| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 5.0, |
| "eval_steps": 500, |
| "global_step": 935, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.26737967914438504, |
| "grad_norm": 17.321611404418945, |
| "learning_rate": 1.8994652406417113e-05, |
| "loss": 4.3588, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.5347593582887701, |
| "grad_norm": 18.49687957763672, |
| "learning_rate": 1.7925133689839573e-05, |
| "loss": 3.7275, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.8021390374331551, |
| "grad_norm": 17.81402587890625, |
| "learning_rate": 1.6855614973262032e-05, |
| "loss": 3.1286, |
| "step": 150 |
| }, |
| { |
| "epoch": 1.0, |
| "eval_loss": 2.293884754180908, |
| "eval_runtime": 2.4316, |
| "eval_samples_per_second": 68.268, |
| "eval_steps_per_second": 17.273, |
| "step": 187 |
| }, |
| { |
| "epoch": 1.0695187165775402, |
| "grad_norm": 16.78999137878418, |
| "learning_rate": 1.5786096256684492e-05, |
| "loss": 2.5828, |
| "step": 200 |
| }, |
| { |
| "epoch": 1.3368983957219251, |
| "grad_norm": 16.12043571472168, |
| "learning_rate": 1.4716577540106953e-05, |
| "loss": 2.0374, |
| "step": 250 |
| }, |
| { |
| "epoch": 1.6042780748663101, |
| "grad_norm": 14.432710647583008, |
| "learning_rate": 1.3647058823529413e-05, |
| "loss": 1.5509, |
| "step": 300 |
| }, |
| { |
| "epoch": 1.8716577540106951, |
| "grad_norm": 11.290574073791504, |
| "learning_rate": 1.2577540106951873e-05, |
| "loss": 1.1191, |
| "step": 350 |
| }, |
| { |
| "epoch": 2.0, |
| "eval_loss": 0.7051454186439514, |
| "eval_runtime": 2.4082, |
| "eval_samples_per_second": 68.932, |
| "eval_steps_per_second": 17.441, |
| "step": 374 |
| }, |
| { |
| "epoch": 2.1390374331550803, |
| "grad_norm": 8.16003131866455, |
| "learning_rate": 1.1508021390374334e-05, |
| "loss": 0.7617, |
| "step": 400 |
| }, |
| { |
| "epoch": 2.406417112299465, |
| "grad_norm": 4.7810235023498535, |
| "learning_rate": 1.0438502673796794e-05, |
| "loss": 0.5062, |
| "step": 450 |
| }, |
| { |
| "epoch": 2.6737967914438503, |
| "grad_norm": 2.9582180976867676, |
| "learning_rate": 9.368983957219252e-06, |
| "loss": 0.3417, |
| "step": 500 |
| }, |
| { |
| "epoch": 2.9411764705882355, |
| "grad_norm": 2.0482232570648193, |
| "learning_rate": 8.299465240641711e-06, |
| "loss": 0.2597, |
| "step": 550 |
| }, |
| { |
| "epoch": 3.0, |
| "eval_loss": 0.21000835299491882, |
| "eval_runtime": 2.1552, |
| "eval_samples_per_second": 77.023, |
| "eval_steps_per_second": 19.488, |
| "step": 561 |
| }, |
| { |
| "epoch": 3.2085561497326203, |
| "grad_norm": 1.4092211723327637, |
| "learning_rate": 7.229946524064172e-06, |
| "loss": 0.1864, |
| "step": 600 |
| }, |
| { |
| "epoch": 3.4759358288770055, |
| "grad_norm": 0.9414141178131104, |
| "learning_rate": 6.1604278074866315e-06, |
| "loss": 0.1345, |
| "step": 650 |
| }, |
| { |
| "epoch": 3.7433155080213902, |
| "grad_norm": 0.7395118474960327, |
| "learning_rate": 5.090909090909091e-06, |
| "loss": 0.1344, |
| "step": 700 |
| }, |
| { |
| "epoch": 4.0, |
| "eval_loss": 0.15455076098442078, |
| "eval_runtime": 2.1122, |
| "eval_samples_per_second": 78.59, |
| "eval_steps_per_second": 19.884, |
| "step": 748 |
| }, |
| { |
| "epoch": 4.010695187165775, |
| "grad_norm": 0.6380388736724854, |
| "learning_rate": 4.021390374331552e-06, |
| "loss": 0.1239, |
| "step": 750 |
| }, |
| { |
| "epoch": 4.278074866310161, |
| "grad_norm": 0.6696634292602539, |
| "learning_rate": 2.9518716577540106e-06, |
| "loss": 0.1042, |
| "step": 800 |
| }, |
| { |
| "epoch": 4.545454545454545, |
| "grad_norm": 0.590194582939148, |
| "learning_rate": 1.8823529411764707e-06, |
| "loss": 0.1017, |
| "step": 850 |
| }, |
| { |
| "epoch": 4.81283422459893, |
| "grad_norm": 0.47769060730934143, |
| "learning_rate": 8.128342245989306e-07, |
| "loss": 0.1022, |
| "step": 900 |
| }, |
| { |
| "epoch": 5.0, |
| "eval_loss": 0.15090639889240265, |
| "eval_runtime": 2.1578, |
| "eval_samples_per_second": 76.931, |
| "eval_steps_per_second": 19.464, |
| "step": 935 |
| } |
| ], |
| "logging_steps": 50, |
| "max_steps": 935, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 5, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": true |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 787640939839488.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
