Training in progress, step 300, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a5404464e9bb484d34cf47867fbfeae189029cf7ff2bee8c63256927076502f
+oid sha256:7c94f899c514e12a820c23aaf925d4a1475a383489cdbbd6502459774a667e01
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c832c15b463bb0902009acdb43bc55402abacb2120ea591b3d08765c6df315f
+oid sha256:ce5808469d477aea76707d2ab205a2b598c3d86fbb6b6471f18fded5891837cc
 size 1386414411

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b61860000f270ef24d0bb03522991107ebd533901ca499cabb492a726a088a
+oid sha256:f2956d0704bae4bbc2056ae3e3a91cba1a4117f4aac73ee5eec7d6c7bf571124
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fab8fc2dd4bbc722b26708598a504e6b169355d93ff7b889697b9ea28dd82b
+oid sha256:9cb1c7e258755e6f64d191d585f4960891d04b05a26de3d362fbb9dcf838225a
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cccf9bf3b3a85fdcc4a8781fe5c4acc7a0e94c949399f0bb52fbdd509f3aa7c
+oid sha256:32d437b6655ea823ecb16d599030f677e6972a2920b12c5ad966216cb4149cd7
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15,
+  "epoch": 0.3,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,36 @@
       "eval_samples_per_second": 80.007,
       "eval_steps_per_second": 1.28,
       "step": 150
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 5204.32177734375,
+      "learning_rate": 9.91822760447871e-07,
+      "loss": 74.1263,
+      "step": 200
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3447.847412109375,
+      "learning_rate": 9.66900501749214e-07,
+      "loss": 74.1159,
+      "step": 250
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7081.478515625,
+      "learning_rate": 9.26078506448917e-07,
+      "loss": 73.7028,
+      "step": 300
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.2524926128464903,
+      "eval_loss": 4.656529903411865,
+      "eval_runtime": 6.2929,
+      "eval_samples_per_second": 79.455,
+      "eval_steps_per_second": 1.271,
+      "step": 300
     }
   ],
   "logging_steps": 50,