Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a74deab4d5ba77c9a4f7e81a067b1f2a8d7194079d99dac030fe35e4b6a40176
+oid sha256:7983cdd29a5b29972d6c4b8862dea15420f3651dc553f3bea94942f74dd801cf
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab8082debf1af3df9983d50166b3db7c9650aa6ee53e9bef56f61c588805d2d
+oid sha256:92389181d276f4f7e82ff00efe6f9cf89365eb036fb84264bc130ea1388a86b0
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9deec2bbc6049590c0611b7f75fd56a9cf2bc765b789590cd118585901f6530
+oid sha256:d17c78731e93c053cc5bdd46a999e26416061fc6f401c1eac6682002c6f7cf23
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2eb03e04e9ec3d534ee7aa67476af96452e64bad29591c419a0c652481ee2b
+oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,123 +2,49 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.1,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.2264673411846161,
+      "grad_norm": 0.24584950506687164,
       "learning_rate": 1.6e-06,
-      "loss": 21.980099487304688,
+      "loss": 22.009127807617187,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.22343619167804718,
+      "grad_norm": 0.2564426362514496,
       "learning_rate": 3.6e-06,
-      "loss": 21.971717834472656,
+      "loss": 22.05052947998047,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.20869942009449005,
+      "grad_norm": 0.2390100657939911,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 21.96947479248047,
+      "loss": 22.014682006835937,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.2140372395515442,
+      "grad_norm": 0.2513236105442047,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 21.95387420654297,
+      "loss": 22.021099853515626,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 7.827788649706458e-06,
-      "eval_loss": 10.985608100891113,
-      "eval_runtime": 5.5324,
-      "eval_samples_per_second": 180.754,
-      "eval_steps_per_second": 30.186,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.020200729370117,
+      "eval_runtime": 2.4621,
+      "eval_samples_per_second": 406.152,
+      "eval_steps_per_second": 67.827,
       "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
-    },
-    {
-      "epoch": 0.225,
-      "grad_norm": 0.21822796761989594,
-      "learning_rate": 3.6921905048418706e-06,
-      "loss": 21.950730895996095,
-      "step": 45
-    },
-    {
-      "epoch": 0.25,
-      "grad_norm": 0.22425295412540436,
-      "learning_rate": 3.598375993789849e-06,
-      "loss": 21.952291870117186,
-      "step": 50
-    },
-    {
-      "epoch": 0.275,
-      "grad_norm": 0.2449563443660736,
-      "learning_rate": 3.4936429539683075e-06,
-      "loss": 21.959083557128906,
-      "step": 55
-    },
-    {
-      "epoch": 0.3,
-      "grad_norm": 0.21149370074272156,
-      "learning_rate": 3.3787068182371314e-06,
-      "loss": 21.980178833007812,
-      "step": 60
-    },
-    {
-      "epoch": 0.3,
-      "eval_accuracy": 7.827788649706458e-06,
-      "eval_loss": 10.983661651611328,
-      "eval_runtime": 5.397,
-      "eval_samples_per_second": 185.287,
-      "eval_steps_per_second": 30.943,
-      "step": 60
     }
   ],
   "logging_steps": 5,