Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:426fb6497d944b0aa8245c758156eaac4a22f1f1574289c2d572c29951f3bcfa
+oid sha256:9f233fcff699b7b9e5ab35ffd6525f02e7f5826913f502e2985f0701a68e5bf8
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9dfc0ac726fa37ee99e3992cf3283d3071da98575ab0ad545adbfc30185469f
+oid sha256:71cddd6c4ff643d7889f00bac1c58dd1b0b622d1a22609d3502d45129df9795c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1e2ed9259304616a8ecebc61c5d000777b2978635f7a705b8d7081c480ce0bde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017482517482517484,
+  "epoch": 0.03496503496503497,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 18.083,
       "eval_steps_per_second": 9.079,
       "step": 10
+    },
+    {
+      "epoch": 0.02097902097902098,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.026223776223776224,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.026223776223776224,
+      "eval_loss": NaN,
+      "eval_runtime": 13.3722,
+      "eval_samples_per_second": 18.022,
+      "eval_steps_per_second": 9.049,
+      "step": 15
+    },
+    {
+      "epoch": 0.03146853146853147,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.03496503496503497,
+      "eval_loss": NaN,
+      "eval_runtime": 13.3333,
+      "eval_samples_per_second": 18.075,
+      "eval_steps_per_second": 9.075,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -66,12 +103,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3296153189744640.0,
+  "total_flos": 6592306379489280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null