| { | |
| "best_metric": 1.4883581399917603, | |
| "best_model_checkpoint": "ccdv_pegasus_xsum_summarization/checkpoint-13500", | |
| "epoch": 2.0012007204322595, | |
| "global_step": 30000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 4.944411091099104e-05, | |
| "loss": 1.3482, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "eval_gen_len": 190.7041, | |
| "eval_loss": 1.5671061277389526, | |
| "eval_rouge1": 43.9725, | |
| "eval_rouge2": 20.8852, | |
| "eval_rougeL": 29.6036, | |
| "eval_rougeLsum": 39.2595, | |
| "eval_runtime": 10745.9844, | |
| "eval_samples_per_second": 0.617, | |
| "eval_steps_per_second": 0.077, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "learning_rate": 4.8888221821982085e-05, | |
| "loss": 1.0335, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.07, | |
| "eval_gen_len": 159.8545, | |
| "eval_loss": 1.5465657711029053, | |
| "eval_rouge1": 44.9236, | |
| "eval_rouge2": 21.1853, | |
| "eval_rougeL": 30.4447, | |
| "eval_rougeLsum": 39.9918, | |
| "eval_runtime": 10231.1208, | |
| "eval_samples_per_second": 0.648, | |
| "eval_steps_per_second": 0.081, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 4.8332332732973116e-05, | |
| "loss": 1.0184, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "eval_gen_len": 143.5453, | |
| "eval_loss": 1.5334348678588867, | |
| "eval_rouge1": 44.9483, | |
| "eval_rouge2": 20.9962, | |
| "eval_rougeL": 30.5328, | |
| "eval_rougeLsum": 40.0531, | |
| "eval_runtime": 8769.3615, | |
| "eval_samples_per_second": 0.756, | |
| "eval_steps_per_second": 0.095, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 4.777644364396416e-05, | |
| "loss": 1.0015, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_gen_len": 137.856, | |
| "eval_loss": 1.529853343963623, | |
| "eval_rouge1": 45.9034, | |
| "eval_rouge2": 21.784, | |
| "eval_rougeL": 31.4025, | |
| "eval_rougeLsum": 40.8983, | |
| "eval_runtime": 7582.4229, | |
| "eval_samples_per_second": 0.875, | |
| "eval_steps_per_second": 0.109, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 4.72205545549552e-05, | |
| "loss": 1.0101, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "eval_gen_len": 134.5485, | |
| "eval_loss": 1.5291049480438232, | |
| "eval_rouge1": 45.6738, | |
| "eval_rouge2": 21.5853, | |
| "eval_rougeL": 31.1439, | |
| "eval_rougeLsum": 40.7442, | |
| "eval_runtime": 6945.0608, | |
| "eval_samples_per_second": 0.955, | |
| "eval_steps_per_second": 0.12, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "learning_rate": 4.6664665465946236e-05, | |
| "loss": 0.9973, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.2, | |
| "eval_gen_len": 131.2587, | |
| "eval_loss": 1.523977518081665, | |
| "eval_rouge1": 45.5052, | |
| "eval_rouge2": 21.4202, | |
| "eval_rougeL": 31.1499, | |
| "eval_rougeLsum": 40.5736, | |
| "eval_runtime": 6458.4712, | |
| "eval_samples_per_second": 1.027, | |
| "eval_steps_per_second": 0.129, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 4.6108776376937274e-05, | |
| "loss": 0.9855, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "eval_gen_len": 131.0582, | |
| "eval_loss": 1.5234577655792236, | |
| "eval_rouge1": 45.8336, | |
| "eval_rouge2": 21.7072, | |
| "eval_rougeL": 31.439, | |
| "eval_rougeLsum": 40.9387, | |
| "eval_runtime": 6345.3859, | |
| "eval_samples_per_second": 1.045, | |
| "eval_steps_per_second": 0.131, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 4.555288728792831e-05, | |
| "loss": 0.9868, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "eval_gen_len": 127.9753, | |
