Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f282d025595bdaadf9e2e7068b5582a3e89d1e1f2058044c1205c1c495bcaf5
+oid sha256:0928c9182eeda93b4ea93e4953fdb9afcfbc625d997f09568bc66d790a47a7c6
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c96b5e6811e264a82636893b20993c7fd3b70e662b81fe25e9b6d360eb6062
+oid sha256:400a6d6a18fc16b638aeb824699e8e27e212104bd39097badfed36b500f6402a
 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": 4.1609886509034544e-05,
+  "epoch": 8.321977301806909e-05,
   "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": 52.529,
       "eval_steps_per_second": 26.264,
       "step": 3
+    },
+    {
+      "epoch": 5.547984867871273e-05,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 6.934981084839092e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 8.321977301806909e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 8.321977301806909e-05,
+      "eval_loss": NaN,
+      "eval_runtime": 580.1344,
+      "eval_samples_per_second": 52.329,
+      "eval_steps_per_second": 26.165,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 94916176773120.0,
+  "total_flos": 189832353546240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null