Training in progress, step 60, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7983cdd29a5b29972d6c4b8862dea15420f3651dc553f3bea94942f74dd801cf
+oid sha256:8fbc25b315eaec6fdfa5a96894be799d4505aeaa0569efe9adef0b9c9c0e39f4
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92389181d276f4f7e82ff00efe6f9cf89365eb036fb84264bc130ea1388a86b0
+oid sha256:3fa7c0721a4a3d85b588484718933d2b751de2198ec9cfb9e99b53e008d4e3d5
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17c78731e93c053cc5bdd46a999e26416061fc6f401c1eac6682002c6f7cf23
+oid sha256:f891a168fb4edd3efbb37e4906a84228928d2ce90f434f192d8f2e669611925b
 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": 406.152,
       "eval_steps_per_second": 67.827,
       "step": 20
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.25184789299964905,
+      "learning_rate": 3.9466531944960116e-06,
+      "loss": 22.0181884765625,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.268789142370224,
+      "learning_rate": 3.902113032590307e-06,
+      "loss": 22.01494598388672,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.2609691917896271,
+      "learning_rate": 3.844579509954769e-06,
+      "loss": 22.0348876953125,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.2492043823003769,
+      "learning_rate": 3.7744456388872234e-06,
+      "loss": 21.99768524169922,
+      "step": 40
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.018282890319824,
+      "eval_runtime": 2.6799,
+      "eval_samples_per_second": 373.142,
+      "eval_steps_per_second": 62.315,
+      "step": 40
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.2999836802482605,
+      "learning_rate": 3.6921905048418706e-06,
+      "loss": 21.986573791503908,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.2840990126132965,
+      "learning_rate": 3.598375993789849e-06,
+      "loss": 22.012301635742187,
+      "step": 50
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.28335806727409363,
+      "learning_rate": 3.4936429539683075e-06,
+      "loss": 22.00952606201172,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.2717016935348511,
+      "learning_rate": 3.3787068182371314e-06,
+      "loss": 21.99034423828125,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 3.1746031746031745e-05,
+      "eval_loss": 11.01639175415039,
+      "eval_runtime": 2.4905,
+      "eval_samples_per_second": 401.523,
+      "eval_steps_per_second": 67.054,
+      "step": 60
     }
   ],
   "logging_steps": 5,