| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.9904761904761905, | |
| "eval_steps": 500, | |
| "global_step": 195, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0761904761904762, | |
| "grad_norm": 0.2616604268550873, | |
| "learning_rate": 4.9918932703355256e-05, | |
| "loss": 0.3151, | |
| "num_input_tokens_seen": 211280, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1523809523809524, | |
| "grad_norm": 0.2265331745147705, | |
| "learning_rate": 4.967625656594782e-05, | |
| "loss": 0.2406, | |
| "num_input_tokens_seen": 419136, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.22857142857142856, | |
| "grad_norm": 0.22684457898139954, | |
| "learning_rate": 4.92735454356513e-05, | |
| "loss": 0.1707, | |
| "num_input_tokens_seen": 631632, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3047619047619048, | |
| "grad_norm": 0.1457625925540924, | |
| "learning_rate": 4.8713411048678635e-05, | |
| "loss": 0.1223, | |
| "num_input_tokens_seen": 836896, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.38095238095238093, | |
| "grad_norm": 0.12437087297439575, | |
| "learning_rate": 4.799948609147061e-05, | |
| "loss": 0.0945, | |
| "num_input_tokens_seen": 1042416, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.45714285714285713, | |
| "grad_norm": 0.12409742921590805, | |
| "learning_rate": 4.713640064133025e-05, | |
| "loss": 0.0874, | |
| "num_input_tokens_seen": 1244384, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 0.09352266043424606, | |
| "learning_rate": 4.6129752138594874e-05, | |
| "loss": 0.0631, | |
| "num_input_tokens_seen": 1445168, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.6095238095238096, | |
| "grad_norm": 0.11023324728012085, | |
| "learning_rate": 4.498606908508754e-05, | |
| "loss": 0.0786, | |
| "num_input_tokens_seen": 1651760, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.6857142857142857, | |
| "grad_norm": 0.11427821964025497, | |
| "learning_rate": 4.371276870427753e-05, | |
| "loss": 0.0628, | |
| "num_input_tokens_seen": 1849920, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.7619047619047619, | |
| "grad_norm": 0.12007594108581543, | |
| "learning_rate": 4.231810883773999e-05, | |
| "loss": 0.0712, | |
| "num_input_tokens_seen": 2056592, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.8380952380952381, | |
| "grad_norm": 0.08302884548902512, | |
| "learning_rate": 4.0811134389884433e-05, | |
| "loss": 0.059, | |
| "num_input_tokens_seen": 2265056, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.9142857142857143, | |
| "grad_norm": 0.10222816467285156, | |
| "learning_rate": 3.920161866827889e-05, | |
| "loss": 0.0635, | |
| "num_input_tokens_seen": 2471328, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.9904761904761905, | |
| "grad_norm": 0.12720927596092224, | |
| "learning_rate": 3.7500000000000003e-05, | |
| "loss": 0.058, | |
| "num_input_tokens_seen": 2676640, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.0761904761904761, | |
| "grad_norm": 0.11531339585781097, | |
| "learning_rate": 3.5717314035076355e-05, | |
| "loss": 0.0693, | |
| "num_input_tokens_seen": 2897712, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.1523809523809523, | |
| "grad_norm": 0.09975585341453552, | |
| "learning_rate": 3.386512217606339e-05, | |
| "loss": 0.0537, | |
| "num_input_tokens_seen": 3089808, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.2285714285714286, | |
| "grad_norm": 0.10007397085428238, | |
| "learning_rate": 3.195543659791132e-05, | |
| "loss": 0.0547, | |
| "num_input_tokens_seen": 3296576, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.3047619047619048, | |
| "grad_norm": 0.10609045624732971, | |
| "learning_rate": 3.0000642344401113e-05, | |
| "loss": 0.0446, | |
| "num_input_tokens_seen": 3508416, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.380952380952381, | |
| "grad_norm": 0.12080738693475723, | |
| "learning_rate": 2.8013417006383076e-05, | |
| "loss": 0.0535, | |
| "num_input_tokens_seen": 3706512, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.457142857142857, | |
| "grad_norm": 0.09527820348739624, | |
| "learning_rate": 2.600664850273538e-05, | |
| "loss": 0.049, | |
| "num_input_tokens_seen": 3913120, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 1.5333333333333332, | |
| "grad_norm": 0.11391786485910416, | |
| "learning_rate": 2.399335149726463e-05, | |
| "loss": 0.0438, | |
| "num_input_tokens_seen": 4121248, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 1.6095238095238096, | |
| "grad_norm": 0.12547072768211365, | |
