Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ff395e01be1283b5654d0977f3ca1a20048f7fd14cabab8ee071fa3a110ea1
+oid sha256:722c420d32d7d08d6ba5dd7d7c2dc0f7434d3f49b6ab1ff2dc180501bb5d5e58
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b33cabe83f82b1eec4ea7b39b0e415dd3ea430db3dc2fc816910f07af32abe8a
+oid sha256:d0e3316d2cf3807eae9dbf9a639db4bf3b211c11598d00a94e92fb77034b1be1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005262465465070386,
+  "epoch": 0.0010524930930140772,
   "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": 6.612,
       "eval_steps_per_second": 3.307,
       "step": 3
+    },
+    {
+      "epoch": 0.0007016620620093847,
+      "grad_norm": Infinity,
+      "learning_rate": 8e-05,
+      "loss": 0.7553,
+      "step": 4
+    },
+    {
+      "epoch": 0.0008770775775117309,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0001,
+      "loss": 0.6949,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010524930930140772,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00012,
+      "loss": 0.861,
+      "step": 6
+    },
+    {
+      "epoch": 0.0010524930930140772,
+      "eval_loss": 0.8225405812263489,
+      "eval_runtime": 365.755,
+      "eval_samples_per_second": 6.565,
+      "eval_steps_per_second": 3.284,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 617621263220736.0,
+  "total_flos": 1235242526441472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null