Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccaee9708f6919567a10a4b2c9d36dae410e47bad47fbdd7a3c8cef5912777a7
+oid sha256:a096f930017b2cc6ca9f4453405747a76258ade452c58dcd9be9992e9b0e8145
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eadd1f329f3da3a83eddee2e4874e3286a0dc412e1a9b5468b763ecd9b19700f
+oid sha256:fa0c8a18b09f7db096523b463944ed56af3c0386a1cd89d1d5fddb2ea98e9088
 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": 0.14484679665738162,
+  "epoch": 0.18570102135561745,
   "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": 18.308,
       "eval_steps_per_second": 9.154,
       "step": 39
+    },
+    {
+      "epoch": 0.14856081708449395,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.1522748375116063,
+      "grad_norm": NaN,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.15598885793871867,
+      "grad_norm": NaN,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.15970287836583102,
+      "grad_norm": NaN,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.16341689879294335,
+      "grad_norm": NaN,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.1671309192200557,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.17084493964716807,
+      "grad_norm": NaN,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.1745589600742804,
+      "grad_norm": NaN,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.17827298050139276,
+      "grad_norm": NaN,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.18198700092850512,
+      "grad_norm": NaN,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.18570102135561745,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "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": 1.2663400131723264e+16,
+  "total_flos": 1.6246613030731776e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null