| { | |
| "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": 1.2597168684005737, | |
| "learning_rate": 4.9931407070965254e-05, | |
| "loss": 0.7844, | |
| "num_input_tokens_seen": 113104, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.8212803602218628, | |
| "learning_rate": 4.97260046830541e-05, | |
| "loss": 0.4838, | |
| "num_input_tokens_seen": 222672, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1411764705882353, | |
| "grad_norm": 0.713465690612793, | |
| "learning_rate": 4.9384919968379945e-05, | |
| "loss": 0.425, | |
| "num_input_tokens_seen": 334464, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.6203038692474365, | |
| "learning_rate": 4.891002460691306e-05, | |
| "loss": 0.4034, | |
| "num_input_tokens_seen": 450112, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.6142417788505554, | |
| "learning_rate": 4.83039245557597e-05, | |
| "loss": 0.3746, | |
| "num_input_tokens_seen": 561888, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.5748819708824158, | |
| "learning_rate": 4.756994574914359e-05, | |
| "loss": 0.3394, | |
| "num_input_tokens_seen": 674576, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32941176470588235, | |
| "grad_norm": 0.5614773631095886, | |
| "learning_rate": 4.6712115847560355e-05, | |
| "loss": 0.3312, | |
| "num_input_tokens_seen": 791472, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.5544697642326355, | |
| "learning_rate": 4.573514213625505e-05, | |
| "loss": 0.3277, | |
| "num_input_tokens_seen": 905712, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4235294117647059, | |
| "grad_norm": 0.5900682806968689, | |
| "learning_rate": 4.464438569430354e-05, | |
| "loss": 0.3274, | |
| "num_input_tokens_seen": 1024304, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.5739061236381531, | |
| "learning_rate": 4.344583197604318e-05, | |
| "loss": 0.3074, | |
| "num_input_tokens_seen": 1139904, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5176470588235295, | |
| "grad_norm": 0.5653313994407654, | |
| "learning_rate": 4.214605796628527e-05, | |
| "loss": 0.3147, | |
| "num_input_tokens_seen": 1257504, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 0.6587158441543579, | |
| "learning_rate": 4.075219608954278e-05, | |
| "loss": 0.3017, | |
| "num_input_tokens_seen": 1374272, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.611764705882353, | |
| "grad_norm": 0.550284743309021, | |
| "learning_rate": 3.927189507131938e-05, | |
| "loss": 0.2992, | |
| "num_input_tokens_seen": 1487248, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": 0.5366208553314209, | |
| "learning_rate": 3.7713277966230514e-05, | |
| "loss": 0.3, | |
| "num_input_tokens_seen": 1598400, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.5543321967124939, | |
| "learning_rate": 3.608489758327472e-05, | |
| "loss": 0.3018, | |
| "num_input_tokens_seen": 1717296, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": 0.5324147343635559, | |
| "learning_rate": 3.4395689552855955e-05, | |
| "loss": 0.2904, | |
| "num_input_tokens_seen": 1831296, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.592769980430603, | |
| "learning_rate": 3.265492329309867e-05, | |
| "loss": 0.2861, | |
| "num_input_tokens_seen": 1947360, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": 0.583766758441925, | |
| "learning_rate": 3.0872151144524595e-05, | |
| "loss": 0.2923, | |
| "num_input_tokens_seen": 2054512, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8941176470588236, | |
| "grad_norm": 0.5162491202354431, | |
| "learning_rate": 2.9057155952211502e-05, | |
| "loss": 0.2831, | |
| "num_input_tokens_seen": 2164752, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.5491448044776917, | |
| "learning_rate": 2.7219897383073373e-05, | |
| "loss": 0.2779, | |
| "num_input_tokens_seen": 2277856, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9882352941176471, | |
| "grad_norm": 0.5450201034545898, | |
| "learning_rate": 2.537045727284232e-05, | |
| "loss": 0.2633, | |
| "num_input_tokens_seen": 2388064, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.035294117647059, | |
| "grad_norm": 0.5881150364875793, | |
| "learning_rate": 2.3518984302657146e-05, | |
| "loss": 0.2631, | |
| "num_input_tokens_seen": 2506096, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0823529411764705, | |
| "grad_norm": 0.5562729835510254, | |
| "learning_rate": 2.1675638308842145e-05, | |
| "loss": 0.264, | |
| "num_input_tokens_seen": 2623072, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.1294117647058823, | |
| "grad_norm": 0.6210693120956421, | |
| "learning_rate": 1.9850534531472546e-05, | |
| "loss": 0.2579, | |
| "num_input_tokens_seen": 2738576, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.5652827024459839, | |
| "learning_rate": 1.8053688107658908e-05, | |
| "loss": 0.2674, | |
| "num_input_tokens_seen": 2852704, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.223529411764706, | |
| "grad_norm": 0.5649927854537964, | |
| "learning_rate": 1.6294959114140034e-05, | |
| "loss": 0.2542, | |
| "num_input_tokens_seen": 2967184, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2705882352941176, | |
| "grad_norm": 0.5547770261764526, | |
| "learning_rate": 1.4583998460759424e-05, | |
| "loss": 0.2499, | |
| "num_input_tokens_seen": 3078944, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.3176470588235294, | |
| "grad_norm": 0.6156982779502869, | |
| "learning_rate": 1.2930194931731382e-05, | |
| "loss": 0.2594, | |
| "num_input_tokens_seen": 3191008, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3647058823529412, | |
| "grad_norm": 0.5913279056549072, | |
| "learning_rate": 1.1342623665304209e-05, | |
| "loss": 0.2696, | |
| "num_input_tokens_seen": 3308176, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.5994729995727539, | |
| "learning_rate": 9.829996354535172e-06, | |
| "loss": 0.2582, | |
| "num_input_tokens_seen": 3420480, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4588235294117646, | |
| "grad_norm": 0.7692103385925293, | |
| "learning_rate": 8.400613442446948e-06, | |
| "loss": 0.2639, | |
| "num_input_tokens_seen": 3535280, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.5058823529411764, | |
| "grad_norm": 0.5787561535835266, | |
| "learning_rate": 7.062318573891716e-06, | |
| "loss": 0.2628, | |
| "num_input_tokens_seen": 3648256, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5529411764705883, | |
| "grad_norm": 0.5587510466575623, | |
| "learning_rate": 5.822455554065217e-06, | |
| "loss": 0.2596, | |
| "num_input_tokens_seen": 3764400, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.5860652327537537, | |
| "learning_rate": 4.687828049857967e-06, | |
| "loss": 0.2438, | |
| "num_input_tokens_seen": 3873456, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.5650219321250916, | |
| "learning_rate": 3.6646622551801345e-06, | |
| "loss": 0.2388, | |
| "num_input_tokens_seen": 3987808, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.6941176470588235, | |
| "grad_norm": 0.6057121753692627, | |
| "learning_rate": 2.75857272513132e-06, | |
| "loss": 0.2587, | |
| "num_input_tokens_seen": 4102208, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7411764705882353, | |
| "grad_norm": 0.6009911894798279, | |
| "learning_rate": 1.9745315664982276e-06, | |
| "loss": 0.2458, | |
| "num_input_tokens_seen": 4214528, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.788235294117647, | |
| "grad_norm": 0.5280789732933044, | |
| "learning_rate": 1.3168411536452152e-06, | |
| "loss": 0.2395, | |
| "num_input_tokens_seen": 4328288, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.835294117647059, | |
| "grad_norm": 0.57253098487854, | |
| "learning_rate": 7.891105195175358e-07, | |
| "loss": 0.2522, | |
| "num_input_tokens_seen": 4447136, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.5598665475845337, | |
| "learning_rate": 3.9423555131007925e-07, | |
| "loss": 0.2553, | |
| "num_input_tokens_seen": 4561008, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9294117647058824, | |
| "grad_norm": 0.5753045678138733, | |
| "learning_rate": 1.343830994765982e-07, | |
| "loss": 0.2445, | |
| "num_input_tokens_seen": 4673504, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.9764705882352942, | |
| "grad_norm": 0.5889866352081299, | |
| "learning_rate": 1.0979087280141298e-08, | |
| "loss": 0.2542, | |
| "num_input_tokens_seen": 4784784, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9952941176470587, | |
| "num_input_tokens_seen": 4830400, | |
| "step": 212, | |
| "total_flos": 3.081382534064374e+17, | |
| "train_loss": 0.30173668602727494, | |
| "train_runtime": 3949.4939, | |
| "train_samples_per_second": 1.722, | |
| "train_steps_per_second": 0.054 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 212, | |
| "num_input_tokens_seen": 4830400, | |
| "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": 3.081382534064374e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |