Training in progress, step 15, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b9a75f32be63387c28153328a1b0691f9e49ee128269c6ff2216dcfebb420ad
+oid sha256:03a0a3336547a47bdfc6a8dd5e2e5239f4d20da2eca8e885ef3d03c4fe74b91a
 size 41119636

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": 0.0015087792090224996,
+  "epoch": 0.0022631688135337493,
   "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": 31.248,
       "eval_steps_per_second": 15.625,
       "step": 10
+    },
+    {
+      "epoch": 0.0016596571299247497,
+      "grad_norm": NaN,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.0,
+      "step": 11
+    },
+    {
+      "epoch": 0.0018105350508269996,
+      "grad_norm": NaN,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 750.933,
+      "step": 12
+    },
+    {
+      "epoch": 0.0019614129717292496,
+      "grad_norm": NaN,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.0021122908926314997,
+      "grad_norm": NaN,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.0022631688135337493,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0022631688135337493,
+      "eval_loss": NaN,
+      "eval_runtime": 357.1352,
+      "eval_samples_per_second": 31.257,
+      "eval_steps_per_second": 15.63,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9161629551820800.0,
+  "total_flos": 1.3762803504513024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null