Training in progress, step 250, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318087727ede6105f9381fb06535ef84c1ea247253646bcb94d6b91eedef458b
+oid sha256:b975330002a6ce5e014ef8138b5ba17aaae01288654ac5b87e0ddbe0f9e40447
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f287d0759907f8a79f97d912bf8046eaee71d2901c8b408bd049cdf70c58afe4
+oid sha256:de4a584b1cd6d33551e6903e2cd0e41d9766b7b7073f938b270f9462d2373963
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003305785123966942,
+  "epoch": 0.0043727316454589184,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 18.717,
       "eval_steps_per_second": 9.359,
       "step": 189
+    },
+    {
+      "epoch": 0.003323276050548778,
+      "grad_norm": NaN,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 13.2545,
+      "step": 190
+    },
+    {
+      "epoch": 0.0034981853163671348,
+      "grad_norm": NaN,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.7063,
+      "step": 200
+    },
+    {
+      "epoch": 0.0036730945821854912,
+      "grad_norm": NaN,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 1.4518,
+      "step": 210
+    },
+    {
+      "epoch": 0.003848003848003848,
+      "grad_norm": NaN,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.4159,
+      "step": 220
+    },
+    {
+      "epoch": 0.004022913113822205,
+      "grad_norm": NaN,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.0041978223796405615,
+      "grad_norm": NaN,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 3.6874,
+      "step": 240
+    },
+    {
+      "epoch": 0.0043727316454589184,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 1.5111,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.2212710447906816e+16,
+  "total_flos": 4.254011420678554e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null