| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.869565217391305, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.17391304347826086, | |
| "grad_norm": 0.5795015692710876, | |
| "learning_rate": 4e-05, | |
| "loss": 2.6851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.34782608695652173, | |
| "grad_norm": 0.6652081608772278, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5809, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.5217391304347826, | |
| "grad_norm": 0.3569735884666443, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2489, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6956521739130435, | |
| "grad_norm": 0.5530170798301697, | |
| "learning_rate": 0.00016, | |
| "loss": 2.6054, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.8695652173913043, | |
| "grad_norm": 0.9040398597717285, | |
| "learning_rate": 0.0002, | |
| "loss": 2.6919, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.0869565217391304, | |
| "grad_norm": 1.6528335809707642, | |
| "learning_rate": 0.00019636363636363636, | |
| "loss": 3.4822, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.2608695652173914, | |
| "grad_norm": 0.5991894602775574, | |
| "learning_rate": 0.00019272727272727274, | |
| "loss": 1.5508, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.434782608695652, | |
| "grad_norm": 1.1784238815307617, | |
| "learning_rate": 0.0001890909090909091, | |
| "loss": 2.3071, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.608695652173913, | |
| "grad_norm": 1.242445468902588, | |
| "learning_rate": 0.00018545454545454545, | |
| "loss": 2.4738, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.7826086956521738, | |
| "grad_norm": 1.0758299827575684, | |
| "learning_rate": 0.00018181818181818183, | |
| "loss": 1.5476, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.9565217391304348, | |
| "grad_norm": 1.110364317893982, | |
| "learning_rate": 0.0001781818181818182, | |
| "loss": 2.0381, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 2.1739130434782608, | |
| "grad_norm": 0.5819414258003235, | |
| "learning_rate": 0.00017454545454545454, | |
| "loss": 1.6068, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.3478260869565215, | |
| "grad_norm": 0.6612680554389954, | |
| "learning_rate": 0.0001709090909090909, | |
| "loss": 1.9076, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.5217391304347827, | |
| "grad_norm": 0.5913424491882324, | |
| "learning_rate": 0.00016727272727272728, | |
| "loss": 1.2975, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.6956521739130435, | |
| "grad_norm": 0.8625181317329407, | |
| "learning_rate": 0.00016363636363636366, | |
| "loss": 1.6797, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.869565217391304, | |
| "grad_norm": 0.8947856426239014, | |
| "learning_rate": 0.00016, | |
| "loss": 1.3828, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 3.0869565217391304, | |
| "grad_norm": 0.6648727655410767, | |
| "learning_rate": 0.00015636363636363637, | |
| "loss": 2.1334, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 3.260869565217391, | |
| "grad_norm": 0.6269745826721191, | |
| "learning_rate": 0.00015272727272727275, | |
| "loss": 1.2481, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.4347826086956523, | |
| "grad_norm": 0.9015301465988159, | |
| "learning_rate": 0.0001490909090909091, | |
| "loss": 1.5312, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 3.608695652173913, | |
| "grad_norm": 0.56430983543396, | |
| "learning_rate": 0.00014545454545454546, | |
| "loss": 1.1648, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 3.782608695652174, | |
| "grad_norm": 0.6650995016098022, | |
| "learning_rate": 0.00014181818181818184, | |
| "loss": 1.9122, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 3.9565217391304346, | |
| "grad_norm": 1.211255669593811, | |
| "learning_rate": 0.0001381818181818182, | |
| "loss": 1.905, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 4.173913043478261, | |
| "grad_norm": 0.8868653178215027, | |
| "learning_rate": 0.00013454545454545455, | |
| "loss": 1.0216, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 4.3478260869565215, | |
| "grad_norm": 1.4661606550216675, | |
| "learning_rate": 0.00013090909090909093, | |
| "loss": 1.2432, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 4.521739130434782, | |
| "grad_norm": 0.5382258892059326, | |
| "learning_rate": 0.00012727272727272728, | |
| "loss": 1.2831, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 4.695652173913043, | |
| "grad_norm": 1.1182520389556885, | |
| "learning_rate": 0.00012363636363636364, | |
| "loss": 1.0676, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 4.869565217391305, | |
| "grad_norm": 0.7625539898872375, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2568, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 5.086956521739131, | |
| "grad_norm": 1.9197959899902344, | |
| "learning_rate": 0.00011636363636363636, | |
| "loss": 1.4596, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 5.260869565217392, | |
| "grad_norm": 1.1358859539031982, | |
| "learning_rate": 0.00011272727272727272, | |
| "loss": 0.6785, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 5.434782608695652, | |
| "grad_norm": 2.8852992057800293, | |
| "learning_rate": 0.00010909090909090909, | |
| "loss": 0.9755, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 5.608695652173913, | |
| "grad_norm": 2.618217945098877, | |
