Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d47f825f842719e9adc8ec2a96d35e27fb73a091c8034a06f5b1bd0e4f9af0
+oid sha256:9960ab9430f87386052f6f688f2b0ef29d3ef0703741a0a04e86c27a4c613458
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a3d87907b233ae85d2a09dc2082cbf577bf60b26f83265e798ffd5cffb3296
+oid sha256:a4aa5f290eab6ad8c50e2e0e5ff48e2e9b3fda37a1cd0f19a806696d5a692747
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e936ced482e7c9446cc6e6e7038e023dc86c658d8bb3b07d132fc5298cce6557
+oid sha256:3b6e88be627a1cf1c12456905775b93be8b9689df366bf1a41cd17e0652aa2d6
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
+oid sha256:1c2eb03e04e9ec3d534ee7aa67476af96452e64bad29591c419a0c652481ee2b
 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": 0.3,
   "eval_steps": 20,
-  "global_step": 20,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,80 @@
       "eval_samples_per_second": 413.978,
       "eval_steps_per_second": 69.134,
       "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.20359881222248077,
+      "learning_rate": 3.9466531944960116e-06,
+      "loss": 10.710234832763671,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.2262589931488037,
+      "learning_rate": 3.902113032590307e-06,
+      "loss": 10.686376190185547,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.26730242371559143,
+      "learning_rate": 3.844579509954769e-06,
+      "loss": 10.716732788085938,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.3094463050365448,
+      "learning_rate": 3.7744456388872234e-06,
+      "loss": 10.634027862548828,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.034777777777777776,
+      "eval_loss": 10.648277282714844,
+      "eval_runtime": 2.6612,
+      "eval_samples_per_second": 375.767,
+      "eval_steps_per_second": 62.753,
+      "step": 40
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.281914085149765,
+      "learning_rate": 3.6921905048418706e-06,
+      "loss": 10.574553680419921,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2943774461746216,
+      "learning_rate": 3.598375993789849e-06,
+      "loss": 10.494444274902344,
+      "step": 50
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.32790377736091614,
+      "learning_rate": 3.4936429539683075e-06,
+      "loss": 10.530224609375,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.41768601536750793,
+      "learning_rate": 3.3787068182371314e-06,
+      "loss": 10.44730453491211,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.05228571428571428,
+      "eval_loss": 10.494199752807617,
+      "eval_runtime": 2.5664,
+      "eval_samples_per_second": 389.653,
+      "eval_steps_per_second": 65.072,
+      "step": 60
     }
   ],
   "logging_steps": 5,