Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b5263c1decc645c9e701779bd3d240d1bd128257b6edb8ead3471aa6e882ff
+oid sha256:f7454f4d66c270e44df1eacbd6185e4004d87782931028de1f535c0307f116fd
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4662d2a8a819e0d85a2d8fe1130697f20508f25fc829adbfc7041f6ee0ff9440
+oid sha256:5ad72731605d1660caf040ca225055f57942f6652ac3f8e3f4a48d6e14eb50fd
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf69dbca5717fd7e2d59b8c55b37845db01c5e5f067d9b29c7651b0c07744c5
+oid sha256:94a590caf5b0791267c7c662cc1f8162ae428b45baf48632e99e270be42d5011
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ac2ccaa6ddf120173c07745369f72632efad440b0563e86a0141350749aa0ae
+oid sha256:d713a762ef6487a34237b674f0e37296a124b258ea254d4be9d4a61b4da657a1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9666666666666667,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 14500,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1022,6 +1022,41 @@
       "learning_rate": 1.3557333333333333e-05,
       "loss": 0.0643,
       "step": 14500
+    },
+    {
+      "epoch": 0.9733333333333334,
+      "grad_norm": 0.18082498013973236,
+      "learning_rate": 1.351288888888889e-05,
+      "loss": 0.0646,
+      "step": 14600
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.14383332431316376,
+      "learning_rate": 1.3468444444444447e-05,
+      "loss": 0.066,
+      "step": 14700
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 0.20313547551631927,
+      "learning_rate": 1.3424000000000002e-05,
+      "loss": 0.0631,
+      "step": 14800
+    },
+    {
+      "epoch": 0.9933333333333333,
+      "grad_norm": 0.14930222928524017,
+      "learning_rate": 1.3379555555555557e-05,
+      "loss": 0.0593,
+      "step": 14900
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.30177292227745056,
+      "learning_rate": 1.3335111111111113e-05,
+      "loss": 0.0651,
+      "step": 15000
     }
   ],
   "logging_steps": 100,
@@ -1041,7 +1076,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.531955765248e+16,
+  "total_flos": 3.65374734336e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null