| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.0921985815602837, | |
| "eval_steps": 25, | |
| "global_step": 53, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.05673758865248227, | |
| "grad_norm": NaN, | |
| "learning_rate": 5e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.05673758865248227, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.3644, | |
| "eval_samples_per_second": 2.796, | |
| "eval_steps_per_second": 1.491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.11347517730496454, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.1702127659574468, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.990516643685222e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.22695035460992907, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.96210254835968e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.28368794326241137, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.91486549841951e-05, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.3404255319148936, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.848984680175049e-05, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.3971631205673759, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.764710002135784e-05, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.45390070921985815, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.662361147021779e-05, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.5106382978723404, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.542326359097619e-05, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.5673758865248227, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.405060971428923e-05, | |
| "loss": 0.0, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.624113475177305, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.251085678648072e-05, | |
| "loss": 0.0, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.6808510638297872, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.08098456178111e-05, | |
| "loss": 0.0, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.7375886524822695, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.895402872628352e-05, | |
| "loss": 0.0, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.7943262411347518, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.695044586103296e-05, | |
| "loss": 0.0, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.851063829787234, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.480669729814635e-05, | |
| "loss": 0.0, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.9078014184397163, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.25309150102121e-05, | |
| "loss": 0.0, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.9645390070921985, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.013173181896283e-05, | |
| "loss": 0.0, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 1.049645390070922, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.76182486480253e-05, | |
| "loss": 0.0, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 1.1063829787234043, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 1.1631205673758864, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.228691778882693e-05, | |
| "loss": 0.0, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 1.2198581560283688, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.948929366463396e-05, | |
| "loss": 0.0, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 1.2765957446808511, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.661773997398298e-05, | |
| "loss": 0.0, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.368314950360415e-05, | |
| "loss": 0.0, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 1.3900709219858156, | |
| "grad_norm": NaN, | |
| "learning_rate": 6.069665416032487e-05, | |
| "loss": 0.0, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 1.4468085106382977, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.7669582743934284e-05, | |
| "loss": 0.0, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.4468085106382977, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.0452, | |
| "eval_samples_per_second": 2.973, | |
| "eval_steps_per_second": 1.586, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 1.50354609929078, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.4613417973165106e-05, | |
| "loss": 0.0, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 1.5602836879432624, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.153975292780853e-05, | |
| "loss": 0.0, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 1.6170212765957448, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.8460247072191496e-05, | |
| "loss": 0.0, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 1.673758865248227, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.5386582026834906e-05, | |
| "loss": 0.0, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 1.7304964539007093, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.233041725606572e-05, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 1.7872340425531914, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.930334583967514e-05, | |
| "loss": 0.0, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 1.8439716312056738, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.631685049639586e-05, | |
| "loss": 0.0, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 1.900709219858156, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.338226002601703e-05, | |
| "loss": 0.0, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 1.9574468085106385, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.0510706335366035e-05, | |
| "loss": 0.0, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 2.0425531914893615, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.771308221117309e-05, | |
| "loss": 0.0, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 2.099290780141844, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 0.0, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 2.1560283687943262, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.238175135197471e-05, | |
| "loss": 0.0, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 2.2127659574468086, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.9868268181037185e-05, | |
| "loss": 0.0, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 2.269503546099291, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.746908498978791e-05, | |
| "loss": 0.0, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 2.326241134751773, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5193302701853673e-05, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 2.382978723404255, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.3049554138967051e-05, | |
| "loss": 0.0, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 2.4397163120567376, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.1045971273716477e-05, | |
| "loss": 0.0, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 2.49645390070922, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.190154382188921e-06, | |
| "loss": 0.0, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 2.5531914893617023, | |
| "grad_norm": NaN, | |
| "learning_rate": 7.489143213519301e-06, | |
| "loss": 0.0, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 2.6099290780141846, | |
| "grad_norm": NaN, | |
| "learning_rate": 5.949390285710776e-06, | |
| "loss": 0.0, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": NaN, | |
| "learning_rate": 4.576736409023813e-06, | |
| "loss": 0.0, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 2.723404255319149, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.376388529782215e-06, | |
| "loss": 0.0, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 2.780141843971631, | |
| "grad_norm": NaN, | |
| "learning_rate": 2.3528999786421756e-06, | |
| "loss": 0.0, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 2.8368794326241136, | |
| "grad_norm": NaN, | |
| "learning_rate": 1.5101531982495308e-06, | |
| "loss": 0.0, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 2.8936170212765955, | |
| "grad_norm": NaN, | |
| "learning_rate": 8.513450158049108e-07, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.8936170212765955, | |
| "eval_loss": NaN, | |
| "eval_runtime": 5.0454, | |
| "eval_samples_per_second": 2.973, | |
| "eval_steps_per_second": 1.586, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 2.950354609929078, | |
| "grad_norm": NaN, | |
| "learning_rate": 3.7897451640321323e-07, | |
| "loss": 0.0, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 3.0354609929078014, | |
| "grad_norm": NaN, | |
| "learning_rate": 9.483356314779479e-08, | |
| "loss": 0.0, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 3.0921985815602837, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0, | |
| "loss": 0.0, | |
| "step": 53 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 53, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "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": 1.218199878107136e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |