Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0b2df195e6db9bbff126263b74251104b6c81259c771b6f46211cb2c7be3d8
+oid sha256:fb73a104abfb9f0e6d7f6278dab4abc13c6828e3310ac6d19f07929f540a9ca0
 size 551070514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0aaa8092d42f737d0d24b5de179d4c5bd61d260ed091186851f7bc6acf50199
+oid sha256:55cba885e7b13f7674bf6187ac6d75d861bf8d427fda7fd12449789925131f2d
 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": 0.5633802816901409,
+  "epoch": 0.8450704225352113,
   "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": 5.083,
       "eval_steps_per_second": 1.356,
       "step": 20
+    },
+    {
+      "epoch": 0.5915492957746479,
+      "grad_norm": NaN,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.6197183098591549,
+      "grad_norm": NaN,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.647887323943662,
+      "grad_norm": NaN,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": NaN,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.676056338028169,
+      "eval_loss": NaN,
+      "eval_runtime": 2.9454,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 1.358,
+      "step": 24
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.7323943661971831,
+      "grad_norm": NaN,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.7605633802816901,
+      "grad_norm": NaN,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.7887323943661971,
+      "grad_norm": NaN,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.7887323943661971,
+      "eval_loss": NaN,
+      "eval_runtime": 2.9601,
+      "eval_samples_per_second": 5.067,
+      "eval_steps_per_second": 1.351,
+      "step": 28
+    },
+    {
+      "epoch": 0.8169014084507042,
+      "grad_norm": NaN,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.8450704225352113,
+      "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": 1.382181645582336e+16,
+  "total_flos": 2.073272468373504e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null