| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.07222824124232576, | |
| "eval_steps": 5, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001444564824846515, | |
| "eval_loss": 12.318426132202148, | |
| "eval_runtime": 452.8191, | |
| "eval_samples_per_second": 2.575, | |
| "eval_steps_per_second": 0.322, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004333694474539545, | |
| "grad_norm": 25.538225173950195, | |
| "learning_rate": 3e-05, | |
| "loss": 49.8181, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007222824124232575, | |
| "eval_loss": 10.13512134552002, | |
| "eval_runtime": 454.3185, | |
| "eval_samples_per_second": 2.566, | |
| "eval_steps_per_second": 0.321, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00866738894907909, | |
| "grad_norm": 48.99589920043945, | |
| "learning_rate": 6e-05, | |
| "loss": 44.5425, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.013001083423618635, | |
| "grad_norm": 41.58720779418945, | |
| "learning_rate": 9e-05, | |
| "loss": 23.7904, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01444564824846515, | |
| "eval_loss": 0.9781672954559326, | |
| "eval_runtime": 453.9838, | |
| "eval_samples_per_second": 2.568, | |
| "eval_steps_per_second": 0.322, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01733477789815818, | |
| "grad_norm": 18.518259048461914, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 4.2303, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.021668472372697724, | |
| "grad_norm": 0.1313701719045639, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.0983, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021668472372697724, | |
| "eval_loss": 0.022199353203177452, | |
| "eval_runtime": 454.0297, | |
| "eval_samples_per_second": 2.568, | |
| "eval_steps_per_second": 0.322, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02600216684723727, | |
| "grad_norm": 0.12492942065000534, | |
| "learning_rate": 9.045084971874738e-05, | |
| "loss": 0.0015, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0288912964969303, | |
| "eval_loss": 0.07847809791564941, | |
| "eval_runtime": 454.0899, | |
| "eval_samples_per_second": 2.568, | |
| "eval_steps_per_second": 0.322, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.030335861321776816, | |
| "grad_norm": 18.6055908203125, | |
| "learning_rate": 8.247240241650918e-05, | |
| "loss": 0.2287, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.03466955579631636, | |
| "grad_norm": 3.176828145980835, | |
| "learning_rate": 7.269952498697734e-05, | |
| "loss": 0.007, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.03611412062116288, | |
| "eval_loss": 0.0683816447854042, | |
| "eval_runtime": 453.9578, | |
| "eval_samples_per_second": 2.569, | |
| "eval_steps_per_second": 0.322, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0390032502708559, | |
| "grad_norm": 0.03669508546590805, | |
| "learning_rate": 6.167226819279528e-05, | |
| "loss": 0.0005, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.04333694474539545, | |
| "grad_norm": 0.5376744270324707, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6832, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04333694474539545, | |
| "eval_loss": 0.024126915261149406, | |
| "eval_runtime": 454.0942, | |
| "eval_samples_per_second": 2.568, | |
| "eval_steps_per_second": 0.322, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.047670639219934995, | |
| "grad_norm": 0.025675935670733452, | |
| "learning_rate": 3.832773180720475e-05, | |
| "loss": 0.0004, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.05055976886962803, | |
| "eval_loss": 0.018978465348482132, | |
| "eval_runtime": 454.2548, | |
| "eval_samples_per_second": 2.567, | |
| "eval_steps_per_second": 0.321, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05200433369447454, | |
| "grad_norm": 9.978776931762695, | |
| "learning_rate": 2.7300475013022663e-05, | |
| "loss": 0.0128, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.056338028169014086, | |
| "grad_norm": 0.01156551018357277, | |
| "learning_rate": 1.7527597583490822e-05, | |
| "loss": 0.1589, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.0577825929938606, | |
| "eval_loss": 0.0023998336400836706, | |
| "eval_runtime": 453.9056, | |
| "eval_samples_per_second": 2.569, | |
| "eval_steps_per_second": 0.322, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.06067172264355363, | |
| "grad_norm": 1.0478241443634033, | |
| "learning_rate": 9.549150281252633e-06, | |
| "loss": 0.003, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.06500541711809317, | |
| "grad_norm": 0.04418126866221428, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.001, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06500541711809317, | |
| "eval_loss": 0.0003434412938077003, | |
| "eval_runtime": 454.0191, | |
| "eval_samples_per_second": 2.568, | |
| "eval_steps_per_second": 0.322, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.06933911159263272, | |
| "grad_norm": 0.06964542716741562, | |
| "learning_rate": 6.15582970243117e-07, | |
| "loss": 0.0012, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.07222824124232576, | |
| "eval_loss": 0.0003464781621005386, | |
| "eval_runtime": 453.9994, | |
| "eval_samples_per_second": 2.568, | |
| "eval_steps_per_second": 0.322, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 5, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.7562264756224e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |