| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 2.809169764560099, |
| "eval_steps": 3, |
| "global_step": 36, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.07930607187112763, |
| "grad_norm": 16.125, |
| "learning_rate": 1e-05, |
| "loss": 3.4783, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.07930607187112763, |
| "eval_loss": 4.231224060058594, |
| "eval_runtime": 35.8899, |
| "eval_samples_per_second": 15.436, |
| "eval_steps_per_second": 7.718, |
| "step": 1 |
| }, |
| { |
| "epoch": 0.15861214374225527, |
| "grad_norm": 15.875, |
| "learning_rate": 2e-05, |
| "loss": 3.581, |
| "step": 2 |
| }, |
| { |
| "epoch": 0.2379182156133829, |
| "grad_norm": 8.5625, |
| "learning_rate": 1.9957341762950346e-05, |
| "loss": 3.3803, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.2379182156133829, |
| "eval_loss": 3.8651065826416016, |
| "eval_runtime": 36.376, |
| "eval_samples_per_second": 15.23, |
| "eval_steps_per_second": 7.615, |
| "step": 3 |
| }, |
| { |
| "epoch": 0.31722428748451054, |
| "grad_norm": 9.0, |
| "learning_rate": 1.982973099683902e-05, |
| "loss": 3.2376, |
| "step": 4 |
| }, |
| { |
| "epoch": 0.3965303593556382, |
| "grad_norm": 6.34375, |
| "learning_rate": 1.961825643172819e-05, |
| "loss": 3.0861, |
| "step": 5 |
| }, |
| { |
| "epoch": 0.4758364312267658, |
| "grad_norm": 3.5625, |
| "learning_rate": 1.932472229404356e-05, |
| "loss": 3.0646, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.4758364312267658, |
| "eval_loss": 3.6871607303619385, |
| "eval_runtime": 36.6092, |
| "eval_samples_per_second": 15.133, |
| "eval_steps_per_second": 7.566, |
| "step": 6 |
| }, |
| { |
| "epoch": 0.5551425030978935, |
| "grad_norm": 2.859375, |
| "learning_rate": 1.8951632913550625e-05, |
| "loss": 3.0159, |
| "step": 7 |
| }, |
| { |
| "epoch": 0.6344485749690211, |
| "grad_norm": 2.75, |
| "learning_rate": 1.8502171357296144e-05, |
| "loss": 3.0312, |
| "step": 8 |
| }, |
| { |
| "epoch": 0.7137546468401487, |
| "grad_norm": 2.15625, |
| "learning_rate": 1.7980172272802398e-05, |
| "loss": 2.8913, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.7137546468401487, |
| "eval_loss": 3.6105825901031494, |
| "eval_runtime": 36.8528, |
| "eval_samples_per_second": 15.033, |
| "eval_steps_per_second": 7.516, |
| "step": 9 |
| }, |
| { |
| "epoch": 0.7930607187112764, |
| "grad_norm": 2.046875, |
| "learning_rate": 1.7390089172206594e-05, |
| "loss": 3.0189, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.872366790582404, |
| "grad_norm": 1.9140625, |
| "learning_rate": 1.6736956436465573e-05, |
| "loss": 2.8854, |
| "step": 11 |
| }, |
| { |
| "epoch": 0.9516728624535316, |
| "grad_norm": 2.015625, |
| "learning_rate": 1.6026346363792565e-05, |
| "loss": 2.9159, |
| "step": 12 |
| }, |
| { |
| "epoch": 0.9516728624535316, |
| "eval_loss": 3.558952808380127, |
| "eval_runtime": 36.3425, |
| "eval_samples_per_second": 15.244, |
| "eval_steps_per_second": 7.622, |
| "step": 12 |
| }, |
| { |
| "epoch": 1.0074349442379182, |
| "grad_norm": 1.625, |
| "learning_rate": 1.526432162877356e-05, |
| "loss": 2.9194, |
| "step": 13 |
| }, |
| { |
| "epoch": 1.0867410161090458, |
| "grad_norm": 1.5, |
| "learning_rate": 1.4457383557765385e-05, |
| "loss": 2.8288, |
| "step": 14 |
| }, |
| { |
| "epoch": 1.1660470879801734, |
| "grad_norm": 1.59375, |
| "learning_rate": 1.3612416661871532e-05, |
| "loss": 2.819, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.1660470879801734, |
| "eval_loss": 3.530693531036377, |
| "eval_runtime": 36.8292, |
| "eval_samples_per_second": 15.042, |
| "eval_steps_per_second": 7.521, |
| "step": 15 |
| }, |
| { |
| "epoch": 1.2453531598513012, |
| "grad_norm": 1.8359375, |
| "learning_rate": 1.2736629900720832e-05, |
| "loss": 2.9035, |
| "step": 16 |
| }, |
| { |
| "epoch": 1.3246592317224288, |
| "grad_norm": 1.4765625, |
| "learning_rate": 1.1837495178165706e-05, |
| "loss": 2.8615, |
| "step": 17 |
| }, |
| { |
| "epoch": 1.4039653035935564, |
| "grad_norm": 1.421875, |
| "learning_rate": 1.092268359463302e-05, |
| "loss": 2.8095, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.4039653035935564, |
| "eval_loss": 3.5109074115753174, |
| "eval_runtime": 36.5179, |
| "eval_samples_per_second": 15.171, |
