| { | |
| "best_metric": 0.002865403890609741, | |
| "best_model_checkpoint": "/home/paperspace/Data/models/mini_akash_unifo_757/llm3br256/checkpoint-25", | |
| "epoch": 22.22222222222222, | |
| "eval_steps": 5, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.11804743856191635, | |
| "learning_rate": 3.3333333333333335e-05, | |
| "loss": 0.0298, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 0.2355736345052719, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 0.0525, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 0.12409032136201859, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0337, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.5555555555555554, | |
| "grad_norm": 0.09876855462789536, | |
| "learning_rate": 9.949107209404665e-05, | |
| "loss": 0.0213, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "grad_norm": 0.04545082896947861, | |
| "learning_rate": 9.797464868072488e-05, | |
| "loss": 0.0145, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 4.444444444444445, | |
| "eval_loss": 0.009283961728215218, | |
| "eval_runtime": 21.8614, | |
| "eval_samples_per_second": 4.574, | |
| "eval_steps_per_second": 0.137, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 5.333333333333333, | |
| "grad_norm": 0.03416820988059044, | |
| "learning_rate": 9.548159976772592e-05, | |
| "loss": 0.0165, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 6.222222222222222, | |
| "grad_norm": 0.038880299776792526, | |
| "learning_rate": 9.206267664155907e-05, | |
| "loss": 0.0108, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 7.111111111111111, | |
| "grad_norm": 0.03544820472598076, | |
| "learning_rate": 8.778747871771292e-05, | |
| "loss": 0.018, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 0.02577349916100502, | |
| "learning_rate": 8.274303669726426e-05, | |
| "loss": 0.015, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "grad_norm": 0.00962463952600956, | |
| "learning_rate": 7.703204087277988e-05, | |
| "loss": 0.0052, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 8.88888888888889, | |
| "eval_loss": 0.005674231797456741, | |
| "eval_runtime": 20.7415, | |
| "eval_samples_per_second": 4.821, | |
| "eval_steps_per_second": 0.145, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 9.777777777777779, | |
| "grad_norm": 0.0239880234003067, | |
| "learning_rate": 7.077075065009433e-05, | |
| "loss": 0.0129, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 10.666666666666666, | |
| "grad_norm": 0.01791444607079029, | |
| "learning_rate": 6.408662784207149e-05, | |
| "loss": 0.0059, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 11.555555555555555, | |
| "grad_norm": 0.02006041631102562, | |
| "learning_rate": 5.7115741913664264e-05, | |
| "loss": 0.0074, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 12.444444444444445, | |
| "grad_norm": 0.01566292718052864, | |
| "learning_rate": 5e-05, | |
| "loss": 0.006, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "grad_norm": 0.013569545932114124, | |
| "learning_rate": 4.288425808633575e-05, | |
| "loss": 0.0042, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 13.333333333333334, | |
| "eval_loss": 0.0036138412542641163, | |
| "eval_runtime": 20.7336, | |
| "eval_samples_per_second": 4.823, | |
| "eval_steps_per_second": 0.145, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 14.222222222222221, | |
| "grad_norm": 0.018722472712397575, | |
| "learning_rate": 3.591337215792852e-05, | |
| "loss": 0.0059, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 15.11111111111111, | |
| "grad_norm": 0.015830494463443756, | |
| "learning_rate": 2.9229249349905684e-05, | |
| "loss": 0.0054, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 16.0, | |
| "grad_norm": 0.008228328078985214, | |
| "learning_rate": 2.296795912722014e-05, | |
| "loss": 0.0031, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 16.88888888888889, | |
| "grad_norm": 0.004453725181519985, | |
| "learning_rate": 1.725696330273575e-05, | |
| "loss": 0.0024, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "grad_norm": 0.00990860816091299, | |
| "learning_rate": 1.2212521282287092e-05, | |
| "loss": 0.0029, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 17.77777777777778, | |
| "eval_loss": 0.002966933185234666, | |
| "eval_runtime": 20.7595, | |
| "eval_samples_per_second": 4.817, | |
| "eval_steps_per_second": 0.145, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 18.666666666666668, | |
| "grad_norm": 0.014893569052219391, | |
| "learning_rate": 7.937323358440935e-06, | |
| "loss": 0.0044, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 19.555555555555557, | |
| "grad_norm": 0.02214457094669342, | |
| "learning_rate": 4.5184002322740785e-06, | |
| "loss": 0.0047, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 20.444444444444443, | |
| "grad_norm": 0.011282005347311497, | |
| "learning_rate": 2.0253513192751373e-06, | |
| "loss": 0.0032, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 21.333333333333332, | |
| "grad_norm": 0.018609197810292244, | |
| "learning_rate": 5.089279059533658e-07, | |
| "loss": 0.0051, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "grad_norm": 0.021045828238129616, | |
| "learning_rate": 0.0, | |
| "loss": 0.0069, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "eval_loss": 0.002865403890609741, | |
| "eval_runtime": 20.7378, | |
| "eval_samples_per_second": 4.822, | |
| "eval_steps_per_second": 0.145, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 22.22222222222222, | |
| "step": 25, | |
| "total_flos": 5.258686279131464e+17, | |
| "train_loss": 0.011901103416457772, | |
| "train_runtime": 3766.8706, | |
| "train_samples_per_second": 1.991, | |
| "train_steps_per_second": 0.007 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 25, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 25, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 5, | |
| "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": 5.258686279131464e+17, | |
| "train_batch_size": 36, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |