| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.06845798391237377, | |
| "eval_steps": 500, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0013691596782474755, | |
| "grad_norm": 3.442312002182007, | |
| "learning_rate": 0.0001, | |
| "loss": 2.1747, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002738319356494951, | |
| "grad_norm": 3.3342490196228027, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0423, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004107479034742427, | |
| "grad_norm": 2.533416986465454, | |
| "learning_rate": 0.00019978589232386035, | |
| "loss": 1.6375, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005476638712989902, | |
| "grad_norm": 1.5912055969238281, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 0.9787, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.006845798391237378, | |
| "grad_norm": 1.6528733968734741, | |
| "learning_rate": 0.00019807852804032305, | |
| "loss": 1.1491, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008214958069484853, | |
| "grad_norm": 2.063443422317505, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 1.0858, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.009584117747732329, | |
| "grad_norm": 2.0438201427459717, | |
| "learning_rate": 0.0001946930129495106, | |
| "loss": 0.9206, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.010953277425979804, | |
| "grad_norm": 1.7179049253463745, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 0.9812, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01232243710422728, | |
| "grad_norm": 1.064609408378601, | |
| "learning_rate": 0.00018968727415326884, | |
| "loss": 1.097, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013691596782474755, | |
| "grad_norm": 1.3474338054656982, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 1.0998, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015060756460722231, | |
| "grad_norm": 0.9349080920219421, | |
| "learning_rate": 0.00018314696123025454, | |
| "loss": 0.7325, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.016429916138969707, | |
| "grad_norm": 1.1312912702560425, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 1.0285, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.017799075817217184, | |
| "grad_norm": 1.008134126663208, | |
| "learning_rate": 0.00017518398074789775, | |
| "loss": 0.7593, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.019168235495464658, | |
| "grad_norm": 0.9038427472114563, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 0.7422, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.020537395173712135, | |
| "grad_norm": 1.281387448310852, | |
| "learning_rate": 0.00016593458151000688, | |
| "loss": 0.8447, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02190655485195961, | |
| "grad_norm": 0.9998169541358948, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 0.8007, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.023275714530207086, | |
| "grad_norm": 0.9114604592323303, | |
| "learning_rate": 0.00015555702330196023, | |
| "loss": 0.8013, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.02464487420845456, | |
| "grad_norm": 1.1608867645263672, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.0643, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.026014033886702037, | |
| "grad_norm": 1.2039852142333984, | |
| "learning_rate": 0.00014422886902190014, | |
| "loss": 0.8865, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.02738319356494951, | |
| "grad_norm": 0.898479700088501, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 0.619, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.028752353243196988, | |
| "grad_norm": 1.2546143531799316, | |
| "learning_rate": 0.00013214394653031616, | |
| "loss": 0.9154, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.030121512921444462, | |
| "grad_norm": 0.962232232093811, | |
| "learning_rate": 0.00012588190451025207, | |
| "loss": 0.7535, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.03149067259969194, | |
| "grad_norm": 1.122208595275879, | |
| "learning_rate": 0.00011950903220161285, | |
| "loss": 0.8251, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.03285983227793941, | |
| "grad_norm": 1.0500138998031616, | |
| "learning_rate": 0.00011305261922200519, | |
| "loss": 0.8844, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03422899195618689, | |
| "grad_norm": 1.0177123546600342, | |
| "learning_rate": 0.00010654031292301432, | |
| "loss": 1.0503, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03559815163443437, | |
| "grad_norm": 0.9960324168205261, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8392, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.03696731131268184, | |
| "grad_norm": 1.3512423038482666, | |
| "learning_rate": 9.345968707698569e-05, | |
| "loss": 0.8133, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.038336470990929315, | |
| "grad_norm": 1.276644229888916, | |
| "learning_rate": 8.694738077799488e-05, | |
| "loss": 0.684, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.039705630669176796, | |
| "grad_norm": 1.1981127262115479, | |
| "learning_rate": 8.049096779838719e-05, | |
| "loss": 0.8897, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.04107479034742427, | |
| "grad_norm": 1.1705209016799927, | |
| "learning_rate": 7.411809548974792e-05, | |
| "loss": 0.813, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.042443950025671744, | |
| "grad_norm": 1.0239105224609375, | |
| "learning_rate": 6.785605346968386e-05, | |
| "loss": 0.7486, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.04381310970391922, | |
| "grad_norm": 0.9569729566574097, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 0.8043, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0451822693821667, | |
| "grad_norm": 0.8030011057853699, | |
| "learning_rate": 5.577113097809989e-05, | |
| "loss": 0.7549, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.04655142906041417, | |
| "grad_norm": 1.0001657009124756, | |
| "learning_rate": 5.000000000000002e-05, | |
| "loss": 0.8386, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.047920588738661646, | |
| "grad_norm": 1.130332112312317, | |
| "learning_rate": 4.444297669803981e-05, | |
| "loss": 0.6993, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04928974841690912, | |
| "grad_norm": 0.7636102437973022, | |
| "learning_rate": 3.9123857099127936e-05, | |
| "loss": 0.6943, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.0506589080951566, | |
| "grad_norm": 0.8889525532722473, | |
| "learning_rate": 3.406541848999312e-05, | |
| "loss": 0.8767, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.052028067773404074, | |
| "grad_norm": 0.9144881963729858, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 0.765, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.05339722745165155, | |
| "grad_norm": 1.054382562637329, | |
| "learning_rate": 2.4816019252102273e-05, | |
| "loss": 1.0028, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.05476638712989902, | |
| "grad_norm": 1.131859302520752, | |
| "learning_rate": 2.0664665970876496e-05, | |
| "loss": 0.9122, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0561355468081465, | |
| "grad_norm": 0.8449717164039612, | |
| "learning_rate": 1.6853038769745467e-05, | |
| "loss": 0.8733, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.057504706486393976, | |
| "grad_norm": 1.1658316850662231, | |
| "learning_rate": 1.339745962155613e-05, | |
| "loss": 0.8213, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.05887386616464145, | |
| "grad_norm": 0.9214019775390625, | |
| "learning_rate": 1.0312725846731175e-05, | |
| "loss": 0.867, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.060243025842888924, | |
| "grad_norm": 1.1125028133392334, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 0.9207, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.061612185521136405, | |
| "grad_norm": 0.6265993714332581, | |
| "learning_rate": 5.306987050489442e-06, | |
| "loss": 0.5684, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06298134519938388, | |
| "grad_norm": 0.9214088320732117, | |
| "learning_rate": 3.40741737109318e-06, | |
| "loss": 0.5572, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.06435050487763136, | |
| "grad_norm": 0.7752699851989746, | |
| "learning_rate": 1.921471959676957e-06, | |
| "loss": 0.6001, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.06571966455587883, | |
| "grad_norm": 0.8832862973213196, | |
| "learning_rate": 8.555138626189618e-07, | |
| "loss": 0.8986, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0670888242341263, | |
| "grad_norm": 0.9648825526237488, | |
| "learning_rate": 2.141076761396521e-07, | |
| "loss": 0.9162, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.06845798391237377, | |
| "grad_norm": 0.7902650833129883, | |
| "learning_rate": 0.0, | |
| "loss": 0.7039, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.66894361542656e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |