Training in progress, step 4500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d71119324b3109a34a9396b252713d1c7a33300926730448d19bad79e2fc94d
+oid sha256:809f1a1aeaef919d82f3f22c05e487fbc5fc7e139d3d58b4d52c8e126c7986e7
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192c1628fa6ba90c2e2eea76bce894e7928e103e0ff2e411b1a192ba2e3a6098
+oid sha256:9556b210fcb352112c2a38a6d47a9d83bba4ecf5c0cd6e72b31cd7982e53cb6a
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72de1dad8d6233809f2cfc8005c48069a201d59ec0aed6d89a2e0fa5965139f5
+oid sha256:9a8f0c85caf6dd2f34d726a24b370bad056914b0890ab902dc89abc74fd551d9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335ba4732fe45980d817fe65fa869ea46a58faf3835fd932d943333c0de29991
+oid sha256:f2e04a982a3fa698ff22d0e2f7f2de0d9d80aaf95f3178aef44eaed617903f5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6625103906899419,
+  "epoch": 1.8703241895261846,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -71,6 +71,13 @@
       "learning_rate": 1.3353283458021613e-05,
       "loss": 0.3765,
       "step": 4000
+    },
+    {
+      "epoch": 1.8703241895261846,
+      "grad_norm": 0.59534752368927,
+      "learning_rate": 1.2522028262676643e-05,
+      "loss": 0.3677,
+      "step": 4500
     }
   ],
   "logging_steps": 500,
@@ -90,7 +97,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9742717291069440.0,
+  "total_flos": 1.096063307218944e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null