| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 6.999519461797213, | |
| "global_step": 7280, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 4.656593406593407e-05, | |
| "loss": 1.5943, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "learning_rate": 4.3131868131868134e-05, | |
| "loss": 1.6732, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 19.2321, | |
| "eval_loss": 2.4691147804260254, | |
| "eval_rouge1": 25.8418, | |
| "eval_rouge2": 8.7011, | |
| "eval_rougeL": 21.1569, | |
| "eval_rougeLsum": 21.4706, | |
| "eval_runtime": 1188.0405, | |
| "eval_samples_per_second": 8.719, | |
| "step": 1040 | |
| }, | |
| { | |
| "epoch": 1.44, | |
| "learning_rate": 3.96978021978022e-05, | |
| "loss": 1.9331, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 1.92, | |
| "learning_rate": 3.6263736263736266e-05, | |
| "loss": 1.9543, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 19.2853, | |
| "eval_loss": 2.4091384410858154, | |
| "eval_rouge1": 26.1697, | |
| "eval_rouge2": 9.222, | |
| "eval_rougeL": 21.5166, | |
| "eval_rougeLsum": 21.8758, | |
| "eval_runtime": 1168.6884, | |
| "eval_samples_per_second": 8.863, | |
| "step": 2080 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "learning_rate": 3.282967032967033e-05, | |
| "loss": 1.8371, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 2.88, | |
| "learning_rate": 2.9395604395604398e-05, | |
| "loss": 1.8282, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "eval_gen_len": 19.2576, | |
| "eval_loss": 2.42261004447937, | |
| "eval_rouge1": 26.1165, | |
| "eval_rouge2": 9.2438, | |
| "eval_rougeL": 21.5311, | |
| "eval_rougeLsum": 21.8577, | |
| "eval_runtime": 1236.3561, | |
| "eval_samples_per_second": 8.378, | |
| "step": 3120 | |
| }, | |
| { | |
| "epoch": 3.37, | |
| "learning_rate": 2.5961538461538464e-05, | |
| "loss": 1.7419, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 3.85, | |
| "learning_rate": 2.252747252747253e-05, | |
| "loss": 1.7287, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "eval_gen_len": 19.2905, | |
| "eval_loss": 2.4440300464630127, | |
| "eval_rouge1": 26.2529, | |
| "eval_rouge2": 9.3031, | |
| "eval_rougeL": 21.5955, | |
| "eval_rougeLsum": 21.9465, | |
| "eval_runtime": 1217.0172, | |
| "eval_samples_per_second": 8.511, | |
| "step": 4160 | |
| }, | |
| { | |
| "epoch": 4.33, | |
| "learning_rate": 1.9093406593406592e-05, | |
| "loss": 1.6642, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 4.81, | |
| "learning_rate": 1.565934065934066e-05, | |
| "loss": 1.6481, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "eval_gen_len": 19.1729, | |
| "eval_loss": 2.471247673034668, | |
| "eval_rouge1": 26.1789, | |
| "eval_rouge2": 9.2847, | |
| "eval_rougeL": 21.5357, | |
| "eval_rougeLsum": 21.8938, | |
| "eval_runtime": 1247.3952, | |
| "eval_samples_per_second": 8.304, | |
| "step": 5200 | |
| }, | |
| { | |
| "epoch": 5.29, | |
| "learning_rate": 1.2225274725274726e-05, | |
| "loss": 1.6071, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 5.77, | |
| "learning_rate": 8.791208791208792e-06, | |
| "loss": 1.5796, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "eval_gen_len": 19.2078, | |
| "eval_loss": 2.485071897506714, | |
| "eval_rouge1": 26.07, | |
| "eval_rouge2": 9.1429, | |
| "eval_rougeL": 21.414, | |
| "eval_rougeLsum": 21.7483, | |
| "eval_runtime": 1301.5565, | |
| "eval_samples_per_second": 7.958, | |
| "step": 6240 | |
| }, | |
| { | |
| "epoch": 6.25, | |
| "learning_rate": 5.357142857142857e-06, | |
| "loss": 1.5558, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 6.73, | |
| "learning_rate": 1.9230769230769234e-06, | |
| "loss": 1.5319, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 19.2394, | |
| "eval_loss": 2.5021677017211914, | |
| "eval_rouge1": 26.1256, | |
| "eval_rouge2": 9.2552, | |
| "eval_rougeL": 21.4899, | |
| "eval_rougeLsum": 21.8194, | |
| "eval_runtime": 1250.4536, | |
| "eval_samples_per_second": 8.283, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "step": 7280, | |
| "total_flos": 1.5986426003154386e+18, | |
| "train_runtime": 137981.946, | |
| "train_samples_per_second": 0.053 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 19.2394, | |
| "eval_loss": 2.5021677017211914, | |
| "eval_rouge1": 26.1256, | |
| "eval_rouge2": 9.2552, | |
| "eval_rougeL": 21.4899, | |
| "eval_rougeLsum": 21.8194, | |
| "eval_runtime": 1276.236, | |
| "eval_samples_per_second": 8.116, | |
| "step": 7280 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "eval_gen_len": 19.2463, | |
| "eval_loss": 2.57672381401062, | |
| "eval_rouge1": 25.8639, | |
| "eval_rouge2": 8.911, | |
| "eval_rougeL": 21.2426, | |
| "eval_rougeLsum": 21.5859, | |
| "eval_runtime": 1713.2216, | |
| "eval_samples_per_second": 8.125, | |
| "step": 7280 | |
| } | |
| ], | |
| "max_steps": 7280, | |
| "num_train_epochs": 7, | |
| "total_flos": 1.5986426003154386e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |