| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9952941176470587, | |
| "eval_steps": 500, | |
| "global_step": 212, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.047058823529411764, | |
| "grad_norm": 1.3170621395111084, | |
| "learning_rate": 4.9931407070965254e-05, | |
| "loss": 0.8347, | |
| "num_input_tokens_seen": 116560, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.7480270862579346, | |
| "learning_rate": 4.97260046830541e-05, | |
| "loss": 0.545, | |
| "num_input_tokens_seen": 229632, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1411764705882353, | |
| "grad_norm": 0.7734505534172058, | |
| "learning_rate": 4.9384919968379945e-05, | |
| "loss": 0.4738, | |
| "num_input_tokens_seen": 345008, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.6531177163124084, | |
| "learning_rate": 4.891002460691306e-05, | |
| "loss": 0.4494, | |
| "num_input_tokens_seen": 464176, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.6236650943756104, | |
| "learning_rate": 4.83039245557597e-05, | |
| "loss": 0.4115, | |
| "num_input_tokens_seen": 579536, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.5742521286010742, | |
| "learning_rate": 4.756994574914359e-05, | |
| "loss": 0.3727, | |
| "num_input_tokens_seen": 695664, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32941176470588235, | |
| "grad_norm": 0.6050655841827393, | |
| "learning_rate": 4.6712115847560355e-05, | |
| "loss": 0.3611, | |
| "num_input_tokens_seen": 816160, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.610315203666687, | |
| "learning_rate": 4.573514213625505e-05, | |
| "loss": 0.3559, | |
| "num_input_tokens_seen": 933856, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4235294117647059, | |
| "grad_norm": 0.6431180834770203, | |
| "learning_rate": 4.464438569430354e-05, | |
| "loss": 0.3541, | |
| "num_input_tokens_seen": 1056032, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.6149665117263794, | |
| "learning_rate": 4.344583197604318e-05, | |
| "loss": 0.3322, | |
| "num_input_tokens_seen": 1175184, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5176470588235295, | |
| "grad_norm": 0.6773995757102966, | |
| "learning_rate": 4.214605796628527e-05, | |
| "loss": 0.3391, | |
| "num_input_tokens_seen": 1296368, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 0.8067043423652649, | |
| "learning_rate": 4.075219608954278e-05, | |
| "loss": 0.3238, | |
| "num_input_tokens_seen": 1416656, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.611764705882353, | |
| "grad_norm": 0.6966668367385864, | |
| "learning_rate": 3.927189507131938e-05, | |
| "loss": 0.3191, | |
| "num_input_tokens_seen": 1533136, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": 0.6485809087753296, | |
| "learning_rate": 3.7713277966230514e-05, | |
| "loss": 0.3192, | |
| "num_input_tokens_seen": 1647680, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.6206268072128296, | |
| "learning_rate": 3.608489758327472e-05, | |
| "loss": 0.324, | |
| "num_input_tokens_seen": 1770192, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": 0.5658767819404602, | |
| "learning_rate": 3.4395689552855955e-05, | |
| "loss": 0.3092, | |
| "num_input_tokens_seen": 1887696, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.6363285779953003, | |
| "learning_rate": 3.265492329309867e-05, | |
| "loss": 0.3074, | |
| "num_input_tokens_seen": 2007312, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": 0.6739779710769653, | |
| "learning_rate": 3.0872151144524595e-05, | |
| "loss": 0.3092, | |
| "num_input_tokens_seen": 2117952, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8941176470588236, | |
| "grad_norm": 0.6705839037895203, | |
| "learning_rate": 2.9057155952211502e-05, | |
| "loss": 0.3015, | |
| "num_input_tokens_seen": 2231696, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.6125645041465759, | |
| "learning_rate": 2.7219897383073373e-05, | |
| "loss": 0.2964, | |
| "num_input_tokens_seen": 2348320, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9882352941176471, | |
| "grad_norm": 0.6411484479904175, | |
| "learning_rate": 2.537045727284232e-05, | |
| "loss": 0.2759, | |
| "num_input_tokens_seen": 2462112, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.035294117647059, | |
| "grad_norm": 0.6348647475242615, | |
| "learning_rate": 2.3518984302657146e-05, | |
| "loss": 0.2772, | |
| "num_input_tokens_seen": 2583648, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0823529411764705, | |
| "grad_norm": 0.659324049949646, | |
| "learning_rate": 2.1675638308842145e-05, | |
| "loss": 0.2834, | |
| "num_input_tokens_seen": 2704112, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.1294117647058823, | |
| "grad_norm": 0.7502089738845825, | |
| "learning_rate": 1.9850534531472546e-05, | |
| "loss": 0.2764, | |
| "num_input_tokens_seen": 2823088, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.6629338264465332, | |
| "learning_rate": 1.8053688107658908e-05, | |
| "loss": 0.2842, | |
| "num_input_tokens_seen": 2940800, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.223529411764706, | |
| "grad_norm": 0.7144020199775696, | |
| "learning_rate": 1.6294959114140034e-05, | |
| "loss": 0.2712, | |
| "num_input_tokens_seen": 3058864, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2705882352941176, | |
| "grad_norm": 0.717128574848175, | |
| "learning_rate": 1.4583998460759424e-05, | |
| "loss": 0.2638, | |
| "num_input_tokens_seen": 3174128, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.3176470588235294, | |
| "grad_norm": 0.7881118059158325, | |
| "learning_rate": 1.2930194931731382e-05, | |
| "loss": 0.2754, | |
| "num_input_tokens_seen": 3289712, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3647058823529412, | |
| "grad_norm": 0.738702654838562, | |
| "learning_rate": 1.1342623665304209e-05, | |
| "loss": 0.2844, | |
| "num_input_tokens_seen": 3410480, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.722718358039856, | |
| "learning_rate": 9.829996354535172e-06, | |
| "loss": 0.2745, | |
| "num_input_tokens_seen": 3526224, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4588235294117646, | |
| "grad_norm": 0.7094296216964722, | |
| "learning_rate": 8.400613442446948e-06, | |
| "loss": 0.2772, | |
| "num_input_tokens_seen": 3644464, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.5058823529411764, | |
| "grad_norm": 0.7090117335319519, | |
| "learning_rate": 7.062318573891716e-06, | |
| "loss": 0.2777, | |
| "num_input_tokens_seen": 3760976, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5529411764705883, | |
| "grad_norm": 0.6970705389976501, | |
| "learning_rate": 5.822455554065217e-06, | |
| "loss": 0.2766, | |
| "num_input_tokens_seen": 3880608, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.7649534344673157, | |
| "learning_rate": 4.687828049857967e-06, | |
| "loss": 0.2599, | |
| "num_input_tokens_seen": 3993216, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.6839666366577148, | |
| "learning_rate": 3.6646622551801345e-06, | |
| "loss": 0.2535, | |
| "num_input_tokens_seen": 4111136, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.6941176470588235, | |
| "grad_norm": 0.7336522340774536, | |
| "learning_rate": 2.75857272513132e-06, | |
| "loss": 0.2741, | |
| "num_input_tokens_seen": 4229136, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7411764705882353, | |
| "grad_norm": 0.6339069604873657, | |
| "learning_rate": 1.9745315664982276e-06, | |
| "loss": 0.2601, | |
| "num_input_tokens_seen": 4344928, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.788235294117647, | |
| "grad_norm": 0.6466521620750427, | |
| "learning_rate": 1.3168411536452152e-06, | |
| "loss": 0.2536, | |
| "num_input_tokens_seen": 4462192, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.835294117647059, | |
| "grad_norm": 0.7034646272659302, | |
| "learning_rate": 7.891105195175358e-07, | |
| "loss": 0.2678, | |
| "num_input_tokens_seen": 4584528, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.6738657355308533, | |
| "learning_rate": 3.9423555131007925e-07, | |
| "loss": 0.2693, | |
| "num_input_tokens_seen": 4701808, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9294117647058824, | |
| "grad_norm": 0.6806563138961792, | |
| "learning_rate": 1.343830994765982e-07, | |
| "loss": 0.2545, | |
| "num_input_tokens_seen": 4817760, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.9764705882352942, | |
| "grad_norm": 0.7523545622825623, | |
| "learning_rate": 1.0979087280141298e-08, | |
| "loss": 0.2693, | |
| "num_input_tokens_seen": 4932544, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9952941176470587, | |
| "num_input_tokens_seen": 4979584, | |
| "step": 212, | |
| "total_flos": 2.1307535061837414e+17, | |
| "train_loss": 0.32363298928962564, | |
| "train_runtime": 2717.673, | |
| "train_samples_per_second": 2.502, | |
| "train_steps_per_second": 0.078 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 212, | |
| "num_input_tokens_seen": 4979584, | |
| "num_train_epochs": 2, | |
| "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": 2.1307535061837414e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |