Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cd10fbe188d520d3253ad467a88980220c1aa7f149ddb7f19b142cba6ebc464
+oid sha256:9464a83d744bb16ab356dc5a575efb989f0629cccfb5f0fbb4e7755291759440
 size 61226900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfbe7b67e49ee107f79ef13ad8ba4dc7d227f75f7856d83652c17ed51a3c2a10
+oid sha256:afc96819c810a0b10fbf28ef176daa0e9d10caff3ef1bde0f8923e657df640be
 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": 0.0003827507017096198,
+  "epoch": 0.0007655014034192396,
   "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": 2.65,
       "eval_steps_per_second": 2.65,
       "step": 3
+    },
+    {
+      "epoch": 0.0005103342689461597,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.0006379178361826997,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007655014034192396,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0007655014034192396,
+      "eval_loss": NaN,
+      "eval_runtime": 311.5865,
+      "eval_samples_per_second": 2.651,
+      "eval_steps_per_second": 2.651,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 553323237212160.0,
+  "total_flos": 1106646474424320.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null