| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.99728014505893, | |
| "eval_steps": 500, | |
| "global_step": 880, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.11332728921124206, | |
| "grad_norm": 12.256142616271973, | |
| "learning_rate": 3.2000000000000003e-06, | |
| "loss": 6.768, | |
| "num_input_tokens_seen": 320000, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.22665457842248413, | |
| "grad_norm": 14.015169143676758, | |
| "learning_rate": 6.533333333333334e-06, | |
| "loss": 2.2714, | |
| "num_input_tokens_seen": 640000, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.3399818676337262, | |
| "grad_norm": 2.729668140411377, | |
| "learning_rate": 9.866666666666668e-06, | |
| "loss": 1.6663, | |
| "num_input_tokens_seen": 960000, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.45330915684496825, | |
| "grad_norm": 2.5849289894104004, | |
| "learning_rate": 1.3200000000000002e-05, | |
| "loss": 1.5351, | |
| "num_input_tokens_seen": 1280000, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.5666364460562103, | |
| "grad_norm": 2.5873868465423584, | |
| "learning_rate": 1.6533333333333333e-05, | |
| "loss": 1.4698, | |
| "num_input_tokens_seen": 1600000, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 0.6799637352674524, | |
| "grad_norm": 1.8172498941421509, | |
| "learning_rate": 1.9866666666666667e-05, | |
| "loss": 1.4164, | |
| "num_input_tokens_seen": 1920000, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.7932910244786945, | |
| "grad_norm": 3.378293037414551, | |
| "learning_rate": 1.994670819911521e-05, | |
| "loss": 1.3952, | |
| "num_input_tokens_seen": 2239840, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 0.9066183136899365, | |
| "grad_norm": 1.4730700254440308, | |
| "learning_rate": 1.977848341505657e-05, | |
| "loss": 1.3792, | |
| "num_input_tokens_seen": 2559800, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.0226654578422485, | |
| "grad_norm": 1.2745240926742554, | |
| "learning_rate": 1.949717842791432e-05, | |
| "loss": 1.3537, | |
| "num_input_tokens_seen": 2884920, | |
| "step": 225 | |
| }, | |
| { | |
| "epoch": 1.1359927470534905, | |
| "grad_norm": 1.7677239179611206, | |
| "learning_rate": 1.9106046300942165e-05, | |
| "loss": 1.2956, | |
| "num_input_tokens_seen": 3204920, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 1.2493200362647325, | |
| "grad_norm": 1.9639768600463867, | |
| "learning_rate": 1.8609610158889943e-05, | |
| "loss": 1.2642, | |
| "num_input_tokens_seen": 3524920, | |
| "step": 275 | |
| }, | |
| { | |
| "epoch": 1.3626473254759746, | |
| "grad_norm": 1.738120436668396, | |
| "learning_rate": 1.8013610881746767e-05, | |
| "loss": 1.2527, | |
| "num_input_tokens_seen": 3844920, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 1.4759746146872166, | |
| "grad_norm": 1.5475760698318481, | |
| "learning_rate": 1.732494071613579e-05, | |
| "loss": 1.2602, | |
| "num_input_tokens_seen": 4164920, | |
| "step": 325 | |
| }, | |
| { | |
| "epoch": 1.5893019038984586, | |
| "grad_norm": 1.3410508632659912, | |
| "learning_rate": 1.6551563572090855e-05, | |
| "loss": 1.2551, | |
| "num_input_tokens_seen": 4484840, | |
| "step": 350 | |
| }, | |
| { | |
| "epoch": 1.7026291931097008, | |
| "grad_norm": 1.6581236124038696, | |
| "learning_rate": 1.5702422926917872e-05, | |
| "loss": 1.2325, | |
| "num_input_tokens_seen": 4804840, | |
| "step": 375 | |
| }, | |
| { | |
| "epoch": 1.8159564823209429, | |
| "grad_norm": 1.8297406435012817, | |
| "learning_rate": 1.4787338401157888e-05, | |
| "loss": 1.2436, | |
| "num_input_tokens_seen": 5124840, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 1.929283771532185, | |
| "grad_norm": 1.9106981754302979, | |
| "learning_rate": 1.3816892202666591e-05, | |
| "loss": 1.2319, | |
| "num_input_tokens_seen": 5444840, | |
| "step": 425 | |
| }, | |
| { | |
| "epoch": 2.045330915684497, | |
| "grad_norm": 1.4120745658874512, | |
| "learning_rate": 1.2802306751992163e-05, | |
| "loss": 1.2132, | |
| "num_input_tokens_seen": 5769800, | |
| "step": 450 | |
| }, | |
| { | |
| "epoch": 2.158658204895739, | |
| "grad_norm": 1.541704535484314, | |
