Upload trainer_state.json

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 54.3016,
-  "best_model_checkpoint": "/uoa/home/s02sd1/Desktop/Project data/pytorch_project/facebook_28.03/checkpoint-43000",
-  "epoch": 64.88011283497885,
-  "global_step": 46000,
+  "best_metric": 54.4377,
+  "best_model_checkpoint": "/uoa/home/s02sd1/Desktop/Project data/pytorch_project/facebook_28.03/checkpoint-53000",
+  "epoch": 78.98448519040903,
+  "global_step": 56000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1156,11 +1156,261 @@
       "eval_samples_per_second": 0.062,
       "eval_steps_per_second": 0.003,
       "step": 46000
+    },
+    {
+      "epoch": 65.59,
+      "learning_rate": 1.0324400564174895e-06,
+      "loss": 0.0157,
+      "step": 46500
+    },
+    {
+      "epoch": 66.29,
+      "learning_rate": 1.011283497884344e-06,
+      "loss": 0.0152,
+      "step": 47000
+    },
+    {
+      "epoch": 66.29,
+      "eval_gen_len": 162.8547,
+      "eval_loss": 1.3345621824264526,
+      "eval_rouge1": 69.2641,
+      "eval_rouge2": 53.4141,
+      "eval_rougeL": 55.3861,
+      "eval_rougeLsum": 59.6768,
+      "eval_runtime": 5757.5178,
+      "eval_samples_per_second": 0.061,
+      "eval_steps_per_second": 0.003,
+      "step": 47000
+    },
+    {
+      "epoch": 67.0,
+      "learning_rate": 9.901269393511988e-07,
+      "loss": 0.0157,
+      "step": 47500
+    },
+    {
+      "epoch": 67.7,
+      "learning_rate": 9.689703808180537e-07,
+      "loss": 0.0149,
+      "step": 48000
+    },
+    {
+      "epoch": 67.7,
+      "eval_gen_len": 163.0684,
+      "eval_loss": 1.3516221046447754,
+      "eval_rouge1": 69.3874,
+      "eval_rouge2": 53.707,
+      "eval_rougeL": 56.0318,
+      "eval_rougeLsum": 60.1116,
+      "eval_runtime": 5778.0873,
+      "eval_samples_per_second": 0.061,
+      "eval_steps_per_second": 0.003,
+      "step": 48000
+    },
+    {
+      "epoch": 68.41,
+      "learning_rate": 9.478138222849083e-07,
+      "loss": 0.014,
+      "step": 48500
+    },
+    {
+      "epoch": 69.11,
+      "learning_rate": 9.266572637517632e-07,
+      "loss": 0.0143,
+      "step": 49000
+    },
+    {
+      "epoch": 69.11,
+      "eval_gen_len": 163.4387,
+      "eval_loss": 1.3576686382293701,
+      "eval_rouge1": 69.5713,
+      "eval_rouge2": 53.8362,
+      "eval_rougeL": 55.9625,
+      "eval_rougeLsum": 60.2185,
+      "eval_runtime": 6313.8347,
+      "eval_samples_per_second": 0.056,
+      "eval_steps_per_second": 0.003,
+      "step": 49000
+    },
+    {
+      "epoch": 69.82,
+      "learning_rate": 9.055007052186177e-07,
+      "loss": 0.0141,
+      "step": 49500
+    },
+    {
+      "epoch": 70.52,
+      "learning_rate": 8.843441466854725e-07,
+      "loss": 0.0139,
+      "step": 50000
+    },
+    {
+      "epoch": 70.52,
+      "eval_gen_len": 161.9259,
+      "eval_loss": 1.346762776374817,
+      "eval_rouge1": 69.5609,
+      "eval_rouge2": 53.9709,
+      "eval_rougeL": 56.0658,
+      "eval_rougeLsum": 60.0989,
+      "eval_runtime": 5992.2258,
+      "eval_samples_per_second": 0.059,
+      "eval_steps_per_second": 0.003,
+      "step": 50000
+    },
+    {
+      "epoch": 71.23,
+      "learning_rate": 8.631875881523273e-07,
+      "loss": 0.0136,
+      "step": 50500
+    },
+    {
+      "epoch": 71.93,
+      "learning_rate": 8.42031029619182e-07,
+      "loss": 0.0132,
+      "step": 51000
+    },
+    {
+      "epoch": 71.93,
+      "eval_gen_len": 161.208,
+      "eval_loss": 1.3650970458984375,
+      "eval_rouge1": 69.5418,