| "eval_loss": 1.5183237791061401, | |
| "eval_rouge1": 45.6348, | |
| "eval_rouge2": 21.5462, | |
| "eval_rougeL": 31.3009, | |
| "eval_rougeLsum": 40.6469, | |
| "eval_runtime": 6091.2782, | |
| "eval_samples_per_second": 1.089, | |
| "eval_steps_per_second": 0.136, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 4.4996998198919356e-05, | |
| "loss": 0.9802, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "eval_gen_len": 127.78, | |
| "eval_loss": 1.5132805109024048, | |
| "eval_rouge1": 45.4357, | |
| "eval_rouge2": 21.3339, | |
| "eval_rougeL": 31.1304, | |
| "eval_rougeLsum": 40.531, | |
| "eval_runtime": 5970.8563, | |
| "eval_samples_per_second": 1.111, | |
| "eval_steps_per_second": 0.139, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 4.4441109109910394e-05, | |
| "loss": 0.9743, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "eval_gen_len": 126.9619, | |
| "eval_loss": 1.5101301670074463, | |
| "eval_rouge1": 45.4845, | |
| "eval_rouge2": 21.4302, | |
| "eval_rougeL": 31.2033, | |
| "eval_rougeLsum": 40.5934, | |
| "eval_runtime": 5820.9525, | |
| "eval_samples_per_second": 1.14, | |
| "eval_steps_per_second": 0.143, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 4.388522002090143e-05, | |
| "loss": 0.972, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "eval_gen_len": 127.1796, | |
| "eval_loss": 1.5053614377975464, | |
| "eval_rouge1": 45.196, | |
| "eval_rouge2": 21.1882, | |
| "eval_rougeL": 30.9407, | |
| "eval_rougeLsum": 40.2648, | |
| "eval_runtime": 5768.324, | |
| "eval_samples_per_second": 1.15, | |
| "eval_steps_per_second": 0.144, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 4.332933093189247e-05, | |
| "loss": 0.9651, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "eval_gen_len": 126.9254, | |
| "eval_loss": 1.5030862092971802, | |
| "eval_rouge1": 45.4822, | |
| "eval_rouge2": 21.4363, | |
| "eval_rougeL": 31.1422, | |
| "eval_rougeLsum": 40.5397, | |
| "eval_runtime": 5665.8916, | |
| "eval_samples_per_second": 1.171, | |
| "eval_steps_per_second": 0.146, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "learning_rate": 4.277344184288351e-05, | |
| "loss": 0.9758, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.43, | |
| "eval_gen_len": 126.4933, | |
| "eval_loss": 1.495548963546753, | |
| "eval_rouge1": 45.299, | |
| "eval_rouge2": 21.346, | |
| "eval_rougeL": 31.0361, | |
| "eval_rougeLsum": 40.3325, | |
| "eval_runtime": 5589.2093, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.149, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "learning_rate": 4.221755275387455e-05, | |
| "loss": 0.9652, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.47, | |
| "eval_gen_len": 126.0859, | |
| "eval_loss": 1.4975615739822388, | |
| "eval_rouge1": 45.4694, | |
| "eval_rouge2": 21.5044, | |
| "eval_rougeL": 31.1786, | |
| "eval_rougeLsum": 40.5032, | |
| "eval_runtime": 5569.8623, | |
| "eval_samples_per_second": 1.191, | |
| "eval_steps_per_second": 0.149, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 4.166166366486558e-05, | |
| "loss": 0.9601, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "eval_gen_len": 126.8815, | |
| "eval_loss": 1.4945002794265747, | |
| "eval_rouge1": 45.1971, | |
| "eval_rouge2": 21.2682, | |
| "eval_rougeL": 30.9321, | |
| "eval_rougeLsum": 40.2959, | |
| "eval_runtime": 5557.7856, | |
| "eval_samples_per_second": 1.193, | |
| "eval_steps_per_second": 0.149, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 4.110577457585663e-05, | |
