Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23fc48f21c8e92007b0f2ec4049c0456b87a1df4cd2f037e359a4bf001f66ce3
+oid sha256:dde894835fce6502a23e82693d922bd62a79711c3c1d704e63a0e0c58d8e3774
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333565377594417bcedbe6430a1bf7422516d8b8d92766359f985a98202d5ac6
+oid sha256:f6881cc8c639c85e7eb1ddcce15f3c7a22cb312f7647fd34969b583a27484e92
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04498269896193772,
+  "epoch": 0.05767012687427912,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 21.478,
       "eval_steps_per_second": 10.768,
       "step": 39
+    },
+    {
+      "epoch": 0.0461361014994233,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.4276,
+      "step": 40
+    },
+    {
+      "epoch": 0.04728950403690888,
+      "grad_norm": NaN,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.04844290657439446,
+      "grad_norm": NaN,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.049596309111880045,
+      "grad_norm": NaN,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.05074971164936563,
+      "grad_norm": NaN,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.05190311418685121,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0530565167243368,
+      "grad_norm": NaN,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.05420991926182238,
+      "grad_norm": NaN,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.05536332179930796,
+      "grad_norm": NaN,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.05651672433679354,
+      "grad_norm": NaN,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.05767012687427912,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.4417,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0912429064060928e+16,
+  "total_flos": 1.4056688285908992e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null