End of training

all_results.json

@@ -1,8 +1,18 @@
 {
     "epoch": 3.0,
-    "train_loss": 4.371463769932677,
-    "train_runtime": 2130.0724,
+    "eval_gen_len": 42.78774617067834,
+    "eval_loss": 2.2129509449005127,
+    "eval_rouge1": 0.0,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 0.0,
+    "eval_rougeLsum": 0.0,
+    "eval_runtime": 222.1589,
+    "eval_samples": 457,
+    "eval_samples_per_second": 2.057,
+    "eval_steps_per_second": 1.031,
+    "train_loss": 3.0209487093938305,
+    "train_runtime": 15633.4435,
     "train_samples": 3567,
-    "train_samples_per_second": 5.024,
-    "train_steps_per_second": 1.256
+    "train_samples_per_second": 0.684,
+    "train_steps_per_second": 0.342
 }

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_gen_len": 42.78774617067834,
+    "eval_loss": 2.2129509449005127,
+    "eval_rouge1": 0.0,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 0.0,
+    "eval_rougeLsum": 0.0,
+    "eval_runtime": 222.1589,
+    "eval_samples": 457,
+    "eval_samples_per_second": 2.057,
+    "eval_steps_per_second": 1.031
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 3.0,
-    "train_loss": 4.371463769932677,
-    "train_runtime": 2130.0724,
+    "train_loss": 3.0209487093938305,
+    "train_runtime": 15633.4435,
     "train_samples": 3567,
-    "train_samples_per_second": 5.024,
-    "train_steps_per_second": 1.256
+    "train_samples_per_second": 0.684,
+    "train_steps_per_second": 0.342
 }

trainer_state.json

@@ -2,54 +2,84 @@
   "best_metric": null,
   "best_model_checkpoint": null,
   "epoch": 3.0,
-  "global_step": 2676,
+  "global_step": 5352,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.53288490284006e-05,
+      "loss": 4.6706,
+      "step": 500
+    },
     {
       "epoch": 0.56,
       "learning_rate": 4.06576980568012e-05,
-      "loss": 6.9052,
-      "step": 500
+      "loss": 3.2966,
+      "step": 1000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.598654708520179e-05,
+      "loss": 3.1131,
+      "step": 1500
     },
     {
       "epoch": 1.12,
       "learning_rate": 3.131539611360239e-05,
-      "loss": 4.058,
-      "step": 1000
+      "loss": 3.023,
+      "step": 2000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.6644245142002988e-05,
+      "loss": 2.8461,
+      "step": 2500
     },
     {
       "epoch": 1.68,
       "learning_rate": 2.197309417040359e-05,
-      "loss": 3.7927,
-      "step": 1500
+      "loss": 2.793,
+      "step": 3000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.7301943198804185e-05,
+      "loss": 2.7901,
+      "step": 3500
     },
     {
       "epoch": 2.24,
       "learning_rate": 1.2630792227204785e-05,
-      "loss": 3.7283,
-      "step": 2000
+      "loss": 2.6794,
+      "step": 4000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.959641255605381e-06,
+      "loss": 2.6457,
+      "step": 4500
     },
     {
       "epoch": 2.8,
       "learning_rate": 3.2884902840059795e-06,
-      "loss": 3.6313,
-      "step": 2500
+      "loss": 2.6186,
+      "step": 5000
     },
     {
       "epoch": 3.0,
-      "step": 2676,
-      "total_flos": 5808282307461120.0,
-      "train_loss": 4.371463769932677,
-      "train_runtime": 2130.0724,
-      "train_samples_per_second": 5.024,
-      "train_steps_per_second": 1.256
+      "step": 5352,
+      "total_flos": 1.0118640236829696e+16,
+      "train_loss": 3.0209487093938305,
+      "train_runtime": 15633.4435,
+      "train_samples_per_second": 0.684,
+      "train_steps_per_second": 0.342
     }
   ],
-  "max_steps": 2676,
+  "max_steps": 5352,
   "num_train_epochs": 3,
-  "total_flos": 5808282307461120.0,
+  "total_flos": 1.0118640236829696e+16,
   "trial_name": null,
   "trial_params": null
 }