| { | |
| "best_metric": 2.449061393737793, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-25", | |
| "epoch": 3.0726256983240225, | |
| "eval_steps": 25, | |
| "global_step": 34, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0893854748603352, | |
| "grad_norm": 2.2400944232940674, | |
| "learning_rate": 5e-05, | |
| "loss": 2.8325, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0893854748603352, | |
| "eval_loss": 3.1105024814605713, | |
| "eval_runtime": 4.2267, | |
| "eval_samples_per_second": 17.744, | |
| "eval_steps_per_second": 2.366, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1787709497206704, | |
| "grad_norm": 2.497319459915161, | |
| "learning_rate": 0.0001, | |
| "loss": 2.9649, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.2681564245810056, | |
| "grad_norm": 1.6535471677780151, | |
| "learning_rate": 9.975923633360985e-05, | |
| "loss": 2.7281, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.3575418994413408, | |
| "grad_norm": 0.5079431533813477, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 2.5012, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.44692737430167595, | |
| "grad_norm": 1.2886574268341064, | |
| "learning_rate": 9.784701678661045e-05, | |
| "loss": 2.5934, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5363128491620112, | |
| "grad_norm": 1.1388893127441406, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4472, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6256983240223464, | |
| "grad_norm": 0.6630513668060303, | |
| "learning_rate": 9.409606321741775e-05, | |
| "loss": 2.4627, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.7150837988826816, | |
| "grad_norm": 0.5299112200737, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.4937, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.8044692737430168, | |
| "grad_norm": 0.34606531262397766, | |
| "learning_rate": 8.865052266813685e-05, | |
| "loss": 2.3436, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8938547486033519, | |
| "grad_norm": 0.43447357416152954, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.3988, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.9832402234636871, | |
| "grad_norm": 0.6565023064613342, | |
| "learning_rate": 8.171966420818228e-05, | |
| "loss": 2.5196, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.0837988826815643, | |
| "grad_norm": 1.497651219367981, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 4.7115, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 1.1731843575418994, | |
| "grad_norm": 0.4036213159561157, | |
| "learning_rate": 7.35698368412999e-05, | |
| "loss": 2.3082, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 1.2625698324022347, | |
| "grad_norm": 0.35112711787223816, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.0545, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 1.3519553072625698, | |
| "grad_norm": 0.36122921109199524, | |
| "learning_rate": 6.451423386272312e-05, | |
| "loss": 2.4982, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 1.441340782122905, | |
| "grad_norm": 0.34908103942871094, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.3008, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 1.5307262569832403, | |
| "grad_norm": 0.2992340624332428, | |
| "learning_rate": 5.490085701647805e-05, | |
| "loss": 2.1225, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.6201117318435754, | |
| "grad_norm": 0.29938769340515137, | |
| "learning_rate": 5e-05, | |
| "loss": 2.3887, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.7094972067039107, | |
| "grad_norm": 0.46157407760620117, | |
| "learning_rate": 4.509914298352197e-05, | |
| "loss": 2.3315, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.7988826815642458, | |
| "grad_norm": 0.2835884392261505, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 2.1885, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.888268156424581, | |
| "grad_norm": 0.3236839175224304, | |
| "learning_rate": 3.5485766137276894e-05, | |
| "loss": 2.3413, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.9776536312849162, | |
| "grad_norm": 0.5033869743347168, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.3506, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 2.078212290502793, | |
| "grad_norm": 0.9654775261878967, | |
| "learning_rate": 2.6430163158700115e-05, | |
| "loss": 4.2699, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 2.1675977653631286, | |
| "grad_norm": 0.3320219814777374, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 2.2123, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 2.2569832402234637, | |
| "grad_norm": 0.3146689832210541, | |
| "learning_rate": 1.8280335791817733e-05, | |
| "loss": 1.8215, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.2569832402234637, | |
| "eval_loss": 2.449061393737793, | |
| "eval_runtime": 4.2282, | |
| "eval_samples_per_second": 17.738, | |
| "eval_steps_per_second": 2.365, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 2.346368715083799, | |
| "grad_norm": 0.3303333520889282, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.624, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 2.435754189944134, | |
| "grad_norm": 0.3606821298599243, | |
| "learning_rate": 1.134947733186315e-05, | |
| "loss": 2.1936, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 2.5251396648044695, | |
| "grad_norm": 0.28290900588035583, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.9875, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 2.6145251396648046, | |
| "grad_norm": 0.3111993074417114, | |
| "learning_rate": 5.903936782582253e-06, | |
| "loss": 2.3929, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 2.7039106145251397, | |
| "grad_norm": 0.3869682848453522, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 2.2854, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 2.793296089385475, | |
| "grad_norm": 0.27436700463294983, | |
| "learning_rate": 2.152983213389559e-06, | |
| "loss": 2.072, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 2.88268156424581, | |
| "grad_norm": 0.3000536859035492, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 2.3339, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 2.972067039106145, | |
| "grad_norm": 0.4352191388607025, | |
| "learning_rate": 2.407636663901591e-07, | |
| "loss": 2.3471, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 3.0726256983240225, | |
| "grad_norm": 1.0655169486999512, | |
| "learning_rate": 0.0, | |
| "loss": 4.1814, | |
| "step": 34 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 34, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.509339571988726e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |