| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.9998129092609915, |
| "eval_steps": 500, |
| "global_step": 334, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.029934518241347054, |
| "grad_norm": 1.3387344639766428, |
| "learning_rate": 5e-06, |
| "loss": 0.7726, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05986903648269411, |
| "grad_norm": 0.7768397662301797, |
| "learning_rate": 5e-06, |
| "loss": 0.6941, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.08980355472404115, |
| "grad_norm": 0.707220098018675, |
| "learning_rate": 5e-06, |
| "loss": 0.669, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11973807296538821, |
| "grad_norm": 0.6673639225008394, |
| "learning_rate": 5e-06, |
| "loss": 0.6651, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.14967259120673526, |
| "grad_norm": 0.931884409826821, |
| "learning_rate": 5e-06, |
| "loss": 0.6563, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1796071094480823, |
| "grad_norm": 0.7248290568232586, |
| "learning_rate": 5e-06, |
| "loss": 0.6486, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.20954162768942938, |
| "grad_norm": 0.7317021024341339, |
| "learning_rate": 5e-06, |
| "loss": 0.6456, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.23947614593077643, |
| "grad_norm": 0.7878073380412045, |
| "learning_rate": 5e-06, |
| "loss": 0.647, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2694106641721235, |
| "grad_norm": 0.9477711469098681, |
| "learning_rate": 5e-06, |
| "loss": 0.638, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2993451824134705, |
| "grad_norm": 0.7824185434647374, |
| "learning_rate": 5e-06, |
| "loss": 0.6395, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3292797006548176, |
| "grad_norm": 0.7691665877451451, |
| "learning_rate": 5e-06, |
| "loss": 0.6352, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.3592142188961646, |
| "grad_norm": 0.85227640579011, |
| "learning_rate": 5e-06, |
| "loss": 0.6344, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.3891487371375117, |
| "grad_norm": 0.7349060200879011, |
| "learning_rate": 5e-06, |
| "loss": 0.6343, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.41908325537885877, |
| "grad_norm": 0.7948303412589806, |
| "learning_rate": 5e-06, |
| "loss": 0.628, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.4490177736202058, |
| "grad_norm": 0.6403554998368226, |
| "learning_rate": 5e-06, |
| "loss": 0.6296, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.47895229186155286, |
| "grad_norm": 0.6579875234047781, |
| "learning_rate": 5e-06, |
| "loss": 0.6286, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.5088868101028999, |
| "grad_norm": 0.6635988202382727, |
| "learning_rate": 5e-06, |
| "loss": 0.6228, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.538821328344247, |
| "grad_norm": 0.6766189913752628, |
| "learning_rate": 5e-06, |
| "loss": 0.6242, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.568755846585594, |
| "grad_norm": 0.7350593528596518, |
| "learning_rate": 5e-06, |
| "loss": 0.6221, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.598690364826941, |
| "grad_norm": 0.7042346638489535, |
| "learning_rate": 5e-06, |
| "loss": 0.6299, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.6286248830682881, |
| "grad_norm": 0.7310808118757001, |
| "learning_rate": 5e-06, |
| "loss": 0.6238, |
| "step": 210 |
| }, |
| { |
| "epoch": 0.6585594013096352, |
| "grad_norm": 0.915027325723907, |
| "learning_rate": 5e-06, |
| "loss": 0.622, |
| "step": 220 |
| }, |
| { |
| "epoch": 0.6884939195509823, |
| "grad_norm": 0.7146070049162939, |
| "learning_rate": 5e-06, |
| "loss": 0.6245, |
| "step": 230 |
| }, |
| { |
| "epoch": 0.7184284377923292, |
| "grad_norm": 0.6682750595418552, |
| "learning_rate": 5e-06, |
| "loss": 0.6234, |
| "step": 240 |
| }, |
| { |
| "epoch": 0.7483629560336763, |
| "grad_norm": 0.6075185838844738, |
| "learning_rate": 5e-06, |
| "loss": 0.6199, |
| "step": 250 |
| }, |
| { |
| "epoch": 0.7782974742750234, |
| "grad_norm": 0.6614005815451841, |
| "learning_rate": 5e-06, |
| "loss": 0.6186, |
| "step": 260 |
| }, |
| { |
| "epoch": 0.8082319925163705, |
| "grad_norm": 0.7431404889886319, |
| "learning_rate": 5e-06, |
| "loss": 0.6261, |
| "step": 270 |
| }, |
| { |
| "epoch": 0.8381665107577175, |
| "grad_norm": 0.6659051677024307, |
| "learning_rate": 5e-06, |
| "loss": 0.6163, |
| "step": 280 |
| }, |
| { |
| "epoch": 0.8681010289990645, |
| "grad_norm": 0.761848043492867, |
| "learning_rate": 5e-06, |
| "loss": 0.6131, |
| "step": 290 |
| }, |
| { |
| "epoch": 0.8980355472404116, |
| "grad_norm": 0.7790121000018401, |
| "learning_rate": 5e-06, |
| "loss": 0.6145, |
| "step": 300 |
| }, |
| { |
| "epoch": 0.9279700654817586, |
| "grad_norm": 0.700122187157476, |
| "learning_rate": 5e-06, |
| "loss": 0.6131, |
| "step": 310 |
| }, |
| { |
| "epoch": 0.9579045837231057, |
| "grad_norm": 0.6439594670749554, |
| "learning_rate": 5e-06, |
| "loss": 0.6152, |
| "step": 320 |
| }, |
| { |
| "epoch": 0.9878391019644528, |
| "grad_norm": 0.9505341757424101, |
| "learning_rate": 5e-06, |
| "loss": 0.6082, |
| "step": 330 |
| }, |
| { |
| "epoch": 0.9998129092609915, |
| "eval_loss": 0.619162917137146, |
| "eval_runtime": 519.149, |
| "eval_samples_per_second": 17.338, |
| "eval_steps_per_second": 0.543, |
| "step": 334 |
| }, |
| { |
| "epoch": 0.9998129092609915, |
| "step": 334, |
| "total_flos": 1272538881589248.0, |
| "train_loss": 0.6363063543856501, |
| "train_runtime": 30442.9812, |
| "train_samples_per_second": 5.617, |
| "train_steps_per_second": 0.011 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 334, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "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": 1272538881589248.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