| "loss": 0.9502, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "eval_gen_len": 126.4628, | |
| "eval_loss": 1.49406898021698, | |
| "eval_rouge1": 45.5653, | |
| "eval_rouge2": 21.5655, | |
| "eval_rougeL": 31.2703, | |
| "eval_rougeLsum": 40.5622, | |
| "eval_runtime": 5535.3927, | |
| "eval_samples_per_second": 1.198, | |
| "eval_steps_per_second": 0.15, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 4.0549885486847665e-05, | |
| "loss": 0.9537, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "eval_gen_len": 126.5709, | |
| "eval_loss": 1.4941043853759766, | |
| "eval_rouge1": 45.2806, | |
| "eval_rouge2": 21.2587, | |
| "eval_rougeL": 30.93, | |
| "eval_rougeLsum": 40.354, | |
| "eval_runtime": 5533.5879, | |
| "eval_samples_per_second": 1.199, | |
| "eval_steps_per_second": 0.15, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 3.999399639783871e-05, | |
| "loss": 0.9629, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "eval_gen_len": 126.547, | |
| "eval_loss": 1.4939745664596558, | |
| "eval_rouge1": 45.2474, | |
| "eval_rouge2": 21.275, | |
| "eval_rougeL": 30.9302, | |
| "eval_rougeLsum": 40.3377, | |
| "eval_runtime": 5530.7272, | |
| "eval_samples_per_second": 1.199, | |
| "eval_steps_per_second": 0.15, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 3.943810730882974e-05, | |
| "loss": 0.9528, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "eval_gen_len": 126.768, | |
| "eval_loss": 1.4947481155395508, | |
| "eval_rouge1": 45.3619, | |
| "eval_rouge2": 21.3754, | |
| "eval_rougeL": 31.0723, | |
| "eval_rougeLsum": 40.4162, | |
| "eval_runtime": 5524.5717, | |
| "eval_samples_per_second": 1.201, | |
| "eval_steps_per_second": 0.15, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "learning_rate": 3.888221821982078e-05, | |
| "loss": 0.9532, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.67, | |
| "eval_gen_len": 126.5323, | |
| "eval_loss": 1.4923893213272095, | |
| "eval_rouge1": 45.5763, | |
| "eval_rouge2": 21.6469, | |
| "eval_rougeL": 31.2585, | |
| "eval_rougeLsum": 40.5722, | |
| "eval_runtime": 5518.2912, | |
| "eval_samples_per_second": 1.202, | |
| "eval_steps_per_second": 0.15, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "learning_rate": 3.832632913081182e-05, | |
| "loss": 0.945, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.7, | |
| "eval_gen_len": 126.69, | |
| "eval_loss": 1.4898710250854492, | |
| "eval_rouge1": 45.2629, | |
| "eval_rouge2": 21.3471, | |
| "eval_rougeL": 31.0405, | |
| "eval_rougeLsum": 40.3211, | |
| "eval_runtime": 6184.8714, | |
| "eval_samples_per_second": 1.072, | |
| "eval_steps_per_second": 0.134, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "learning_rate": 3.777044004180286e-05, | |
| "loss": 0.9464, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.73, | |
| "eval_gen_len": 126.9052, | |
| "eval_loss": 1.489205002784729, | |
| "eval_rouge1": 45.3769, | |
| "eval_rouge2": 21.3457, | |
| "eval_rougeL": 30.9968, | |
| "eval_rougeLsum": 40.388, | |
| "eval_runtime": 5520.5499, | |
| "eval_samples_per_second": 1.202, | |
| "eval_steps_per_second": 0.15, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "learning_rate": 3.7214550952793906e-05, | |
| "loss": 0.9544, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.77, | |
| "eval_gen_len": 126.5739, | |
| "eval_loss": 1.4892535209655762, | |
| "eval_rouge1": 45.411, | |
| "eval_rouge2": 21.3852, | |
| "eval_rougeL": 31.0295, | |
| "eval_rougeLsum": 40.4881, | |
| "eval_runtime": 5521.4271, | |
| "eval_samples_per_second": 1.201, | |
| "eval_steps_per_second": 0.15, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "learning_rate": 3.6658661863784937e-05, | |
| "loss": 0.9467, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "eval_gen_len": 126.7315, | |
| "eval_loss": 1.4929231405258179, | |
| "eval_rouge1": 45.4345, | |
| "eval_rouge2": 21.4378, | |
| "eval_rougeL": 31.1163, | |
| "eval_rougeLsum": 40.4393, | |
| "eval_runtime": 5524.2145, | |
| "eval_samples_per_second": 1.201, | |
| "eval_steps_per_second": 0.15, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "learning_rate": 3.610277277477598e-05, | |
| "loss": 0.9517, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.83, | |
| "eval_gen_len": 126.58, | |
| "eval_loss": 1.4917516708374023, | |
| "eval_rouge1": 45.3614, | |
| "eval_rouge2": 21.3396, | |
| "eval_rougeL": 30.9925, | |
| "eval_rougeLsum": 40.3636, | |
| "eval_runtime": 5514.201, | |
| "eval_samples_per_second": 1.203, | |
| "eval_steps_per_second": 0.151, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "learning_rate": 3.554688368576702e-05, | |
| "loss": 0.9497, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.87, | |
| "eval_gen_len": 126.7977, | |
| "eval_loss": 1.4918133020401, | |
| "eval_rouge1": 45.2485, | |
| "eval_rouge2": 21.2367, | |
| "eval_rougeL": 30.9282, | |
| "eval_rougeLsum": 40.3438, | |
| "eval_runtime": 6509.3818, | |
| "eval_samples_per_second": 1.019, | |
| "eval_steps_per_second": 0.128, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "learning_rate": 3.499099459675806e-05, | |
| "loss": 0.9386, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.9, | |
| "eval_gen_len": 126.7524, | |
| "eval_loss": 1.4883581399917603, | |
| "eval_rouge1": 45.5038, | |
| "eval_rouge2": 21.5064, | |
| "eval_rougeL": 31.2132, | |
| "eval_rougeLsum": 40.5696, | |
| "eval_runtime": 5529.57, | |
| "eval_samples_per_second": 1.2, | |
| "eval_steps_per_second": 0.15, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "learning_rate": 3.4435105507749095e-05, | |
| "loss": 0.9473, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.93, | |
| "eval_gen_len": 126.6534, | |
| "eval_loss": 1.4918317794799805, | |
| "eval_rouge1": 45.2367, | |
| "eval_rouge2": 21.2615, | |
| "eval_rougeL": 30.9179, | |
| "eval_rougeLsum": 40.2548, | |
| "eval_runtime": 5515.735, | |
| "eval_samples_per_second": 1.203, | |
| "eval_steps_per_second": 0.15, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "learning_rate": 3.387921641874013e-05, | |
| "loss": 0.9235, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.97, | |
| "eval_gen_len": 126.5972, | |
| "eval_loss": 1.4897193908691406, | |
| "eval_rouge1": 45.8027, | |
| "eval_rouge2": 21.7228, | |
| "eval_rougeL": 31.3946, | |
| "eval_rougeLsum": 40.764, | |
| "eval_runtime": 5518.2889, | |
| "eval_samples_per_second": 1.202, | |
| "eval_steps_per_second": 0.15, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "learning_rate": 3.332332732973118e-05, | |
| "loss": 0.9344, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "eval_gen_len": 126.9212, | |
| "eval_loss": 1.4973394870758057, | |
| "eval_rouge1": 44.8773, | |
| "eval_rouge2": 20.9475, | |
| "eval_rougeL": 30.5827, | |
| "eval_rougeLsum": 39.9489, | |
| "eval_runtime": 5510.2549, | |
| "eval_samples_per_second": 1.204, | |
| "eval_steps_per_second": 0.151, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "learning_rate": 3.2767438240722215e-05, | |
| "loss": 0.9139, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.03, | |
| "eval_gen_len": 126.692, | |
| "eval_loss": 1.5064738988876343, | |
