Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c8559a8d0a2ea38925aa316251725b81d8f90cd9c228f7f24576f5cfe7acefe
+oid sha256:dec7ece3544220b966057c16f4417dd47dffa6d50fd096f0ba2cf9000e385ab6
 size 124606

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4c88bcfb579b2e7508a39d1e3ecea98ce0d55cab783c43b0c3f30d514399d9
+oid sha256:099c48e4264aa5ad0ea5ad9c27da7555c348a98ab77f8ea389561ddad5f50b84
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b58ef7d8df65e566f7438a152a34c8bb3b894353cc82b46f586c77ce2cc450ea
+oid sha256:3cca11a90a8c450b0aee76178dd904f8dbff618c6e076126fc53a6731730afed
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01926318324103058,
+  "epoch": 0.025684244321374106,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 309.945,
       "eval_steps_per_second": 77.516,
       "step": 15
+    },
+    {
+      "epoch": 0.020547395457099285,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.02183160767316799,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.023115819889236697,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.024400032105305402,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.025684244321374106,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.025684244321374106,
+      "eval_loss": NaN,
+      "eval_runtime": 16.8799,
+      "eval_samples_per_second": 310.784,
+      "eval_steps_per_second": 77.726,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 52620814712832.0,
+  "total_flos": 70404459724800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null