Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:722c420d32d7d08d6ba5dd7d7c2dc0f7434d3f49b6ab1ff2dc180501bb5d5e58
+oid sha256:74835f4ffd515007378bf0bfa20aad7163c7b72ed71830c340297d56bcef5f54
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e3316d2cf3807eae9dbf9a639db4bf3b211c11598d00a94e92fb77034b1be1
+oid sha256:a23d8c54930bcfa400a42faf2dd8310c9fa2fc3255471da30515ca920d46e8eb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010524930930140772,
+  "epoch": 0.0015787396395211155,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 6.565,
       "eval_steps_per_second": 3.284,
       "step": 6
+    },
+    {
+      "epoch": 0.0012279086085164232,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00014,
+      "loss": 0.8151,
+      "step": 7
+    },
+    {
+      "epoch": 0.0014033241240187695,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016,
+      "loss": 0.8015,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015787396395211155,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018,
+      "loss": 0.962,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015787396395211155,
+      "eval_loss": 0.8225405812263489,
+      "eval_runtime": 365.0236,
+      "eval_samples_per_second": 6.578,
+      "eval_steps_per_second": 3.29,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1235242526441472.0,
+  "total_flos": 1852863789662208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null