+      "eval_rouge2": 53.7154,
+      "eval_rougeL": 55.7361,
+      "eval_rougeLsum": 60.0613,
+      "eval_runtime": 7093.4012,
+      "eval_samples_per_second": 0.049,
+      "eval_steps_per_second": 0.003,
+      "step": 51000
+    },
+    {
+      "epoch": 72.64,
+      "learning_rate": 8.208744710860367e-07,
+      "loss": 0.0131,
+      "step": 51500
+    },
+    {
+      "epoch": 73.34,
+      "learning_rate": 7.997179125528913e-07,
+      "loss": 0.0127,
+      "step": 52000
+    },
+    {
+      "epoch": 73.34,
+      "eval_gen_len": 162.2849,
+      "eval_loss": 1.3561229705810547,
+      "eval_rouge1": 69.4318,
+      "eval_rouge2": 53.5887,
+      "eval_rougeL": 55.4159,
+      "eval_rougeLsum": 59.6162,
+      "eval_runtime": 6162.4321,
+      "eval_samples_per_second": 0.057,
+      "eval_steps_per_second": 0.003,
+      "step": 52000
+    },
+    {
+      "epoch": 74.05,
+      "learning_rate": 7.785613540197461e-07,
+      "loss": 0.0127,
+      "step": 52500
+    },
+    {
+      "epoch": 74.75,
+      "learning_rate": 7.574047954866008e-07,
+      "loss": 0.0123,
+      "step": 53000
+    },
+    {
+      "epoch": 74.75,
+      "eval_gen_len": 159.567,
+      "eval_loss": 1.3640151023864746,
+      "eval_rouge1": 69.9555,
+      "eval_rouge2": 54.4377,
+      "eval_rougeL": 56.2914,
+      "eval_rougeLsum": 60.5544,
+      "eval_runtime": 6099.51,
+      "eval_samples_per_second": 0.058,
+      "eval_steps_per_second": 0.003,
+      "step": 53000
+    },
+    {
+      "epoch": 75.46,
+      "learning_rate": 7.362482369534556e-07,
+      "loss": 0.0123,
+      "step": 53500
+    },
+    {
+      "epoch": 76.16,
+      "learning_rate": 7.150916784203103e-07,
+      "loss": 0.0119,
+      "step": 54000
+    },
+    {
+      "epoch": 76.16,
+      "eval_gen_len": 162.0228,
+      "eval_loss": 1.3737815618515015,
+      "eval_rouge1": 69.6472,
+      "eval_rouge2": 53.9313,
+      "eval_rougeL": 55.9586,
+      "eval_rougeLsum": 59.9692,
+      "eval_runtime": 6462.5491,
+      "eval_samples_per_second": 0.054,
+      "eval_steps_per_second": 0.003,
+      "step": 54000
+    },
+    {
+      "epoch": 76.87,
+      "learning_rate": 6.93935119887165e-07,
+      "loss": 0.0118,
+      "step": 54500
+    },
+    {
+      "epoch": 77.57,
+      "learning_rate": 6.727785613540198e-07,
+      "loss": 0.0117,
+      "step": 55000
+    },
+    {
+      "epoch": 77.57,
+      "eval_gen_len": 162.3789,
+      "eval_loss": 1.3787622451782227,
+      "eval_rouge1": 69.5463,
+      "eval_rouge2": 53.7206,
+      "eval_rougeL": 56.0721,
+      "eval_rougeLsum": 60.3372,
+      "eval_runtime": 6234.7587,
+      "eval_samples_per_second": 0.056,
+      "eval_steps_per_second": 0.003,
+      "step": 55000
+    },
+    {
+      "epoch": 78.28,
+      "learning_rate": 6.516220028208745e-07,
+      "loss": 0.0114,
+      "step": 55500
+    },
+    {
+      "epoch": 78.98,
+      "learning_rate": 6.304654442877292e-07,
+      "loss": 0.0114,
+      "step": 56000
+    },
+    {
+      "epoch": 78.98,
+      "eval_gen_len": 162.1083,
+      "eval_loss": 1.3712390661239624,
+      "eval_rouge1": 69.5879,
+      "eval_rouge2": 53.9682,
+      "eval_rougeL": 56.2965,
+      "eval_rougeLsum": 60.5547,
+      "eval_runtime": 6229.6909,
+      "eval_samples_per_second": 0.056,
+      "eval_steps_per_second": 0.003,
+      "step": 56000
     }
   ],
   "max_steps": 70900,
   "num_train_epochs": 100,
-  "total_flos": 7.747033211322532e+17,
+  "total_flos": 9.43193629959635e+17,
   "trial_name": null,
   "trial_params": null
 }