| {"loss": 0.46143222, "token_acc": 0.86343383, "grad_norm": 9.3185215, "learning_rate": 3.33e-06, "memory(GiB)": 54.87, "train_speed(iter/s)": 0.015237, "epoch": 0.04102564, "global_step/max_steps": "1/24", "percentage": "4.17%", "elapsed_time": "55s", "remaining_time": "21m 7s"} |
| {"loss": 0.47108185, "token_acc": 0.85968093, "grad_norm": 8.64310455, "learning_rate": 6.67e-06, "memory(GiB)": 54.87, "train_speed(iter/s)": 0.018995, "epoch": 0.08205128, "global_step/max_steps": "2/24", "percentage": "8.33%", "elapsed_time": "1m 34s", "remaining_time": "17m 22s"} |
| {"loss": 0.42076147, "token_acc": 0.85514685, "grad_norm": 5.66566086, "learning_rate": 1e-05, "memory(GiB)": 54.87, "train_speed(iter/s)": 0.020169, "epoch": 0.12307692, "global_step/max_steps": "3/24", "percentage": "12.50%", "elapsed_time": "2m 18s", "remaining_time": "16m 7s"} |
| {"loss": 0.37250823, "token_acc": 0.88401355, "grad_norm": 6.63496256, "learning_rate": 9.52e-06, "memory(GiB)": 76.52, "train_speed(iter/s)": 0.019331, "epoch": 0.16410256, "global_step/max_steps": "4/24", "percentage": "16.67%", "elapsed_time": "3m 16s", "remaining_time": "16m 21s"} |
| {"loss": 0.34375307, "token_acc": 0.87457379, "grad_norm": 4.0149045, "learning_rate": 9.05e-06, "memory(GiB)": 76.52, "train_speed(iter/s)": 0.019574, "epoch": 0.20512821, "global_step/max_steps": "5/24", "percentage": "20.83%", "elapsed_time": "4m 4s", "remaining_time": "15m 30s"} |
| {"loss": 0.35020918, "token_acc": 0.8917227, "grad_norm": 3.02704263, "learning_rate": 8.57e-06, "memory(GiB)": 76.52, "train_speed(iter/s)": 0.020114, "epoch": 0.24615385, "global_step/max_steps": "6/24", "percentage": "25.00%", "elapsed_time": "4m 47s", "remaining_time": "14m 23s"} |
| {"loss": 0.31043854, "token_acc": 0.90935031, "grad_norm": 2.69551635, "learning_rate": 8.1e-06, "memory(GiB)": 76.52, "train_speed(iter/s)": 0.02063, "epoch": 0.28717949, "global_step/max_steps": "7/24", "percentage": "29.17%", "elapsed_time": "5m 28s", "remaining_time": "13m 18s"} |
| {"loss": 0.3027271, "token_acc": 0.89195308, "grad_norm": 2.27069497, "learning_rate": 7.62e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.020872, "epoch": 0.32820513, "global_step/max_steps": "8/24", "percentage": "33.33%", "elapsed_time": "6m 12s", "remaining_time": "12m 25s"} |
| {"loss": 0.28800282, "token_acc": 0.91445856, "grad_norm": 2.58754706, "learning_rate": 7.14e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.020954, "epoch": 0.36923077, "global_step/max_steps": "9/24", "percentage": "37.50%", "elapsed_time": "6m 58s", "remaining_time": "11m 38s"} |
| {"loss": 0.28545466, "token_acc": 0.90576357, "grad_norm": 2.16132617, "learning_rate": 6.67e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.021314, "epoch": 0.41025641, "global_step/max_steps": "10/24", "percentage": "41.67%", "elapsed_time": "7m 38s", "remaining_time": "10m 42s"} |
| {"eval_loss": 0.29409501, "eval_token_acc": 0.90527162, "eval_runtime": 10.0421, "eval_samples_per_second": 4.78, "eval_steps_per_second": 0.597, "epoch": 0.41025641, "global_step/max_steps": "10/24", "percentage": "41.67%", "elapsed_time": "7m 48s", "remaining_time": "10m 56s"} |
| {"loss": 0.29755145, "token_acc": 0.89969161, "grad_norm": 2.20071864, "learning_rate": 6.19e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.02072, "epoch": 0.45128205, "global_step/max_steps": "11/24", "percentage": "45.83%", "elapsed_time": "8m 40s", "remaining_time": "10m 14s"} |
| {"loss": 0.28594711, "token_acc": 0.90274928, "grad_norm": 2.26474857, "learning_rate": 5.71e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.020675, "epoch": 0.49230769, "global_step/max_steps": "12/24", "percentage": "50.00%", "elapsed_time": "9m 29s", "remaining_time": "9m 29s"} |
| {"loss": 0.27647626, "token_acc": 0.89691489, "grad_norm": 2.19667244, "learning_rate": 5.24e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.020771, "epoch": 0.53333333, "global_step/max_steps": "13/24", "percentage": "54.17%", "elapsed_time": "10m 15s", "remaining_time": "8m 40s"} |
| {"loss": 0.28978908, "token_acc": 0.92168009, "grad_norm": 2.21953773, "learning_rate": 4.76e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.020869, "epoch": 0.57435897, "global_step/max_steps": "14/24", "percentage": "58.33%", "elapsed_time": "11m 0s", "remaining_time": "7m 51s"} |
| {"loss": 0.25644785, "token_acc": 0.91911697, "grad_norm": 1.99253571, "learning_rate": 4.29e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.021005, "epoch": 0.61538462, "global_step/max_steps": "15/24", "percentage": "62.50%", "elapsed_time": "11m 43s", "remaining_time": "7m 2s"} |
| {"loss": 0.25205338, "token_acc": 0.92406639, "grad_norm": 1.91407692, "learning_rate": 3.81e-06, "memory(GiB)": 102.1, "train_speed(iter/s)": 0.020998, "epoch": 0.65641026, "global_step/max_steps": "16/24", "percentage": "66.67%", "elapsed_time": "12m 31s", "remaining_time": "6m 15s"} |
| {"loss": 0.25136927, "token_acc": 0.92661265, "grad_norm": 1.94001377, "learning_rate": 3.33e-06, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.02106, "epoch": 0.6974359, "global_step/max_steps": "17/24", "percentage": "70.83%", "elapsed_time": "13m 16s", "remaining_time": "5m 28s"} |
| {"loss": 0.27359912, "token_acc": 0.89710177, "grad_norm": 2.43866014, "learning_rate": 2.86e-06, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.021257, "epoch": 0.73846154, "global_step/max_steps": "18/24", "percentage": "75.00%", "elapsed_time": "13m 56s", "remaining_time": "4m 38s"} |
| {"loss": 0.23825151, "token_acc": 0.92749731, "grad_norm": 2.5236938, "learning_rate": 2.38e-06, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.021291, "epoch": 0.77948718, "global_step/max_steps": "19/24", "percentage": "79.17%", "elapsed_time": "14m 41s", "remaining_time": "3m 52s"} |
| {"loss": 0.25170776, "token_acc": 0.89211481, "grad_norm": 3.14535904, "learning_rate": 1.9e-06, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.021329, "epoch": 0.82051282, "global_step/max_steps": "20/24", "percentage": "83.33%", "elapsed_time": "15m 27s", "remaining_time": "3m 5s"} |
| {"eval_loss": 0.26594558, "eval_token_acc": 0.91252329, "eval_runtime": 10.0357, "eval_samples_per_second": 4.783, "eval_steps_per_second": 0.598, "epoch": 0.82051282, "global_step/max_steps": "20/24", "percentage": "83.33%", "elapsed_time": "15m 37s", "remaining_time": "3m 7s"} |
| {"loss": 0.23205811, "token_acc": 0.90668009, "grad_norm": 3.71121573, "learning_rate": 1.43e-06, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.020958, "epoch": 0.86153846, "global_step/max_steps": "21/24", "percentage": "87.50%", "elapsed_time": "16m 31s", "remaining_time": "2m 21s"} |
| {"loss": 0.21498692, "token_acc": 0.93693359, "grad_norm": 1.96844864, "learning_rate": 9.5e-07, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.020997, "epoch": 0.9025641, "global_step/max_steps": "22/24", "percentage": "91.67%", "elapsed_time": "17m 17s", "remaining_time": "1m 34s"} |
| {"loss": 0.26505035, "token_acc": 0.88642392, "grad_norm": 2.83930326, "learning_rate": 4.8e-07, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.021149, "epoch": 0.94358974, "global_step/max_steps": "23/24", "percentage": "95.83%", "elapsed_time": "17m 56s", "remaining_time": "46s"} |
| {"loss": 0.21959037, "token_acc": 0.92977191, "grad_norm": 1.96380556, "learning_rate": 0.0, "memory(GiB)": 117.53, "train_speed(iter/s)": 0.021197, "epoch": 0.98461538, "global_step/max_steps": "24/24", "percentage": "100.00%", "elapsed_time": "18m 41s", "remaining_time": "0s"} |
| {"eval_loss": 0.26333836, "eval_token_acc": 0.91394805, "eval_runtime": 10.028, "eval_samples_per_second": 4.787, "eval_steps_per_second": 0.598, "epoch": 0.98461538, "global_step/max_steps": "24/24", "percentage": "100.00%", "elapsed_time": "18m 51s", "remaining_time": "0s"} |
| {"train_runtime": 1136.4427, "train_samples_per_second": 1.367, "train_steps_per_second": 0.021, "total_flos": 31015965818880.0, "train_loss": 0.30046865, "epoch": 0.98461538, "global_step/max_steps": "24/24", "percentage": "100.00%", "elapsed_time": "18m 56s", "remaining_time": "0s"} |
|
|
