Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e10ed7b50e949f90d2e3a407a2118cea8fb162cbcc603e0d26b6a0df7d5f8705
+oid sha256:edc490c27a3a314e633b67d93a33499f8c03a4c1ff76310155ffa7664c7fb40e
 size 140565460

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1e9e74eb9ce556fb3a56ba6bf5b59adaffe1aec162bf64b4914e0fc6e813ef
+oid sha256:90457f2aa05b0bf6c779e9c18eabfb4d5b3e6a7ed4d46f5f4d989d3f73ffe883
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002955082742316785,
+  "epoch": 0.00591016548463357,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 2.168,
       "eval_steps_per_second": 2.168,
       "step": 25
+    },
+    {
+      "epoch": 0.0035460992907801418,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.004137115839243499,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.004728132387706856,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.005319148936170213,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.00591016548463357,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.00591016548463357,
+      "eval_loss": NaN,
+      "eval_runtime": 433.4948,
+      "eval_samples_per_second": 2.168,
+      "eval_steps_per_second": 2.168,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4319317642444800.0,
+  "total_flos": 8638635284889600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null