Training in progress, step 126, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e561b6cb34688e8d2653791601540f42b23bc987a1eb9d356c181b83bbc701d1
+oid sha256:bd18e1c349490c48312847f30ef245585b393eadf9cb42b94e468143181e4ec5
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a40889db8a064f871f3a5b556a6df0a8bdf5611386f27d043e93ad02429fb8a
+oid sha256:cb5a558f1d728dec8709993a98052593efab5b7c64f196591332a1eca22512e2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c99427ab0e3f179e8260c56d2a524955cd643e000ed1c4e3ac111dee56d825
+oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011019283746556473,
+  "epoch": 0.0022038567493112946,
   "eval_steps": 63,
-  "global_step": 63,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,56 @@
       "eval_samples_per_second": 18.739,
       "eval_steps_per_second": 9.37,
       "step": 63
+    },
+    {
+      "epoch": 0.001224364860728497,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 0.9676,
+      "step": 70
+    },
+    {
+      "epoch": 0.0013992741265468538,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.0015741833923652105,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 0.9896,
+      "step": 90
+    },
+    {
+      "epoch": 0.0017490926581835674,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.001924001924001924,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.0020989111898202808,
+      "grad_norm": NaN,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 2.0429,
+      "step": 120
+    },
+    {
+      "epoch": 0.0022038567493112946,
+      "eval_loss": NaN,
+      "eval_runtime": 644.4978,
+      "eval_samples_per_second": 18.677,
+      "eval_steps_per_second": 9.339,
+      "step": 126
     }
   ],
   "logging_steps": 10,
@@ -84,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.076686774861824e+16,
+  "total_flos": 2.1621628295184384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null