Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d557c312fe00e0d62f1979e5aa95c8bdbda0380ccfbd79649c263cb857e05d7
+oid sha256:f76ea9cb9b23ea4c6930993c6b9b7a434aea7d477199d4cd5372d96748b1fedd
 size 250819170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:708042764592e3d5126d98e7a05d9a0a0ceac8fe30eb5f19c4d5479057b7c5e6
+oid sha256:4ef826b3e7e98ec569b4f5a5ed433dad8b290620b815576e63219b2257f79ffe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09836065573770492,
+  "epoch": 0.19672131147540983,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 4.035,
       "eval_steps_per_second": 2.049,
       "step": 15
+    },
+    {
+      "epoch": 0.1180327868852459,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.13114754098360656,
+      "eval_loss": NaN,
+      "eval_runtime": 16.1224,
+      "eval_samples_per_second": 4.032,
+      "eval_steps_per_second": 2.047,
+      "step": 20
+    },
+    {
+      "epoch": 0.1377049180327869,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.15737704918032788,
+      "grad_norm": NaN,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "eval_loss": NaN,
+      "eval_runtime": 16.1227,
+      "eval_samples_per_second": 4.032,
+      "eval_steps_per_second": 2.047,
+      "step": 25
+    },
+    {
+      "epoch": 0.17704918032786884,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.19672131147540983,
+      "eval_loss": NaN,
+      "eval_runtime": 16.133,
+      "eval_samples_per_second": 4.029,
+      "eval_steps_per_second": 2.045,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.9039745212416e+16,
+  "total_flos": 3.8079490424832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null