Training in progress, step 82, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8487ce7bdbc23b357aa541d0b6f6552ab3cd137d9189f6805444f0a71649243
+oid sha256:39b94c672a97c9015e8295fd7a26b83b30f58fc04dbbdb99d68bcad055f93947
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3595634126481ea254b652ccb287819db6abe86cb9d82adc40da7f64a80c4f6e
+oid sha256:41f026569d2524bee91b5ef6c45e9ccac7bd6699e35f824786c4e9bc2cd3b716
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9485cd7ca685639d72a742a35da6508ee70e4def8667e09a65fece70b6b717f
+oid sha256:1453247989fe4f40cb58011506f6735ba25507deafeaf2cc886ff35d4634f2b0
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:725ee499aaa0bc04b490ac3af0c734c514c976dd8cd2f204b00fdb43d2a90bf8
+oid sha256:d20550e97739760e033bfa2dbeb5dbd23fb1ea480b478b5de311b00b3043e221
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.838709677419355,
+  "epoch": 3.0230414746543777,
   "eval_steps": 7,
-  "global_step": 77,
+  "global_step": 82,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -642,6 +642,41 @@
       "eval_samples_per_second": 13.773,
       "eval_steps_per_second": 1.797,
       "step": 77
+    },
+    {
+      "epoch": 2.8755760368663594,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015600000000000002,
+      "loss": 1.4261,
+      "step": 78
+    },
+    {
+      "epoch": 2.912442396313364,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00015800000000000002,
+      "loss": 1.4717,
+      "step": 79
+    },
+    {
+      "epoch": 2.9493087557603688,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00016,
+      "loss": 1.4148,
+      "step": 80
+    },
+    {
+      "epoch": 2.986175115207373,
+      "grad_norm": Infinity,
+      "learning_rate": 0.000162,
+      "loss": 1.4234,
+      "step": 81
+    },
+    {
+      "epoch": 3.0230414746543777,
+      "grad_norm": Infinity,
+      "learning_rate": 0.000164,
+      "loss": 2.5737,
+      "step": 82
     }
   ],
   "logging_steps": 1,
@@ -656,12 +691,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.34091163573289e+16,
+  "total_flos": 6.752659144546714e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null