Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f53255e0deaeeffbf1ae729c9448bbfb1b39a2492498059eff321c821c9ccb
+oid sha256:40016990bc93e4b17c5b85b508be894036599d653754126c1c4963a1ba5a1d13
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457548b77ed5d7703d69eacdc9aca9fe710c41943f0b7a77991d95d5848083b0
+oid sha256:8e88192bf334b9c7faf9c721400914bbaf7bfe8e40a198b1bf1017b765e863a3
 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": 0.005112474437627812,
+  "epoch": 0.007668711656441718,
   "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": 9.46,
       "eval_steps_per_second": 2.365,
       "step": 20
+    },
+    {
+      "epoch": 0.005368098159509203,
+      "grad_norm": NaN,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.005623721881390593,
+      "grad_norm": NaN,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 0.0,
+      "step": 22
+    },
+    {
+      "epoch": 0.005879345603271984,
+      "grad_norm": NaN,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 0.0,
+      "step": 23
+    },
+    {
+      "epoch": 0.006134969325153374,
+      "grad_norm": NaN,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.006134969325153374,
+      "eval_loss": NaN,
+      "eval_runtime": 174.2467,
+      "eval_samples_per_second": 9.458,
+      "eval_steps_per_second": 2.364,
+      "step": 24
+    },
+    {
+      "epoch": 0.006390593047034765,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.0066462167689161555,
+      "grad_norm": NaN,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.006901840490797546,
+      "grad_norm": NaN,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.007157464212678937,
+      "grad_norm": NaN,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.007157464212678937,
+      "eval_loss": NaN,
+      "eval_runtime": 174.0326,
+      "eval_samples_per_second": 9.469,
+      "eval_steps_per_second": 2.367,
+      "step": 28
+    },
+    {
+      "epoch": 0.007413087934560327,
+      "grad_norm": NaN,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.007668711656441718,
+      "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": 7031423835832320.0,
+  "total_flos": 1.054713575374848e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null