Training in progress, step 500

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 8.786969866071429,
+    "train_runtime": 85.7227,
+    "train_samples": 2000,
+    "train_samples_per_second": 69.993,
+    "train_steps_per_second": 0.735
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:531d9c9479dbd7b8bd016cda03e9d07b44f1bbe0d8fc75bc40325b15272b9b95
+oid sha256:ef301b0e33c2572154c8921e9369e7e61e86825f2271b6192dc1248768825366
 size 652213854

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 8.786969866071429,
+    "train_runtime": 85.7227,
+    "train_samples": 2000,
+    "train_samples_per_second": 69.993,
+    "train_steps_per_second": 0.735
+}

trainer_state.json

@@ -0,0 +1,28 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 63,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 63,
+      "total_flos": 1156011922554880.0,
+      "train_loss": 8.786969866071429,
+      "train_runtime": 85.7227,
+      "train_samples_per_second": 69.993,
+      "train_steps_per_second": 0.735
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 63,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "total_flos": 1156011922554880.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90e4b79c62470aaf0062a910558c12022ac0832f5364886e4d15058c0eabc0d7
+oid sha256:4ac844c30deffb32b1d82d419281cb63dad404ebf9718a0ab249f5258126c011
 size 4536