Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10dd57fcd736d65d260ba835b7c77d356de5997eccf0f1f5adde9a6c1fb79ca
+oid sha256:1d71119324b3109a34a9396b252713d1c7a33300926730448d19bad79e2fc94d
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6343b146a693516c9b46c66a077b7f935cb841637dd5341caeb48b69ad74ca7e
+oid sha256:192c1628fa6ba90c2e2eea76bce894e7928e103e0ff2e411b1a192ba2e3a6098
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0d20d58bd89e713c08b07c8c7060ac9cf564e52b782f77021cead0bd733f4b
+oid sha256:72de1dad8d6233809f2cfc8005c48069a201d59ec0aed6d89a2e0fa5965139f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf23b21acd31c1d3464aaff618f82d2724f1b36ad9868a85d99877306c53404
+oid sha256:335ba4732fe45980d817fe65fa869ea46a58faf3835fd932d943333c0de29991
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4546965918536992,
+  "epoch": 1.6625103906899419,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,13 @@
       "learning_rate": 1.4184538653366584e-05,
       "loss": 0.3754,
       "step": 3500
+    },
+    {
+      "epoch": 1.6625103906899419,
+      "grad_norm": 0.8853089213371277,
+      "learning_rate": 1.3353283458021613e-05,
+      "loss": 0.3765,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -83,7 +90,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8524801509949440.0,
+  "total_flos": 9742717291069440.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null