| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07383773928896992, | |
| "eval_steps": 9, | |
| "global_step": 81, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0009115770282588879, | |
| "eval_loss": 2.555964469909668, | |
| "eval_runtime": 406.622, | |
| "eval_samples_per_second": 4.545, | |
| "eval_steps_per_second": 0.568, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0027347310847766638, | |
| "grad_norm": 7.979882717132568, | |
| "learning_rate": 3e-05, | |
| "loss": 10.1658, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0054694621695533276, | |
| "grad_norm": 6.485815048217773, | |
| "learning_rate": 6e-05, | |
| "loss": 9.9619, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008204193254329991, | |
| "grad_norm": 26.487564086914062, | |
| "learning_rate": 9e-05, | |
| "loss": 9.7054, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008204193254329991, | |
| "eval_loss": 2.3843369483947754, | |
| "eval_runtime": 408.562, | |
| "eval_samples_per_second": 4.523, | |
| "eval_steps_per_second": 0.565, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.010938924339106655, | |
| "grad_norm": 4.259462833404541, | |
| "learning_rate": 9.987820251299122e-05, | |
| "loss": 9.506, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.013673655423883319, | |
| "grad_norm": 4.685791492462158, | |
| "learning_rate": 9.924038765061042e-05, | |
| "loss": 9.2787, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.016408386508659983, | |
| "grad_norm": 6.113475799560547, | |
| "learning_rate": 9.806308479691595e-05, | |
| "loss": 8.9251, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.016408386508659983, | |
| "eval_loss": 2.118788003921509, | |
| "eval_runtime": 408.4849, | |
| "eval_samples_per_second": 4.524, | |
| "eval_steps_per_second": 0.566, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.019143117593436645, | |
| "grad_norm": 19.60219955444336, | |
| "learning_rate": 9.635919272833938e-05, | |
| "loss": 8.2305, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02187784867821331, | |
| "grad_norm": 23.08515167236328, | |
| "learning_rate": 9.414737964294636e-05, | |
| "loss": 7.2251, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.024612579762989972, | |
| "grad_norm": 15.243215560913086, | |
| "learning_rate": 9.145187862775209e-05, | |
| "loss": 6.5719, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.024612579762989972, | |
| "eval_loss": 1.5913326740264893, | |
| "eval_runtime": 408.4775, | |
| "eval_samples_per_second": 4.524, | |
| "eval_steps_per_second": 0.566, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.027347310847766638, | |
| "grad_norm": 10.839764595031738, | |
| "learning_rate": 8.83022221559489e-05, | |
| "loss": 5.6314, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0300820419325433, | |
| "grad_norm": 9.605040550231934, | |
| "learning_rate": 8.473291852294987e-05, | |
| "loss": 5.397, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.032816773017319965, | |
| "grad_norm": 12.7434720993042, | |
| "learning_rate": 8.07830737662829e-05, | |
| "loss": 4.4798, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.032816773017319965, | |
| "eval_loss": 1.2467855215072632, | |
| "eval_runtime": 408.5454, | |
| "eval_samples_per_second": 4.523, | |
| "eval_steps_per_second": 0.565, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.03555150410209663, | |
| "grad_norm": 10.537009239196777, | |
| "learning_rate": 7.649596321166024e-05, | |
| "loss": 5.077, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.03828623518687329, | |
| "grad_norm": 9.679017066955566, | |
| "learning_rate": 7.191855733945387e-05, | |
| "loss": 5.2566, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.04102096627164995, | |
| "grad_norm": 15.049214363098145, | |
| "learning_rate": 6.710100716628344e-05, | |
| "loss": 4.4715, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04102096627164995, | |
| "eval_loss": 1.105316162109375, | |
| "eval_runtime": 408.5369, | |
| "eval_samples_per_second": 4.523, | |
| "eval_steps_per_second": 0.565, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.04375569735642662, | |
| "grad_norm": 10.599452018737793, | |
| "learning_rate": 6.209609477998338e-05, | |
| "loss": 4.073, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.04649042844120328, | |
| "grad_norm": 8.252169609069824, | |
| "learning_rate": 5.695865504800327e-05, | |
| "loss": 4.3738, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.049225159525979945, | |
| "grad_norm": 10.953838348388672, | |
| "learning_rate": 5.174497483512506e-05, | |
| "loss": 3.5531, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.049225159525979945, | |
| "eval_loss": 0.9935899972915649, | |
| "eval_runtime": 408.5367, | |
| "eval_samples_per_second": 4.523, | |
| "eval_steps_per_second": 0.565, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.05195989061075661, | |
| "grad_norm": 9.884892463684082, | |
| "learning_rate": 4.6512176312793736e-05, | |
| "loss": 3.4851, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.054694621695533276, | |
| "grad_norm": 8.605599403381348, | |
| "learning_rate": 4.131759111665349e-05, | |
| "loss": 4.5235, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05742935278030994, | |
| "grad_norm": 8.588393211364746, | |
| "learning_rate": 3.6218132209150045e-05, | |
| "loss": 3.8852, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.05742935278030994, | |
| "eval_loss": 0.9350164532661438, | |
| "eval_runtime": 408.6463, | |
| "eval_samples_per_second": 4.522, | |
| "eval_steps_per_second": 0.565, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.0601640838650866, | |
| "grad_norm": 9.282758712768555, | |
| "learning_rate": 3.12696703292044e-05, | |
| "loss": 3.6969, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.06289881494986327, | |
| "grad_norm": 9.940718650817871, | |
| "learning_rate": 2.6526421860705473e-05, | |
| "loss": 3.4917, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.06563354603463993, | |
| "grad_norm": 10.431665420532227, | |
| "learning_rate": 2.2040354826462668e-05, | |
| "loss": 3.7412, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06563354603463993, | |
| "eval_loss": 0.8883235454559326, | |
| "eval_runtime": 408.7916, | |
| "eval_samples_per_second": 4.521, | |
| "eval_steps_per_second": 0.565, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.06836827711941659, | |
| "grad_norm": 9.749879837036133, | |
| "learning_rate": 1.7860619515673033e-05, | |
| "loss": 3.1491, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.07110300820419325, | |
| "grad_norm": 8.8101224899292, | |
| "learning_rate": 1.4033009983067452e-05, | |
| "loss": 2.7604, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.07383773928896992, | |
| "grad_norm": 10.01700210571289, | |
| "learning_rate": 1.0599462319663905e-05, | |
| "loss": 3.1736, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.07383773928896992, | |
| "eval_loss": 0.8615151047706604, | |
| "eval_runtime": 408.7768, | |
| "eval_samples_per_second": 4.521, | |
| "eval_steps_per_second": 0.565, | |
| "step": 81 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.148060618471506e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |