Training in progress, step 40, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1eb40a55caeef9711919f7740477d0f2c47cc67ce7a09b1a484527ad8340441
+oid sha256:68430ed90582ec36ba6c0f053827de6305df7b0426b8c522ee8f1f603f0a87d6
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771a18c451612f8e645481bf984c885a29aaaee94750217cb000c1dd7a306e19
+oid sha256:0871ab613a3719279157cedf4662a8676a4c76739dabf3cde23efb35114018aa
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bd3d1a2f58ae7c5971df94ab38f5e952b7947bc754ebd01bb0045964a824d2
+oid sha256:e9d1ea809ba32b7efd678ae04203f4d557f85f71b36f396a16e0baf7241d69c8
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
+oid sha256:889f6fc92910dc1617d7e2b8e49ec9358ef58d2162623ab1d55db477fded32fc
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
+  "epoch": 0.2,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,43 @@
       "eval_samples_per_second": 180.754,
       "eval_steps_per_second": 30.186,
       "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.20624566078186035,
+      "learning_rate": 3.9466531944960116e-06,
+      "loss": 21.974824523925783,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.22814048826694489,
+      "learning_rate": 3.902113032590307e-06,
+      "loss": 21.986297607421875,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.2210160493850708,
+      "learning_rate": 3.844579509954769e-06,
+      "loss": 21.97326202392578,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2189972996711731,
+      "learning_rate": 3.7744456388872234e-06,
+      "loss": 21.941111755371093,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 7.827788649706458e-06,
+      "eval_loss": 10.984576225280762,
+      "eval_runtime": 5.3798,
+      "eval_samples_per_second": 185.881,
+      "eval_steps_per_second": 31.042,
+      "step": 40
     }
   ],
   "logging_steps": 5,