Training in progress, step 500

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 2.4250597953796387,
+    "train_runtime": 3.5143,
+    "train_samples": 1854797,
+    "train_samples_per_second": 18.212,
+    "train_steps_per_second": 0.285
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925f012d0fafc65a63647ff52388709a2e4d2f2f363714ede311748e453234b3
+oid sha256:355cfc139dcedf713fecb995297f7e23eda985eed91c164de1cc246145aa043c
 size 4114319645

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.0,
+    "train_loss": 2.4250597953796387,
+    "train_runtime": 3.5143,
+    "train_samples": 1854797,
+    "train_samples_per_second": 18.212,
+    "train_steps_per_second": 0.285
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.450506793185249e-05,
+  "global_step": 1,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "step": 1,
+      "total_flos": 178669297336320.0,
+      "train_loss": 2.4250597953796387,
+      "train_runtime": 3.5143,
+      "train_samples_per_second": 18.212,
+      "train_steps_per_second": 0.285
+    }
+  ],
+  "max_steps": 1,
+  "num_train_epochs": 1,
+  "total_flos": 178669297336320.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f76a2a33e4e6e3f4fe6e4cf4f7209db5756986afe61992f8b12663e645a7f9
+oid sha256:cc16ed911933a1a9f1fb9b5c9ed42e306ece83ad916da5786f318d4db6e2c524
 size 3707