| { |
| "best_global_step": 6000, |
| "best_metric": 0.773181501278178, |
| "best_model_checkpoint": "./finetuned-finbert-crypto/checkpoint-6000", |
| "epoch": 2.7881040892193307, |
| "eval_steps": 500, |
| "global_step": 6000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.23234200743494424, |
| "grad_norm": 7.068714141845703, |
| "learning_rate": 4.613537794299877e-05, |
| "loss": 0.9047, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.23234200743494424, |
| "eval_accuracy": 0.6913781082965373, |
| "eval_loss": 0.6830344796180725, |
| "eval_runtime": 58.4281, |
| "eval_samples_per_second": 147.292, |
| "eval_steps_per_second": 2.311, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.4646840148698885, |
| "grad_norm": 8.502310752868652, |
| "learning_rate": 4.226301115241636e-05, |
| "loss": 0.7414, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.4646840148698885, |
| "eval_accuracy": 0.7399488728793865, |
| "eval_loss": 0.6058772206306458, |
| "eval_runtime": 58.2625, |
| "eval_samples_per_second": 147.711, |
| "eval_steps_per_second": 2.317, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.6970260223048327, |
| "grad_norm": 13.922765731811523, |
| "learning_rate": 3.8390644361833954e-05, |
| "loss": 0.6748, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.6970260223048327, |
| "eval_accuracy": 0.7341389728096677, |
| "eval_loss": 0.6262826323509216, |
| "eval_runtime": 58.3395, |
| "eval_samples_per_second": 147.516, |
| "eval_steps_per_second": 2.314, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.929368029739777, |
| "grad_norm": 13.632185935974121, |
| "learning_rate": 3.451827757125155e-05, |
| "loss": 0.6574, |
| "step": 2000 |
| }, |
| { |
| "epoch": 0.929368029739777, |
| "eval_accuracy": 0.7493609109923309, |
| "eval_loss": 0.595951497554779, |
| "eval_runtime": 58.1549, |
| "eval_samples_per_second": 147.984, |
| "eval_steps_per_second": 2.321, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.161710037174721, |
| "grad_norm": 12.459709167480469, |
| "learning_rate": 3.064591078066915e-05, |
| "loss": 0.5383, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.161710037174721, |
| "eval_accuracy": 0.7552870090634441, |
| "eval_loss": 0.6442441940307617, |
| "eval_runtime": 58.4695, |
| "eval_samples_per_second": 147.188, |
| "eval_steps_per_second": 2.309, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.3940520446096654, |
| "grad_norm": 13.643019676208496, |
| "learning_rate": 2.677354399008674e-05, |
| "loss": 0.5048, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.3940520446096654, |
| "eval_accuracy": 0.7565651870787823, |
| "eval_loss": 0.5826976895332336, |
| "eval_runtime": 58.4255, |
| "eval_samples_per_second": 147.299, |
| "eval_steps_per_second": 2.311, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.6263940520446096, |
| "grad_norm": 6.947994709014893, |
| "learning_rate": 2.290117719950434e-05, |
| "loss": 0.4868, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.6263940520446096, |
| "eval_accuracy": 0.7679525912154311, |
| "eval_loss": 0.5739635229110718, |
| "eval_runtime": 58.5024, |
| "eval_samples_per_second": 147.105, |
| "eval_steps_per_second": 2.308, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.858736059479554, |
| "grad_norm": 6.8905558586120605, |
| "learning_rate": 1.9028810408921934e-05, |
| "loss": 0.4816, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.858736059479554, |
| "eval_accuracy": 0.7709737392516849, |
| "eval_loss": 0.5892115235328674, |
| "eval_runtime": 58.1383, |
| "eval_samples_per_second": 148.026, |
| "eval_steps_per_second": 2.322, |
| "step": 4000 |
| }, |
| { |
| "epoch": 2.091078066914498, |
| "grad_norm": 16.006935119628906, |
| "learning_rate": 1.515644361833953e-05, |
| "loss": 0.3767, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.091078066914498, |
| "eval_accuracy": 0.7634208691610505, |
| "eval_loss": 0.768525242805481, |
| "eval_runtime": 58.4924, |
| "eval_samples_per_second": 147.13, |
| "eval_steps_per_second": 2.308, |
| "step": 4500 |
| }, |
| { |
| "epoch": 2.323420074349442, |
| "grad_norm": 8.312914848327637, |
| "learning_rate": 1.1284076827757125e-05, |
| "loss": 0.2703, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.323420074349442, |
| "eval_accuracy": 0.7714385312572624, |
| "eval_loss": 0.7697556614875793, |
| "eval_runtime": 58.5644, |
| "eval_samples_per_second": 146.949, |
| "eval_steps_per_second": 2.305, |
| "step": 5000 |
| }, |
| { |
| "epoch": 2.5557620817843865, |
| "grad_norm": 8.89210033416748, |
| "learning_rate": 7.411710037174721e-06, |
| "loss": 0.2519, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.5557620817843865, |
| "eval_accuracy": 0.7712061352544736, |
| "eval_loss": 0.7800889015197754, |
| "eval_runtime": 58.3079, |
| "eval_samples_per_second": 147.596, |
| "eval_steps_per_second": 2.315, |
| "step": 5500 |
| }, |
| { |
| "epoch": 2.7881040892193307, |
| "grad_norm": 9.266032218933105, |
| "learning_rate": 3.539343246592317e-06, |
| "loss": 0.2486, |
| "step": 6000 |
| }, |
| { |
| "epoch": 2.7881040892193307, |
| "eval_accuracy": 0.773181501278178, |
| "eval_loss": 0.7413144707679749, |
| "eval_runtime": 58.2575, |
| "eval_samples_per_second": 147.724, |
| "eval_steps_per_second": 2.317, |
| "step": 6000 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 6456, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 6313274901674496.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
