Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85b7b0e4ace7054254e82037809d822a0260defa463b8e0d0a8c09e5fbc22503
-size 1256
+oid sha256:941a42bd85e2ebebbfbf80f54f02238860c6b98d4eb9c4698a8aa137a95b18eb
+size 1183674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:787db2ff4963d8fc83bd30e719b9c580a4d6f5f8a3872b9086238b9b35f2dc6d
+oid sha256:d24a3b0e78134936662f0d4d52c5e330a1992c2511f7644b73ba6dacbcf6b6b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:219c62af0a99d0a3db4c57e4189ef3b142499e30571ad5cc800b8b67c9ce1583
+oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012861736334405145,
+  "epoch": 0.02572347266881029,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 101.631,
       "eval_steps_per_second": 101.631,
       "step": 3
+    },
+    {
+      "epoch": 0.01714898177920686,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 17.5816,
+      "step": 4
+    },
+    {
+      "epoch": 0.021436227224008574,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 16.6133,
+      "step": 5
+    },
+    {
+      "epoch": 0.02572347266881029,
+      "grad_norm": 18.79177474975586,
+      "learning_rate": 2e-05,
+      "loss": 17.427,
+      "step": 6
+    },
+    {
+      "epoch": 0.02572347266881029,
+      "eval_loss": 16.551647186279297,
+      "eval_runtime": 0.4925,
+      "eval_samples_per_second": 101.517,
+      "eval_steps_per_second": 101.517,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12981865807872.0,
+  "total_flos": 25963731615744.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null