| "eval_steps_per_second": 7.585, |
| "step": 18 |
| }, |
| { |
| "epoch": 1.483271375464684, |
| "grad_norm": 1.4140625, |
| "learning_rate": 1e-05, |
| "loss": 2.7651, |
| "step": 19 |
| }, |
| { |
| "epoch": 1.5625774473358116, |
| "grad_norm": 1.3828125, |
| "learning_rate": 9.07731640536698e-06, |
| "loss": 2.8122, |
| "step": 20 |
| }, |
| { |
| "epoch": 1.6418835192069392, |
| "grad_norm": 1.390625, |
| "learning_rate": 8.162504821834296e-06, |
| "loss": 2.8054, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.6418835192069392, |
| "eval_loss": 3.499537706375122, |
| "eval_runtime": 36.564, |
| "eval_samples_per_second": 15.152, |
| "eval_steps_per_second": 7.576, |
| "step": 21 |
| }, |
| { |
| "epoch": 1.7211895910780668, |
| "grad_norm": 1.296875, |
| "learning_rate": 7.263370099279173e-06, |
| "loss": 2.7538, |
| "step": 22 |
| }, |
| { |
| "epoch": 1.8004956629491944, |
| "grad_norm": 1.328125, |
| "learning_rate": 6.387583338128471e-06, |
| "loss": 2.7587, |
| "step": 23 |
| }, |
| { |
| "epoch": 1.8798017348203222, |
| "grad_norm": 1.3359375, |
| "learning_rate": 5.542616442234618e-06, |
| "loss": 2.9067, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.8798017348203222, |
| "eval_loss": 3.4932873249053955, |
| "eval_runtime": 36.4531, |
| "eval_samples_per_second": 15.198, |
| "eval_steps_per_second": 7.599, |
| "step": 24 |
| }, |
| { |
| "epoch": 1.9591078066914498, |
| "grad_norm": 1.296875, |
| "learning_rate": 4.7356783712264405e-06, |
| "loss": 2.7533, |
| "step": 25 |
| }, |
| { |
| "epoch": 2.0161090458488227, |
| "grad_norm": 1.3125, |
| "learning_rate": 3.973653636207437e-06, |
| "loss": 2.7047, |
| "step": 26 |
| }, |
| { |
| "epoch": 2.0954151177199503, |
| "grad_norm": 1.25, |
| "learning_rate": 3.2630435635344283e-06, |
| "loss": 2.8035, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.0954151177199503, |
| "eval_loss": 3.4902639389038086, |
| "eval_runtime": 36.5582, |
| "eval_samples_per_second": 15.154, |
| "eval_steps_per_second": 7.577, |
| "step": 27 |
| }, |
| { |
| "epoch": 2.174721189591078, |
| "grad_norm": 1.2890625, |
| "learning_rate": 2.6099108277934105e-06, |
| "loss": 2.778, |
| "step": 28 |
| }, |
| { |
| "epoch": 2.254027261462206, |
| "grad_norm": 1.2421875, |
| "learning_rate": 2.019827727197605e-06, |
| "loss": 2.691, |
| "step": 29 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "grad_norm": 1.2734375, |
| "learning_rate": 1.4978286427038602e-06, |
| "loss": 2.7619, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.3333333333333335, |
| "eval_loss": 3.4889628887176514, |
| "eval_runtime": 36.371, |
| "eval_samples_per_second": 15.232, |
| "eval_steps_per_second": 7.616, |
| "step": 30 |
| }, |
| { |
| "epoch": 2.412639405204461, |
| "grad_norm": 1.3046875, |
| "learning_rate": 1.0483670864493777e-06, |
| "loss": 2.7703, |
| "step": 31 |
| }, |
| { |
| "epoch": 2.4919454770755887, |
| "grad_norm": 1.2734375, |
| "learning_rate": 6.752777059564431e-07, |
| "loss": 2.8694, |
| "step": 32 |
| }, |
| { |
| "epoch": 2.5712515489467163, |
| "grad_norm": 1.359375, |
| "learning_rate": 3.817435682718096e-07, |
| "loss": 2.8226, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.5712515489467163, |
| "eval_loss": 3.489114999771118, |
| "eval_runtime": 36.366, |
| "eval_samples_per_second": 15.234, |
| "eval_steps_per_second": 7.617, |
| "step": 33 |
| }, |
| { |
| "epoch": 2.650557620817844, |
| "grad_norm": 1.296875, |
| "learning_rate": 1.7026900316098217e-07, |
| "loss": 2.7609, |
| "step": 34 |
| }, |
| { |
| "epoch": 2.7298636926889714, |
| "grad_norm": 1.28125, |
| "learning_rate": 4.2658237049655325e-08, |
| "loss": 2.7784, |
| "step": 35 |
| }, |
| { |
| "epoch": 2.809169764560099, |
| "grad_norm": 1.296875, |
| "learning_rate": 0.0, |
| "loss": 2.7211, |
| "step": 36 |
| }, |
| { |
| "epoch": 2.809169764560099, |
| "eval_loss": 3.488926649093628, |
| "eval_runtime": 36.5143, |
| "eval_samples_per_second": 15.172, |
| "eval_steps_per_second": 7.586, |
| "step": 36 |
| } |
| ], |
| "logging_steps": 1, |
| "max_steps": 36, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 12, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 7.417945105681613e+16, |
| "train_batch_size": 2, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
