Training in progress, step 13500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890ad2873a2bbd9defa42e9be53c396630c1fa479c804ecbcda9c1bef5c9a5b7
+oid sha256:a5eab5cf423687e71bb09a2192d390f2707db089b85d712fe4ba933f4e60e68f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df779224de4aac7dbc2c481b18f226ef75df55b33434fd2a24aaa00199ae182
+oid sha256:807f9477c6257e1784434ba0760f1f95f0fdf6abcdcb9183ee441309d58f6f04
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:392a7eb84bc6c0f11073a38c2f0980cc2fcea2ab711f0ee9d31a3b2c47437b70
+oid sha256:35473c59fad66809b7d88f5a452c0f7e0ed4b7e0e9e5416152035290cb60f273
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8f863bfc80aea1aeb546487ead9ef6092bc37fe14387401d70bc8b324d152f2
+oid sha256:3f3a75abd7e2a468c4e910b9da4dc47554f88ea4d9cfaefa84fb6258d08648a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8666666666666667,
+  "epoch": 0.9,
   "eval_steps": 500,
-  "global_step": 13000,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -917,6 +917,41 @@
       "learning_rate": 1.4223555555555557e-05,
       "loss": 0.0723,
       "step": 13000
+    },
+    {
+      "epoch": 0.8733333333333333,
+      "grad_norm": 0.2538166642189026,
+      "learning_rate": 1.4179111111111112e-05,
+      "loss": 0.065,
+      "step": 13100
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.3290730118751526,
+      "learning_rate": 1.4134666666666667e-05,
+      "loss": 0.0712,
+      "step": 13200
+    },
+    {
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.1109674721956253,
+      "learning_rate": 1.4090222222222222e-05,
+      "loss": 0.0658,
+      "step": 13300
+    },
+    {
+      "epoch": 0.8933333333333333,
+      "grad_norm": 0.30605512857437134,
+      "learning_rate": 1.4045777777777777e-05,
+      "loss": 0.0696,
+      "step": 13400
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.32679420709609985,
+      "learning_rate": 1.4001333333333333e-05,
+      "loss": 0.0669,
+      "step": 13500
     }
   ],
   "logging_steps": 100,
@@ -936,7 +971,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.166581030912e+16,
+  "total_flos": 3.288372609024e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null