step 780

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2c13d1f6aca9d6c804c0bc9298ed055733e600a46b1bdca00020324eba63c6a
+oid sha256:015647113cba9eeeeb86480d56b6cad9c3aa139fa1fcc711038a96c643d2f922
 size 24673403925

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0411962160512664,
-  "global_step": 540,
+  "epoch": 0.0595056454073848,
+  "global_step": 780,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -228,11 +228,107 @@
       "eval_samples_per_second": 3.268,
       "eval_steps_per_second": 0.418,
       "step": 540
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.2439846992492676,
+      "eval_runtime": 95.3723,
+      "eval_samples_per_second": 3.282,
+      "eval_steps_per_second": 0.419,
+      "step": 560
+    },
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.22643780708313,
+      "eval_runtime": 95.2142,
+      "eval_samples_per_second": 3.287,
+      "eval_steps_per_second": 0.42,
+      "step": 580
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.2366464138031006,
+      "eval_runtime": 94.7461,
+      "eval_samples_per_second": 3.304,
+      "eval_steps_per_second": 0.422,
+      "step": 600
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.2283596992492676,
+      "eval_runtime": 94.7042,
+      "eval_samples_per_second": 3.305,
+      "eval_steps_per_second": 0.422,
+      "step": 620
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.228659152984619,
+      "eval_runtime": 95.4845,
+      "eval_samples_per_second": 3.278,
+      "eval_steps_per_second": 0.419,
+      "step": 640
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.2173023223876953,
+      "eval_runtime": 96.1967,
+      "eval_samples_per_second": 3.254,
+      "eval_steps_per_second": 0.416,
+      "step": 660
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.209789276123047,
+      "eval_runtime": 95.9623,
+      "eval_samples_per_second": 3.262,
+      "eval_steps_per_second": 0.417,
+      "step": 680
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.2206969261169434,
+      "eval_runtime": 96.1394,
+      "eval_samples_per_second": 3.256,
+      "eval_steps_per_second": 0.416,
+      "step": 700
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 2.2181010246276855,
+      "eval_runtime": 95.7693,
+      "eval_samples_per_second": 3.268,
+      "eval_steps_per_second": 0.418,
+      "step": 720
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 2.202101707458496,
+      "eval_runtime": 94.766,
+      "eval_samples_per_second": 3.303,
+      "eval_steps_per_second": 0.422,
+      "step": 740
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 2.196211099624634,
+      "eval_runtime": 96.1177,
+      "eval_samples_per_second": 3.256,
+      "eval_steps_per_second": 0.416,
+      "step": 760
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 2.19002103805542,
+      "eval_runtime": 95.6171,
+      "eval_samples_per_second": 3.273,
+      "eval_steps_per_second": 0.418,
+      "step": 780
     }
   ],
   "max_steps": 13108,
   "num_train_epochs": 1,
-  "total_flos": 7509129560064.0,
+  "total_flos": 11051923931136.0,
   "trial_name": null,
   "trial_params": null
 }