| "learning_rate": 2.1986582993616926e-05, | |
| "loss": 0.0474, | |
| "num_input_tokens_seen": 4327824, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.6857142857142857, | |
| "grad_norm": 0.09639491140842438, | |
| "learning_rate": 1.9999357655598893e-05, | |
| "loss": 0.0443, | |
| "num_input_tokens_seen": 4537936, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.7619047619047619, | |
| "grad_norm": 0.14130523800849915, | |
| "learning_rate": 1.8044563402088684e-05, | |
| "loss": 0.0429, | |
| "num_input_tokens_seen": 4744432, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.8380952380952382, | |
| "grad_norm": 0.08459249138832092, | |
| "learning_rate": 1.613487782393661e-05, | |
| "loss": 0.0421, | |
| "num_input_tokens_seen": 4955296, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.9142857142857141, | |
| "grad_norm": 0.12624752521514893, | |
| "learning_rate": 1.4282685964923642e-05, | |
| "loss": 0.0438, | |
| "num_input_tokens_seen": 5154784, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.9904761904761905, | |
| "grad_norm": 0.09155242145061493, | |
| "learning_rate": 1.2500000000000006e-05, | |
| "loss": 0.0387, | |
| "num_input_tokens_seen": 5358160, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.0761904761904764, | |
| "grad_norm": 0.08326593786478043, | |
| "learning_rate": 1.0798381331721109e-05, | |
| "loss": 0.0462, | |
| "num_input_tokens_seen": 5577808, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.1523809523809523, | |
| "grad_norm": 0.09486888349056244, | |
| "learning_rate": 9.18886561011557e-06, | |
| "loss": 0.0455, | |
| "num_input_tokens_seen": 5775552, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.2285714285714286, | |
| "grad_norm": 0.086710125207901, | |
| "learning_rate": 7.681891162260015e-06, | |
| "loss": 0.0389, | |
| "num_input_tokens_seen": 5986112, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 2.3047619047619046, | |
| "grad_norm": 0.09076906740665436, | |
| "learning_rate": 6.28723129572247e-06, | |
| "loss": 0.0505, | |
| "num_input_tokens_seen": 6185568, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 2.380952380952381, | |
| "grad_norm": 0.13775157928466797, | |
| "learning_rate": 5.013930914912476e-06, | |
| "loss": 0.0469, | |
| "num_input_tokens_seen": 6389392, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 2.4571428571428573, | |
| "grad_norm": 0.0946015864610672, | |
| "learning_rate": 3.8702478614051355e-06, | |
| "loss": 0.0382, | |
| "num_input_tokens_seen": 6594256, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 2.533333333333333, | |
| "grad_norm": 0.08834231644868851, | |
| "learning_rate": 2.8635993586697553e-06, | |
| "loss": 0.0359, | |
| "num_input_tokens_seen": 6802240, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 2.6095238095238096, | |
| "grad_norm": 0.10152524709701538, | |
| "learning_rate": 2.0005139085293945e-06, | |
| "loss": 0.0379, | |
| "num_input_tokens_seen": 7004816, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 2.685714285714286, | |
| "grad_norm": 0.10987098515033722, | |
| "learning_rate": 1.286588951321363e-06, | |
| "loss": 0.0416, | |
| "num_input_tokens_seen": 7208608, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 2.761904761904762, | |
| "grad_norm": 0.09526591747999191, | |
| "learning_rate": 7.264545643486997e-07, | |
| "loss": 0.0394, | |
| "num_input_tokens_seen": 7418320, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 2.8380952380952382, | |
| "grad_norm": 0.10505763441324234, | |
| "learning_rate": 3.237434340521789e-07, | |
| "loss": 0.0421, | |
| "num_input_tokens_seen": 7633248, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 2.914285714285714, | |
| "grad_norm": 0.09359151870012283, | |
| "learning_rate": 8.106729664475176e-08, | |
| "loss": 0.0377, | |
| "num_input_tokens_seen": 7838576, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 2.9904761904761905, | |
| "grad_norm": 0.10142253339290619, | |
| "learning_rate": 0.0, | |
| "loss": 0.0468, | |
| "num_input_tokens_seen": 8039616, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 2.9904761904761905, | |
| "num_input_tokens_seen": 8039616, | |
| "step": 195, | |
| "total_flos": 3.746792787278561e+17, | |
| "train_loss": 0.0682682229922368, | |
| "train_runtime": 5945.5431, | |
| "train_samples_per_second": 0.53, | |
| "train_steps_per_second": 0.033 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 195, | |
| "num_input_tokens_seen": 8039616, | |
| "num_train_epochs": 3, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.746792787278561e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |