Training in progress, step 140, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d47f50d75e32624acd21703332c797184b665fb4d2b10847a7d7de1432abb3a1
+oid sha256:c5deddc4532a7e43a9d0f9fbe82070649a4eb6e36c4c10045bb971c255475d45
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1345b0a7769c8848417baabda9535c454ba0aef0691913ff0f8c0d83f03bfc3
+oid sha256:930c0e2ebbffa6eaa81c1c13cb56bae07035671452615a27785b151dda07ab8f
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:443907af357cccf92496cdd4e04b21f17558d4acf38fddc732c70cd7db47e70d
+oid sha256:bfad5b1db434a4570e357f1971d87bf80fdc19c2e91af8a74bce9bbf251a95cc
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc32de04bd8951ded22e38a3a317dcc3e3d6e420820aadb0c1fc7777161631b4
+oid sha256:c40d5e94eed411043d006187ef3d57f655338dfd7cfaaf34e38342dbbae53acc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6,
+  "epoch": 0.7,
   "eval_steps": 20,
-  "global_step": 120,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,43 @@
       "eval_samples_per_second": 370.215,
       "eval_steps_per_second": 61.826,
       "step": 120
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.24475905299186707,
+      "learning_rate": 1.3819660112501052e-06,
+      "loss": 22.0078369140625,
+      "step": 125
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.2379191815853119,
+      "learning_rate": 1.227001661415096e-06,
+      "loss": 22.009359741210936,
+      "step": 130
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 0.26111480593681335,
+      "learning_rate": 1.0773176740426246e-06,
+      "loss": 21.976290893554687,
+      "step": 135
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.28270959854125977,
+      "learning_rate": 9.339365425440129e-07,
+      "loss": 22.019345092773438,
+      "step": 140
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.009251594543457,
+      "eval_runtime": 2.5123,
+      "eval_samples_per_second": 398.045,
+      "eval_steps_per_second": 66.473,
+      "step": 140
     }
   ],
   "logging_steps": 5,