Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bad96fc0f157292ce44e8f62688012911d46a5651f5a65c96e85081eca7f2c6
+oid sha256:5f92faa49a56aedd454535048b1e06924d81e2c8cc05512908905b8fd385c918
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc5c617bcffc032ba0281f0f26f22d052a134e19aba1e46306681d5244891f2
+oid sha256:d8cbd021f5127c640bc8a47f0004380d5165428ac1aacc9692f2405588142f30
 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": 0.004417886777491433,
+  "epoch": 0.005663957407040299,
   "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": 12.758,
       "eval_steps_per_second": 6.38,
       "step": 39
+    },
+    {
+      "epoch": 0.0045311659256322395,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0046444450737730455,
+      "grad_norm": NaN,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.0047577242219138515,
+      "grad_norm": NaN,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.0048710033700546575,
+      "grad_norm": NaN,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.004984282518195464,
+      "grad_norm": NaN,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.005097561666336269,
+      "grad_norm": NaN,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.8006,
+      "step": 45
+    },
+    {
+      "epoch": 0.005210840814477075,
+      "grad_norm": NaN,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 0.005324119962617881,
+      "grad_norm": NaN,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.0,
+      "step": 47
+    },
+    {
+      "epoch": 0.005437399110758687,
+      "grad_norm": NaN,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 2.8967,
+      "step": 48
+    },
+    {
+      "epoch": 0.005550678258899493,
+      "grad_norm": NaN,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 3.1334,
+      "step": 49
+    },
+    {
+      "epoch": 0.005663957407040299,
+      "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": 2.18957069942784e+16,
+  "total_flos": 2.79249596448768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null