0.00012363636363636364, | |
| "loss": 0.6452, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.216, | |
| "grad_norm": 0.3534717857837677, | |
| "learning_rate": 0.00012, | |
| "loss": 0.7724, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.224, | |
| "grad_norm": 0.3112258315086365, | |
| "learning_rate": 0.00011636363636363636, | |
| "loss": 0.7029, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.232, | |
| "grad_norm": 0.32025501132011414, | |
| "learning_rate": 0.00011272727272727272, | |
| "loss": 0.9089, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "grad_norm": 0.23741815984249115, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.5997, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.248, | |
| "grad_norm": 0.4178565442562103, | |
| "learning_rate": 0.00010545454545454545, | |
| "loss": 0.835, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.256, | |
| "grad_norm": 0.23426000773906708, | |
| "learning_rate": 0.00010181818181818181, | |
| "loss": 0.7768, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.264, | |
| "grad_norm": 0.28046417236328125, | |
| "learning_rate": 9.818181818181818e-05, | |
| "loss": 0.8841, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.272, | |
| "grad_norm": 0.37808024883270264, | |
| "learning_rate": 9.454545454545455e-05, | |
| "loss": 0.8584, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "grad_norm": 0.2408115565776825, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.7474, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.288, | |
| "grad_norm": 0.24366675317287445, | |
| "learning_rate": 8.727272727272727e-05, | |
| "loss": 0.7107, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.296, | |
| "grad_norm": 0.2985966205596924, | |
| "learning_rate": 8.363636363636364e-05, | |
| "loss": 0.7617, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.304, | |
| "grad_norm": 0.23527264595031738, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7948, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.312, | |
| "grad_norm": 0.268421471118927, | |
| "learning_rate": 7.636363636363637e-05, | |
| "loss": 0.5638, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.26604562997817993, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.7577, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.328, | |
| "grad_norm": 0.21873734891414642, | |
| "learning_rate": 6.90909090909091e-05, | |
| "loss": 0.758, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.336, | |
| "grad_norm": 0.27550163865089417, | |
| "learning_rate": 6.545454545454546e-05, | |
| "loss": 0.774, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.344, | |
| "grad_norm": 0.2736279368400574, | |
| "learning_rate": 6.181818181818182e-05, | |
| "loss": 0.7378, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.352, | |
| "grad_norm": 0.2714160978794098, | |
| "learning_rate": 5.818181818181818e-05, | |
| "loss": 0.6681, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "grad_norm": 0.29298704862594604, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.5982, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.368, | |
| "grad_norm": 0.3377845585346222, | |
| "learning_rate": 5.090909090909091e-05, | |
| "loss": 0.6176, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.376, | |
| "grad_norm": 0.34884122014045715, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.8299, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.384, | |
| "grad_norm": 0.2873862087726593, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.6805, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.392, | |
| "grad_norm": 0.25929009914398193, | |
| "learning_rate": 4e-05, | |
| "loss": 0.7985, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "grad_norm": 0.2327166497707367, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.5968, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.408, | |
| "grad_norm": 0.27193504571914673, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.7195, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.416, | |
| "grad_norm": 0.2823130488395691, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 0.8598, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.424, | |
| "grad_norm": 0.30219078063964844, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 0.763, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.432, | |
| "grad_norm": 0.2724802792072296, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 0.7016, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "grad_norm": 0.26255902647972107, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.6229, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.448, | |
| "grad_norm": 0.27147480845451355, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 0.7846, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.456, | |
| "grad_norm": 0.2804729640483856, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 0.777, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.464, | |
| "grad_norm": 0.22172842919826508, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 0.9042, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.472, | |
| "grad_norm": 0.33171340823173523, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 0.6419, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "grad_norm": 0.21746467053890228, | |
| "learning_rate": 0.0, | |
| "loss": 0.6739, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "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": 2413435443197952.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |