| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0036533016713855147, | |
| "eval_steps": 13, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.306603342771029e-05, | |
| "grad_norm": 0.28918322920799255, | |
| "learning_rate": 2e-05, | |
| "loss": 10.8636, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.306603342771029e-05, | |
| "eval_loss": 10.86647891998291, | |
| "eval_runtime": 22.1337, | |
| "eval_samples_per_second": 260.372, | |
| "eval_steps_per_second": 130.209, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00014613206685542058, | |
| "grad_norm": 0.2704920768737793, | |
| "learning_rate": 4e-05, | |
| "loss": 10.8678, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00021919810028313088, | |
| "grad_norm": 0.320715069770813, | |
| "learning_rate": 6e-05, | |
| "loss": 10.8699, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00029226413371084115, | |
| "grad_norm": 0.2879772484302521, | |
| "learning_rate": 8e-05, | |
| "loss": 10.871, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00036533016713855145, | |
| "grad_norm": 0.29102233052253723, | |
| "learning_rate": 0.0001, | |
| "loss": 10.8623, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00043839620056626175, | |
| "grad_norm": 0.28974610567092896, | |
| "learning_rate": 0.00012, | |
| "loss": 10.8671, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005114622339939721, | |
| "grad_norm": 0.3089694082736969, | |
| "learning_rate": 0.00014, | |
| "loss": 10.8637, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005845282674216823, | |
| "grad_norm": 0.2890279293060303, | |
| "learning_rate": 0.00016, | |
| "loss": 10.861, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006575943008493927, | |
| "grad_norm": 0.2911294400691986, | |
| "learning_rate": 0.00018, | |
| "loss": 10.86, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007306603342771029, | |
| "grad_norm": 0.2866094410419464, | |
| "learning_rate": 0.0002, | |
| "loss": 10.8557, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008037263677048133, | |
| "grad_norm": 0.30325502157211304, | |
| "learning_rate": 0.0001996917333733128, | |
| "loss": 10.8584, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.0008767924011325235, | |
| "grad_norm": 0.30411583185195923, | |
| "learning_rate": 0.00019876883405951377, | |
| "loss": 10.8526, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0009498584345602339, | |
| "grad_norm": 0.3274756968021393, | |
| "learning_rate": 0.00019723699203976766, | |
| "loss": 10.847, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0009498584345602339, | |
| "eval_loss": 10.844072341918945, | |
| "eval_runtime": 21.5704, | |
| "eval_samples_per_second": 267.172, | |
| "eval_steps_per_second": 133.609, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0010229244679879441, | |
| "grad_norm": 0.312881201505661, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 10.8442, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0010959905014156545, | |
| "grad_norm": 0.33085769414901733, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 10.842, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011690565348433646, | |
| "grad_norm": 0.32802972197532654, | |
| "learning_rate": 0.0001891006524188368, | |
| "loss": 10.8367, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.001242122568271075, | |
| "grad_norm": 0.33731862902641296, | |
| "learning_rate": 0.00018526401643540922, | |
| "loss": 10.8294, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.0013151886016987853, | |
| "grad_norm": 0.3787227272987366, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 10.8306, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0013882546351264957, | |
| "grad_norm": 0.36396968364715576, | |
| "learning_rate": 0.0001760405965600031, | |
| "loss": 10.8309, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.0014613206685542058, | |
| "grad_norm": 0.3313588500022888, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 10.8222, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0015343867019819162, | |
| "grad_norm": 0.3631451725959778, | |
| "learning_rate": 0.00016494480483301836, | |
| "loss": 10.8216, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0016074527354096265, | |
| "grad_norm": 0.37917131185531616, | |
| "learning_rate": 0.00015877852522924732, | |
| "loss": 10.8169, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.0016805187688373367, | |
| "grad_norm": 0.38298654556274414, | |
| "learning_rate": 0.0001522498564715949, | |
| "loss": 10.8117, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.001753584802265047, | |
| "grad_norm": 0.3721317946910858, | |
| "learning_rate": 0.00014539904997395468, | |
| "loss": 10.8094, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0018266508356927574, | |
| "grad_norm": 0.42554646730422974, | |
| "learning_rate": 0.000138268343236509, | |
| "loss": 10.8066, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0018997168691204677, | |
| "grad_norm": 0.43415600061416626, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 10.8049, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0018997168691204677, | |
| "eval_loss": 10.798599243164062, | |
| "eval_runtime": 21.098, | |
| "eval_samples_per_second": 273.154, | |
| "eval_steps_per_second": 136.601, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.001972782902548178, | |
| "grad_norm": 0.43748196959495544, | |
| "learning_rate": 0.00012334453638559057, | |
| "loss": 10.7936, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0020458489359758882, | |
| "grad_norm": 0.4384560286998749, | |
| "learning_rate": 0.0001156434465040231, | |
| "loss": 10.7943, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.0021189149694035986, | |
| "grad_norm": 0.41844192147254944, | |
| "learning_rate": 0.0001078459095727845, | |
| "loss": 10.7908, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.002191981002831309, | |
| "grad_norm": 0.40660977363586426, | |
| "learning_rate": 0.0001, | |
| "loss": 10.7931, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0022650470362590193, | |
| "grad_norm": 0.4524174630641937, | |
| "learning_rate": 9.215409042721552e-05, | |
| "loss": 10.7828, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.002338113069686729, | |
| "grad_norm": 0.41357022523880005, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 10.7804, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.0024111791031144396, | |
| "grad_norm": 0.4162754714488983, | |
| "learning_rate": 7.66554636144095e-05, | |
| "loss": 10.7834, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.00248424513654215, | |
| "grad_norm": 0.4617297351360321, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 10.777, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.0025573111699698603, | |
| "grad_norm": 0.43608060479164124, | |
| "learning_rate": 6.173165676349103e-05, | |
| "loss": 10.7809, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0026303772033975706, | |
| "grad_norm": 0.4260936975479126, | |
| "learning_rate": 5.4600950026045326e-05, | |
| "loss": 10.7844, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.002703443236825281, | |
| "grad_norm": 0.44484320282936096, | |
| "learning_rate": 4.7750143528405126e-05, | |
| "loss": 10.7721, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.0027765092702529913, | |
| "grad_norm": 0.4757128059864044, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 10.7667, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.0028495753036807013, | |
| "grad_norm": 0.4379104971885681, | |
| "learning_rate": 3.5055195166981645e-05, | |
| "loss": 10.7727, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0028495753036807013, | |
| "eval_loss": 10.769347190856934, | |
| "eval_runtime": 21.0477, | |
| "eval_samples_per_second": 273.807, | |
| "eval_steps_per_second": 136.927, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0029226413371084116, | |
| "grad_norm": 0.4572875201702118, | |
| "learning_rate": 2.9289321881345254e-05, | |
| "loss": 10.7623, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002995707370536122, | |
| "grad_norm": 0.45184326171875, | |
| "learning_rate": 2.3959403439996907e-05, | |
| "loss": 10.7694, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.0030687734039638323, | |
| "grad_norm": 0.4599740207195282, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 10.7655, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.0031418394373915427, | |
| "grad_norm": 0.4575888216495514, | |
| "learning_rate": 1.4735983564590783e-05, | |
| "loss": 10.7638, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.003214905470819253, | |
| "grad_norm": 0.4490920901298523, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 10.7672, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.0032879715042469634, | |
| "grad_norm": 0.44325825572013855, | |
| "learning_rate": 7.612046748871327e-06, | |
| "loss": 10.7705, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0033610375376746733, | |
| "grad_norm": 0.43270397186279297, | |
| "learning_rate": 4.8943483704846475e-06, | |
| "loss": 10.7745, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.0034341035711023837, | |
| "grad_norm": 0.467824786901474, | |
| "learning_rate": 2.7630079602323442e-06, | |
| "loss": 10.7668, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.003507169604530094, | |
| "grad_norm": 0.4718198776245117, | |
| "learning_rate": 1.231165940486234e-06, | |
| "loss": 10.7651, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.0035802356379578044, | |
| "grad_norm": 0.48334893584251404, | |
| "learning_rate": 3.0826662668720364e-07, | |
| "loss": 10.7576, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.0036533016713855147, | |
| "grad_norm": 0.45176786184310913, | |
| "learning_rate": 0.0, | |
| "loss": 10.7631, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8182450225152.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |