10k

all_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "train_loss": 1.7669375141701935,
-    "train_runtime": 10839.0571,
-    "train_samples": 9919,
-    "train_samples_per_second": 1.83,
-    "train_steps_per_second": 0.153
+    "epoch": 1.0,
+    "train_loss": 1.6453349383580202,
+    "train_runtime": 6270.6718,
+    "train_samples": 10370,
+    "train_samples_per_second": 1.654,
+    "train_steps_per_second": 0.138
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f969327ada3bd8dbee21381bf85e5eab0012f56c8b38e3b91b8598b80c158c67
+oid sha256:f0d6c3df1021e5d2805eec094101c9756aab92a2c23d7ed5a670d9f95d11a232
 size 1109883945

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 2.0,
-    "train_loss": 1.7669375141701935,
-    "train_runtime": 10839.0571,
-    "train_samples": 9919,
-    "train_samples_per_second": 1.83,
-    "train_steps_per_second": 0.153
+    "epoch": 1.0,
+    "train_loss": 1.6453349383580202,
+    "train_runtime": 6270.6718,
+    "train_samples": 10370,
+    "train_samples_per_second": 1.654,
+    "train_steps_per_second": 0.138
 }

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5780346820809249,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 865,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -13,13 +13,22 @@
       "learning_rate": 1.2658959537572255e-05,
       "loss": 1.7414,
       "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "step": 865,
+      "total_flos": 2032235525514240.0,
+      "train_loss": 1.6453349383580202,
+      "train_runtime": 6270.6718,
+      "train_samples_per_second": 1.654,
+      "train_steps_per_second": 0.138
     }
   ],
   "logging_steps": 500,
   "max_steps": 865,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1175835405312000.0,
+  "total_flos": 2032235525514240.0,
   "trial_name": null,
   "trial_params": null
 }