| "eval_rouge1": 45.4207, | |
| "eval_rouge2": 21.3856, | |
| "eval_rougeL": 31.0837, | |
| "eval_rougeLsum": 40.4414, | |
| "eval_runtime": 5526.017, | |
| "eval_samples_per_second": 1.2, | |
| "eval_steps_per_second": 0.15, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "learning_rate": 3.221154915171325e-05, | |
| "loss": 0.8939, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.07, | |
| "eval_gen_len": 126.5179, | |
| "eval_loss": 1.508902668952942, | |
| "eval_rouge1": 45.5575, | |
| "eval_rouge2": 21.5153, | |
| "eval_rougeL": 31.2115, | |
| "eval_rougeLsum": 40.5517, | |
| "eval_runtime": 5698.8075, | |
| "eval_samples_per_second": 1.164, | |
| "eval_steps_per_second": 0.146, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "learning_rate": 3.165566006270429e-05, | |
| "loss": 0.8968, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.1, | |
| "eval_gen_len": 126.5447, | |
| "eval_loss": 1.5106098651885986, | |
| "eval_rouge1": 45.4574, | |
| "eval_rouge2": 21.4786, | |
| "eval_rougeL": 31.1065, | |
| "eval_rougeLsum": 40.495, | |
| "eval_runtime": 5606.9538, | |
| "eval_samples_per_second": 1.183, | |
| "eval_steps_per_second": 0.148, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "learning_rate": 3.109977097369533e-05, | |
| "loss": 0.8999, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.13, | |
| "eval_gen_len": 126.6894, | |
| "eval_loss": 1.5100876092910767, | |
| "eval_rouge1": 45.4805, | |
| "eval_rouge2": 21.4579, | |
| "eval_rougeL": 31.1062, | |
| "eval_rougeLsum": 40.5138, | |
| "eval_runtime": 5594.355, | |
| "eval_samples_per_second": 1.186, | |
| "eval_steps_per_second": 0.148, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "learning_rate": 3.054388188468637e-05, | |
| "loss": 0.903, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.17, | |
| "eval_gen_len": 126.5988, | |
| "eval_loss": 1.5103389024734497, | |
| "eval_rouge1": 45.495, | |
| "eval_rouge2": 21.4395, | |
| "eval_rougeL": 31.1445, | |
| "eval_rougeLsum": 40.4949, | |
| "eval_runtime": 5586.6059, | |
| "eval_samples_per_second": 1.187, | |
| "eval_steps_per_second": 0.149, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "learning_rate": 2.9987992795677407e-05, | |
| "loss": 0.8988, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.2, | |
| "eval_gen_len": 126.5643, | |
| "eval_loss": 1.5120760202407837, | |
| "eval_rouge1": 45.2764, | |
| "eval_rouge2": 21.2652, | |
| "eval_rougeL": 30.944, | |
| "eval_rougeLsum": 40.3249, | |
| "eval_runtime": 5558.8098, | |
| "eval_samples_per_second": 1.193, | |
| "eval_steps_per_second": 0.149, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "learning_rate": 2.9432103706668445e-05, | |
| "loss": 0.9027, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.23, | |
| "eval_gen_len": 126.8441, | |
| "eval_loss": 1.5092076063156128, | |
| "eval_rouge1": 45.4884, | |
| "eval_rouge2": 21.4334, | |
| "eval_rougeL": 31.0499, | |
| "eval_rougeLsum": 40.4796, | |
| "eval_runtime": 5536.9856, | |
| "eval_samples_per_second": 1.198, | |
| "eval_steps_per_second": 0.15, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "learning_rate": 2.8876214617659486e-05, | |
| "loss": 0.9044, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.27, | |
| "eval_gen_len": 126.8737, | |
| "eval_loss": 1.5079020261764526, | |
| "eval_rouge1": 45.5708, | |
| "eval_rouge2": 21.5358, | |
| "eval_rougeL": 31.1862, | |
| "eval_rougeLsum": 40.594, | |
| "eval_runtime": 5524.867, | |
| "eval_samples_per_second": 1.201, | |
| "eval_steps_per_second": 0.15, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "learning_rate": 2.8320325528650527e-05, | |
| "loss": 0.906, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.3, | |
| "eval_gen_len": 126.8627, | |
| "eval_loss": 1.5116254091262817, | |
| "eval_rouge1": 45.4542, | |
| "eval_rouge2": 21.4172, | |
| "eval_rougeL": 31.0754, | |
| "eval_rougeLsum": 40.439, | |
| "eval_runtime": 5524.341, | |
| "eval_samples_per_second": 1.201, | |
| "eval_steps_per_second": 0.15, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "learning_rate": 2.776443643964157e-05, | |
| "loss": 0.8994, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.33, | |
| "eval_gen_len": 126.8206, | |
| "eval_loss": 1.5085355043411255, | |
| "eval_rouge1": 45.5424, | |
| "eval_rouge2": 21.5009, | |
| "eval_rougeL": 31.1428, | |
| "eval_rougeLsum": 40.5667, | |
| "eval_runtime": 5528.1375, | |
| "eval_samples_per_second": 1.2, | |
| "eval_steps_per_second": 0.15, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "learning_rate": 2.7208547350632603e-05, | |
| "loss": 0.9088, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.37, | |
| "eval_gen_len": 126.7414, | |
| "eval_loss": 1.5124515295028687, | |
| "eval_rouge1": 45.3129, | |
| "eval_rouge2": 21.2629, | |
| "eval_rougeL": 30.9461, | |
| "eval_rougeLsum": 40.3271, | |
| "eval_runtime": 5534.3419, | |
| "eval_samples_per_second": 1.199, | |
| "eval_steps_per_second": 0.15, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "learning_rate": 2.665265826162364e-05, | |
| "loss": 0.8983, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.4, | |
| "eval_gen_len": 126.357, | |
| "eval_loss": 1.5135449171066284, | |
| "eval_rouge1": 45.6846, | |
| "eval_rouge2": 21.6282, | |
| "eval_rougeL": 31.2929, | |
| "eval_rougeLsum": 40.6821, | |
| "eval_runtime": 5538.2932, | |
| "eval_samples_per_second": 1.198, | |
| "eval_steps_per_second": 0.15, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "learning_rate": 2.6096769172614682e-05, | |
| "loss": 0.907, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.43, | |
| "eval_gen_len": 127.0029, | |
| "eval_loss": 1.5076923370361328, | |
| "eval_rouge1": 45.4873, | |
| "eval_rouge2": 21.455, | |
| "eval_rougeL": 31.1193, | |
| "eval_rougeLsum": 40.5128, | |
| "eval_runtime": 5539.9922, | |
| "eval_samples_per_second": 1.197, | |
| "eval_steps_per_second": 0.15, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "learning_rate": 2.5540880083605723e-05, | |
| "loss": 0.9097, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.47, | |
| "eval_gen_len": 126.8553, | |
| "eval_loss": 1.5052434206008911, | |
| "eval_rouge1": 45.5988, | |
| "eval_rouge2": 21.6134, | |
| "eval_rougeL": 31.247, | |
| "eval_rougeLsum": 40.58, | |
| "eval_runtime": 5539.7468, | |
| "eval_samples_per_second": 1.197, | |
| "eval_steps_per_second": 0.15, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "learning_rate": 2.498499099459676e-05, | |
| "loss": 0.9033, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.5, | |
| "eval_gen_len": 127.0048, | |
| "eval_loss": 1.5133850574493408, | |
| "eval_rouge1": 45.3223, | |
| "eval_rouge2": 21.2968, | |
| "eval_rougeL": 30.9357, | |
| "eval_rougeLsum": 40.3813, | |
| "eval_runtime": 9404.5, | |
| "eval_samples_per_second": 0.705, | |
| "eval_steps_per_second": 0.088, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "learning_rate": 2.44291019055878e-05, | |
| "loss": 0.8925, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.53, | |
| "eval_gen_len": 126.7316, | |
| "eval_loss": 1.510839819908142, | |
| "eval_rouge1": 45.6747, | |
| "eval_rouge2": 21.6374, | |
| "eval_rougeL": 31.31, | |
| "eval_rougeLsum": 40.7015, | |
| "eval_runtime": 22732.2519, | |
| "eval_samples_per_second": 0.292, | |
| "eval_steps_per_second": 0.037, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "learning_rate": 2.387321281657884e-05, | |
| "loss": 0.8913, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.57, | |
| "eval_gen_len": 126.6869, | |
| "eval_loss": 1.5129714012145996, | |
| "eval_rouge1": 45.6531, | |
| "eval_rouge2": 21.6354, | |
| "eval_rougeL": 31.2956, | |
| "eval_rougeLsum": 40.6555, | |
| "eval_runtime": 6945.8776, | |
| "eval_samples_per_second": 0.955, | |
| "eval_steps_per_second": 0.119, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "learning_rate": 2.3317323727569874e-05, | |
| "loss": 0.8931, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "eval_gen_len": 126.4862, | |
| "eval_loss": 1.5111068487167358, | |
| "eval_rouge1": 45.7876, | |
| "eval_rouge2": 21.7115, | |
| "eval_rougeL": 31.3274, | |
| "eval_rougeLsum": 40.7579, | |
| "eval_runtime": 5539.5619, | |
| "eval_samples_per_second": 1.197, | |
| "eval_steps_per_second": 0.15, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "learning_rate": 2.2761434638560915e-05, | |
| "loss": 0.9009, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.63, | |
| "eval_gen_len": 126.6229, | |
| "eval_loss": 1.5083845853805542, | |
| "eval_rouge1": 45.6359, | |
| "eval_rouge2": 21.583, | |
| "eval_rougeL": 31.2775, | |
| "eval_rougeLsum": 40.6351, | |
| "eval_runtime": 5545.0209, | |
| "eval_samples_per_second": 1.196, | |
| "eval_steps_per_second": 0.15, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "learning_rate": 2.2205545549551953e-05, | |
| "loss": 0.8925, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.67, | |
| "eval_gen_len": 126.8396, | |
| "eval_loss": 1.5094473361968994, | |
| "eval_rouge1": 45.397, | |
| "eval_rouge2": 21.4266, | |
| "eval_rougeL": 31.082, | |
| "eval_rougeLsum": 40.4261, | |
| "eval_runtime": 5534.6802, | |
| "eval_samples_per_second": 1.198, | |
| "eval_steps_per_second": 0.15, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "learning_rate": 2.1649656460542994e-05, | |
| "loss": 0.8991, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.7, | |
| "eval_gen_len": 126.722, | |
| "eval_loss": 1.512014627456665, | |
| "eval_rouge1": 45.2851, | |
| "eval_rouge2": 21.2798, | |
| "eval_rougeL": 30.8973, | |
| "eval_rougeLsum": 40.2787, | |
| "eval_runtime": 5538.1327, | |
| "eval_samples_per_second": 1.198, | |
| "eval_steps_per_second": 0.15, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "learning_rate": 2.1093767371534032e-05, | |
| "loss": 0.9019, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.73, | |
| "eval_gen_len": 126.8048, | |
| "eval_loss": 1.510252833366394, | |
| "eval_rouge1": 45.2905, | |
| "eval_rouge2": 21.2992, | |
| "eval_rougeL": 30.9204, | |
| "eval_rougeLsum": 40.3262, | |
| "eval_runtime": 5535.5354, | |
| "eval_samples_per_second": 1.198, | |
| "eval_steps_per_second": 0.15, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "learning_rate": 2.0537878282525073e-05, | |
| "loss": 0.891, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.77, | |
| "eval_gen_len": 126.2902, | |
| "eval_loss": 1.5112383365631104, | |
| "eval_rouge1": 45.7091, | |
| "eval_rouge2": 21.6159, | |
| "eval_rougeL": 31.2889, | |
| "eval_rougeLsum": 40.6986, | |
| "eval_runtime": 5537.5343, | |
| "eval_samples_per_second": 1.198, | |
| "eval_steps_per_second": 0.15, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "learning_rate": 1.998198919351611e-05, | |
| "loss": 0.898, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.8, | |
| "eval_gen_len": 126.5218, | |
| "eval_loss": 1.5084278583526611, | |
| "eval_rouge1": 45.4964, | |
| "eval_rouge2": 21.4702, | |
| "eval_rougeL": 31.177, | |
| "eval_rougeLsum": 40.5432, | |
| "eval_runtime": 5530.5865, | |
| "eval_samples_per_second": 1.199, | |
| "eval_steps_per_second": 0.15, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "learning_rate": 1.942610010450715e-05, | |
| "loss": 0.8839, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.83, | |
| "eval_gen_len": 126.8648, | |
| "eval_loss": 1.5090144872665405, | |
| "eval_rouge1": 45.6279, | |
| "eval_rouge2": 21.5346, | |
| "eval_rougeL": 31.252, | |
| "eval_rougeLsum": 40.6096, | |
| "eval_runtime": 5522.5033, | |
| "eval_samples_per_second": 1.201, | |
| "eval_steps_per_second": 0.15, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "learning_rate": 1.8870211015498187e-05, | |
| "loss": 0.8899, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.87, | |
| "eval_gen_len": 126.8498, | |
| "eval_loss": 1.5073039531707764, | |
| "eval_rouge1": 45.6406, | |
| "eval_rouge2": 21.5551, | |
| "eval_rougeL": 31.2519, | |
| "eval_rougeLsum": 40.6425, | |
| "eval_runtime": 5520.5026, | |
| "eval_samples_per_second": 1.202, | |
| "eval_steps_per_second": 0.15, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "learning_rate": 1.8314321926489228e-05, | |
| "loss": 0.8904, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.9, | |
| "eval_gen_len": 126.689, | |
| "eval_loss": 1.5086652040481567, | |
| "eval_rouge1": 45.7334, | |
| "eval_rouge2": 21.7071, | |
| "eval_rougeL": 31.3069, | |
| "eval_rougeLsum": 40.6992, | |
| "eval_runtime": 5519.0861, | |
| "eval_samples_per_second": 1.202, | |
| "eval_steps_per_second": 0.15, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "learning_rate": 1.7758432837480266e-05, | |
| "loss": 0.8958, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.93, | |
| "eval_gen_len": 126.9157, | |
| "eval_loss": 1.5112992525100708, | |
| "eval_rouge1": 45.4618, | |
| "eval_rouge2": 21.4623, | |
| "eval_rougeL": 31.0914, | |
| "eval_rougeLsum": 40.4648, | |
| "eval_runtime": 5520.0088, | |
| "eval_samples_per_second": 1.202, | |
| "eval_steps_per_second": 0.15, | |
| "step": 29000 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "learning_rate": 1.7202543748471307e-05, | |
| "loss": 0.8991, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 1.97, | |
| "eval_gen_len": 126.7855, | |
| "eval_loss": 1.5126971006393433, | |
| "eval_rouge1": 45.6364, | |
| "eval_rouge2": 21.5467, | |
| "eval_rougeL": 31.2001, | |
| "eval_rougeLsum": 40.5946, | |
| "eval_runtime": 5532.4138, | |
| "eval_samples_per_second": 1.199, | |
| "eval_steps_per_second": 0.15, | |
| "step": 29500 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "learning_rate": 1.6646654659462345e-05, | |
| "loss": 0.889, | |
| "step": 30000 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "eval_gen_len": 126.6989, | |
| "eval_loss": 1.5128982067108154, | |
| "eval_rouge1": 45.3668, | |
| "eval_rouge2": 21.3563, | |
| "eval_rougeL": 30.998, | |
| "eval_rougeLsum": 40.3714, | |
| "eval_runtime": 5736.9272, | |
| "eval_samples_per_second": 1.156, | |
| "eval_steps_per_second": 0.145, | |
| "step": 30000 | |
| } | |
| ], | |
| "max_steps": 44973, | |
| "num_train_epochs": 3, | |
| "total_flos": 7.801293866564321e+17, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |