Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63151eef78871d4650608ef549037cf99b0e16790214bfe48d55536edb4fe03c
+oid sha256:e9c40b44501e933ff78ff3a857ce11f492de4aebca8bbed2f4def7facf1a58b0
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2253e795dc05a61424b14049017b49e4e4f5027f1fae5ede26d6f5e6a52f637e
+oid sha256:0882fa6a840ee8da212b0baa3109ca1911ebdfb2219b504d862e7fd852ba9a5f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005286809410520751,
+  "epoch": 0.007930214115781126,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 7.208,
       "eval_steps_per_second": 1.805,
       "step": 20
+    },
+    {
+      "epoch": 0.0055511498810467885,
+      "grad_norm": NaN,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.005815490351572826,
+      "grad_norm": NaN,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.006079830822098863,
+      "grad_norm": NaN,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.006344171292624901,
+      "grad_norm": NaN,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.006344171292624901,
+      "eval_loss": NaN,
+      "eval_runtime": 220.9742,
+      "eval_samples_per_second": 7.209,
+      "eval_steps_per_second": 1.806,
+      "step": 24
+    },
+    {
+      "epoch": 0.006608511763150938,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.006872852233676976,
+      "grad_norm": NaN,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.007137192704203013,
+      "grad_norm": NaN,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.007401533174729051,
+      "grad_norm": NaN,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.007401533174729051,
+      "eval_loss": NaN,
+      "eval_runtime": 221.0002,
+      "eval_samples_per_second": 7.208,
+      "eval_steps_per_second": 1.805,
+      "step": 28
+    },
+    {
+      "epoch": 0.007665873645255088,
+      "grad_norm": NaN,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.007930214115781126,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8985050276167680.0,
+  "total_flos": 1.3232528588537856e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null