| { | |
| "best_metric": 1.621693730354309, | |
| "best_model_checkpoint": "./lora-out/checkpoint-50", | |
| "epoch": 0.15552099533437014, | |
| "eval_steps": 50, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0, | |
| "learning_rate": 2e-05, | |
| "loss": 1.7924, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8083, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8177, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7595, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.0001, | |
| "loss": 1.6598, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6919, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6706, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02, | |
| "learning_rate": 0.00016, | |
| "loss": 1.6879, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7051, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7022, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.000199999456645141, | |
| "loss": 1.6809, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019999782658646859, | |
| "loss": 1.6098, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.0001999951098416968, | |
| "loss": 1.7014, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00019999130644034888, | |
| "loss": 1.5885, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019998641642375657, | |
| "loss": 1.6243, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019998043984506027, | |
| "loss": 1.6484, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00019997337676920803, | |
| "loss": 1.6093, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019996522727295496, | |
| "loss": 1.6173, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019995599144486247, | |
| "loss": 1.646, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.00019994566938529712, | |
| "loss": 1.6469, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019993426120642983, | |
| "loss": 1.6564, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019992176703223432, | |
| "loss": 1.5901, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.000199908186998486, | |
| "loss": 1.664, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 0.00019989352125276047, | |
| "loss": 1.6275, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019987776995443178, | |
| "loss": 1.5839, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019986093327467076, | |
| "loss": 1.5611, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.00019984301139644334, | |
| "loss": 1.669, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0001998240045145083, | |
| "loss": 1.5641, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019980391283541522, | |
| "loss": 1.6023, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.00019978273657750238, | |
| "loss": 1.6309, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0001997604759708942, | |
| "loss": 1.6353, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019973713125749884, | |
| "loss": 1.6328, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.00019971270269100564, | |
| "loss": 1.5683, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019968719053688213, | |
| "loss": 1.6217, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.0001996605950723714, | |
| "loss": 1.5734, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.11, | |
| "learning_rate": 0.00019963291658648896, | |
| "loss": 1.6162, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019960415538001957, | |
| "loss": 1.5922, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.0001995743117655141, | |
| "loss": 1.5806, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.000199543386067286, | |
| "loss": 1.5938, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00019951137862140778, | |
| "loss": 1.6386, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019947828977570756, | |
| "loss": 1.6476, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019944411988976496, | |
| "loss": 1.6557, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.00019940886933490749, | |
| "loss": 1.5836, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019937253849420635, | |
| "loss": 1.6421, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.0001993351277624723, | |
| "loss": 1.629, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00019929663754625145, | |
| "loss": 1.6392, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019925706826382064, | |
| "loss": 1.5677, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019921642034518317, | |
| "loss": 1.6144, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.00019917469423206389, | |
| "loss": 1.6068, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "learning_rate": 0.00019913189037790456, | |
| "loss": 1.6421, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16, | |
| "eval_loss": 1.621693730354309, | |
| "eval_runtime": 233.7603, | |
| "eval_samples_per_second": 16.354, | |
| "eval_steps_per_second": 4.09, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 963, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "total_flos": 1.402135828758528e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |