Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c5aa757d5d7608315b96735f67eb6ae54ed87b79939fbb3ae3d10d7d91fcad
+oid sha256:0d3e81090b776aed5efee86a39b2998a2278cb8f4546380cb2d9c1eb1455b22f
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d74a808c4a40c48c0d5954b19a73387ba5c6e6295178153e440ef176de4cac8
+oid sha256:7fa081e379c7b904fec4d734e680d6c3a44b1a4fbc8ebe714244b7ad46b331c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16632016632016633,
+  "epoch": 0.2494802494802495,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 20.424,
       "eval_steps_per_second": 10.412,
       "step": 20
+    },
+    {
+      "epoch": 0.17463617463617465,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.1995841995841996,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.2079002079002079,
+      "eval_loss": NaN,
+      "eval_runtime": 2.5125,
+      "eval_samples_per_second": 20.298,
+      "eval_steps_per_second": 10.348,
+      "step": 25
+    },
+    {
+      "epoch": 0.22453222453222454,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.2494802494802495,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.2494802494802495,
+      "eval_loss": NaN,
+      "eval_runtime": 2.4945,
+      "eval_samples_per_second": 20.445,
+      "eval_steps_per_second": 10.423,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2757139491717120.0,
+  "total_flos": 4135709237575680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null