Training in progress, step 60000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af3f4a1f133742ba96dae3c45f770a27ea62c2e568471f10d66b5855eb2dc1d
+oid sha256:b9423ced92e1ead42dafd29660955040c4f9cbeb106ac16d725898dabb295a0b
 size 409608164

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:509f3c88035b7e9fb05ec96eb47bdd5e2808c2d07898812b41f063bc86b89bbf
+oid sha256:7a8525f10d587fdf62ca0b5a216d729a480636349022a107c4c4f443ecd7e1a6
 size 814647162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9643649b2a55e6c3d1369ebca0f19dd3fdfc0858f9b4499b8fb83e2169b0729e
+oid sha256:ce9759301f561e437292986014727b714a5d6c291bf10ad6a3f2ba61221ee481
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.945551390806865,
+  "epoch": 5.918327086210298,
   "eval_steps": 20000,
-  "global_step": 40000,
+  "global_step": 60000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,34 @@
       "learning_rate": 5e-05,
       "loss": 0.0008,
       "step": 40000
+    },
+    {
+      "epoch": 4.438745314657724,
+      "grad_norm": 0.05877165496349335,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 45000
+    },
+    {
+      "epoch": 4.931939238508582,
+      "grad_norm": 0.0312739722430706,
+      "learning_rate": 5e-05,
+      "loss": 0.0008,
+      "step": 50000
+    },
+    {
+      "epoch": 5.425133162359439,
+      "grad_norm": 0.013028254732489586,
+      "learning_rate": 5e-05,
+      "loss": 0.0007,
+      "step": 55000
+    },
+    {
+      "epoch": 5.918327086210298,
+      "grad_norm": 0.011430254206061363,
+      "learning_rate": 5e-05,
+      "loss": 0.0006,
+      "step": 60000
     }
   ],
   "logging_steps": 5000,
@@ -82,7 +110,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.465293207841869e+17,
+  "total_flos": 5.1980516444269824e+17,
   "train_batch_size": 128,
   "trial_name": null,
   "trial_params": null