| "learning_rate": 1.1755314904214284e-05, | |
| "loss": 1.0794, | |
| "num_input_tokens_seen": 6089800, | |
| "step": 475 | |
| }, | |
| { | |
| "epoch": 2.271985494106981, | |
| "grad_norm": 2.239482879638672, | |
| "learning_rate": 1.06880242680232e-05, | |
| "loss": 1.0779, | |
| "num_input_tokens_seen": 6409680, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 2.385312783318223, | |
| "grad_norm": 2.1483075618743896, | |
| "learning_rate": 9.612777191078257e-06, | |
| "loss": 1.0722, | |
| "num_input_tokens_seen": 6729680, | |
| "step": 525 | |
| }, | |
| { | |
| "epoch": 2.498640072529465, | |
| "grad_norm": 1.631958246231079, | |
| "learning_rate": 8.542008030801254e-06, | |
| "loss": 1.0663, | |
| "num_input_tokens_seen": 7049680, | |
| "step": 550 | |
| }, | |
| { | |
| "epoch": 2.611967361740707, | |
| "grad_norm": 1.948183298110962, | |
| "learning_rate": 7.4880993611518095e-06, | |
| "loss": 1.056, | |
| "num_input_tokens_seen": 7369680, | |
| "step": 575 | |
| }, | |
| { | |
| "epoch": 2.725294650951949, | |
| "grad_norm": 1.8783904314041138, | |
| "learning_rate": 6.463238778236287e-06, | |
| "loss": 1.0578, | |
| "num_input_tokens_seen": 7689680, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 2.838621940163191, | |
| "grad_norm": 2.3182311058044434, | |
| "learning_rate": 5.479277960676959e-06, | |
| "loss": 1.0531, | |
| "num_input_tokens_seen": 8009600, | |
| "step": 625 | |
| }, | |
| { | |
| "epoch": 2.951949229374433, | |
| "grad_norm": 2.483482837677002, | |
| "learning_rate": 4.547595614593489e-06, | |
| "loss": 1.0523, | |
| "num_input_tokens_seen": 8329600, | |
| "step": 650 | |
| }, | |
| { | |
| "epoch": 3.067996373526745, | |
| "grad_norm": 1.3066755533218384, | |
| "learning_rate": 3.6789658881265135e-06, | |
| "loss": 1.0127, | |
| "num_input_tokens_seen": 8654720, | |
| "step": 675 | |
| }, | |
| { | |
| "epoch": 3.1813236627379875, | |
| "grad_norm": 1.4423686265945435, | |
| "learning_rate": 2.883433777182255e-06, | |
| "loss": 0.9245, | |
| "num_input_tokens_seen": 8974520, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 3.2946509519492295, | |
| "grad_norm": 2.5524277687072754, | |
| "learning_rate": 2.170198963229372e-06, | |
| "loss": 0.918, | |
| "num_input_tokens_seen": 9294520, | |
| "step": 725 | |
| }, | |
| { | |
| "epoch": 3.4079782411604715, | |
| "grad_norm": 1.343592882156372, | |
| "learning_rate": 1.547509426469368e-06, | |
| "loss": 0.9192, | |
| "num_input_tokens_seen": 9614520, | |
| "step": 750 | |
| }, | |
| { | |
| "epoch": 3.5213055303717136, | |
| "grad_norm": 1.9703131914138794, | |
| "learning_rate": 1.022566064657663e-06, | |
| "loss": 0.9177, | |
| "num_input_tokens_seen": 9934520, | |
| "step": 775 | |
| }, | |
| { | |
| "epoch": 3.6346328195829556, | |
| "grad_norm": 2.417506694793701, | |
| "learning_rate": 6.01439420581047e-07, | |
| "loss": 0.9152, | |
| "num_input_tokens_seen": 10254520, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 3.7479601087941976, | |
| "grad_norm": 1.23152494430542, | |
| "learning_rate": 2.889994811704966e-07, | |
| "loss": 0.917, | |
| "num_input_tokens_seen": 10574520, | |
| "step": 825 | |
| }, | |
| { | |
| "epoch": 3.8612873980054396, | |
| "grad_norm": 1.5819039344787598, | |
| "learning_rate": 8.885936006545304e-08, | |
| "loss": 0.912, | |
| "num_input_tokens_seen": 10894520, | |
| "step": 850 | |
| }, | |
| { | |
| "epoch": 3.9746146872166817, | |
| "grad_norm": 1.4086824655532837, | |
| "learning_rate": 3.333514894887646e-09, | |
| "loss": 0.9239, | |
| "num_input_tokens_seen": 11214520, | |
| "step": 875 | |
| }, | |
| { | |
| "epoch": 3.99728014505893, | |
| "num_input_tokens_seen": 11278520, | |
| "step": 880, | |
| "total_flos": 7.651349314204147e+17, | |
| "train_loss": 1.351207665421746, | |
| "train_runtime": 8552.2085, | |
| "train_samples_per_second": 2.578, | |
| "train_steps_per_second": 0.103 | |
| } | |
| ], | |
| "logging_steps": 25, | |
| "max_steps": 880, | |
| "num_input_tokens_seen": 11278520, | |
| "num_train_epochs": 4, | |
| "save_steps": 250, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.651349314204147e+17, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |