Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c956afbc7d95e23b03d314666ec35401fd1949a5bb9faffbc17f5f0fd23cb1e5
+oid sha256:0e1d2235069b03cb7df5be256b2cc7cc3cd8f0582a419b804b290b0b34abde74
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004212932121764271,
+  "epoch": 0.0006319398182646406,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 17.222,
       "eval_steps_per_second": 8.611,
       "step": 10
+    },
+    {
+      "epoch": 0.00046342253339406975,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0005055518546117125,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 6461.936,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005476811758293551,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0005898104970469979,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0006319398182646406,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006319398182646406,
+      "eval_loss": NaN,
+      "eval_runtime": 3326.0425,
+      "eval_samples_per_second": 12.02,
+      "eval_steps_per_second": 6.01,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7650345064857600.0,
+  "total_flos": 1.156552165687296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null