| "learning_rate": 0.00010545454545454545, | |
| "loss": 0.9123, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 5.782608695652174, | |
| "grad_norm": 1.0614593029022217, | |
| "learning_rate": 0.00010181818181818181, | |
| "loss": 1.5262, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 5.956521739130435, | |
| "grad_norm": 2.063232898712158, | |
| "learning_rate": 9.818181818181818e-05, | |
| "loss": 1.3585, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 6.173913043478261, | |
| "grad_norm": 1.3435719013214111, | |
| "learning_rate": 9.454545454545455e-05, | |
| "loss": 0.9793, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 6.3478260869565215, | |
| "grad_norm": 1.4425543546676636, | |
| "learning_rate": 9.090909090909092e-05, | |
| "loss": 0.8326, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 6.521739130434782, | |
| "grad_norm": 1.411342740058899, | |
| "learning_rate": 8.727272727272727e-05, | |
| "loss": 0.7428, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 6.695652173913043, | |
| "grad_norm": 2.045598268508911, | |
| "learning_rate": 8.363636363636364e-05, | |
| "loss": 0.816, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 6.869565217391305, | |
| "grad_norm": 1.8088502883911133, | |
| "learning_rate": 8e-05, | |
| "loss": 0.7132, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 7.086956521739131, | |
| "grad_norm": 2.4303224086761475, | |
| "learning_rate": 7.636363636363637e-05, | |
| "loss": 1.2982, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 7.260869565217392, | |
| "grad_norm": 1.6079760789871216, | |
| "learning_rate": 7.272727272727273e-05, | |
| "loss": 0.7633, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 7.434782608695652, | |
| "grad_norm": 1.357133388519287, | |
| "learning_rate": 6.90909090909091e-05, | |
| "loss": 0.4112, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 7.608695652173913, | |
| "grad_norm": 1.36146080493927, | |
| "learning_rate": 6.545454545454546e-05, | |
| "loss": 0.4352, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 7.782608695652174, | |
| "grad_norm": 1.250328540802002, | |
| "learning_rate": 6.181818181818182e-05, | |
| "loss": 1.0597, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 7.956521739130435, | |
| "grad_norm": 2.3408303260803223, | |
| "learning_rate": 5.818181818181818e-05, | |
| "loss": 0.6463, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 8.173913043478262, | |
| "grad_norm": 1.5889191627502441, | |
| "learning_rate": 5.4545454545454546e-05, | |
| "loss": 0.6388, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 8.347826086956522, | |
| "grad_norm": 0.8752424120903015, | |
| "learning_rate": 5.090909090909091e-05, | |
| "loss": 0.7383, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 8.521739130434783, | |
| "grad_norm": 1.2275079488754272, | |
| "learning_rate": 4.7272727272727275e-05, | |
| "loss": 0.4331, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 8.695652173913043, | |
| "grad_norm": 1.4064780473709106, | |
| "learning_rate": 4.3636363636363636e-05, | |
| "loss": 0.3424, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 8.869565217391305, | |
| "grad_norm": 1.825239896774292, | |
| "learning_rate": 4e-05, | |
| "loss": 0.5151, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 9.08695652173913, | |
| "grad_norm": 3.0296473503112793, | |
| "learning_rate": 3.6363636363636364e-05, | |
| "loss": 0.5569, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 9.26086956521739, | |
| "grad_norm": 1.301712155342102, | |
| "learning_rate": 3.272727272727273e-05, | |
| "loss": 0.3894, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 9.434782608695652, | |
| "grad_norm": 1.1728489398956299, | |
| "learning_rate": 2.909090909090909e-05, | |
| "loss": 0.8132, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 9.608695652173914, | |
| "grad_norm": 1.175506830215454, | |
| "learning_rate": 2.5454545454545454e-05, | |
| "loss": 0.2151, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 9.782608695652174, | |
| "grad_norm": 0.9729976058006287, | |
| "learning_rate": 2.1818181818181818e-05, | |
| "loss": 0.1576, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 9.956521739130435, | |
| "grad_norm": 2.4422378540039062, | |
| "learning_rate": 1.8181818181818182e-05, | |
| "loss": 0.4448, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 10.173913043478262, | |
| "grad_norm": 1.0331871509552002, | |
| "learning_rate": 1.4545454545454545e-05, | |
| "loss": 0.1602, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 10.347826086956522, | |
| "grad_norm": 0.9095517992973328, | |
| "learning_rate": 1.0909090909090909e-05, | |
| "loss": 0.6064, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 10.521739130434783, | |
| "grad_norm": 1.2574269771575928, | |
| "learning_rate": 7.272727272727272e-06, | |
| "loss": 0.2496, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 10.695652173913043, | |
| "grad_norm": 1.1020245552062988, | |
| "learning_rate": 3.636363636363636e-06, | |
| "loss": 0.185, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 10.869565217391305, | |
| "grad_norm": 1.7821040153503418, | |
| "learning_rate": 0.0, | |
| "loss": 0.5375, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 60, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 12, | |
| "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": 6160960925368320.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |