Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9960ab9430f87386052f6f688f2b0ef29d3ef0703741a0a04e86c27a4c613458
+oid sha256:77c00e25cdc0159a953b89e31ee75fb9f4f04268f163b9148e898a67d1ad3fe2
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4aa5f290eab6ad8c50e2e0e5ff48e2e9b3fda37a1cd0f19a806696d5a692747
+oid sha256:75ec1a2907af41bcd49fe20d0461096a9770864c1c9061542df1c79e4a507473
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b6e88be627a1cf1c12456905775b93be8b9689df366bf1a41cd17e0652aa2d6
+oid sha256:96a091ed1da45753ae33db029e7b844183915b5f9838c10180e2883aeefdf91d
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c2eb03e04e9ec3d534ee7aa67476af96452e64bad29591c419a0c652481ee2b
+oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3,
+  "epoch": 0.5,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,80 @@
       "eval_samples_per_second": 389.653,
       "eval_steps_per_second": 65.072,
       "step": 60
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.3432864248752594,
+      "learning_rate": 3.254352716947074e-06,
+      "loss": 10.377902221679687,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.4390406012535095,
+      "learning_rate": 3.1214301147033453e-06,
+      "loss": 10.318882751464844,
+      "step": 70
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.39456093311309814,
+      "learning_rate": 2.9808470076610163e-06,
+      "loss": 10.358218383789062,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.3331209719181061,
+      "learning_rate": 2.833563720990581e-06,
+      "loss": 10.379315185546876,
+      "step": 80
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.05953968253968254,
+      "eval_loss": 10.34837818145752,
+      "eval_runtime": 2.5456,
+      "eval_samples_per_second": 392.837,
+      "eval_steps_per_second": 65.604,
+      "step": 80
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.394307941198349,
+      "learning_rate": 2.680586348883286e-06,
+      "loss": 10.364244842529297,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.6861296892166138,
+      "learning_rate": 2.5229598819076393e-06,
+      "loss": 10.229421997070313,
+      "step": 90
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.39627140760421753,
+      "learning_rate": 2.36176106866422e-06,
+      "loss": 10.251496124267579,
+      "step": 95
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.48685982823371887,
+      "learning_rate": 2.198091060500926e-06,
+      "loss": 10.250384521484374,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.06242857142857143,
+      "eval_loss": 10.20656967163086,
+      "eval_runtime": 2.4131,
+      "eval_samples_per_second": 414.406,
+      "eval_steps_per_second": 69.206,
+      "step": 100
     }
   ],
   "logging_steps": 5,