Training in progress, step 26500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ccf946285de08631d7aa88880e80f21b17cb40c2984d2717a416bfb77ad97a
+oid sha256:bfa391b775f0d5dcb24018c3990fb7c29ef27625dac44264f09f0201ea61bae3
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeda28924749f4137205971bf8004ba3b8af4913c5628296171daba1b0f5410d
+oid sha256:6bdafb74e8684c8e1f92c0028b2980a9bdebe0cc49ff0249647d05a17b3e6460
 size 2912179275

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c840b8163698a55b0b3f56b403f2dc973339590ef5a4044d649f1b4f04447f6
+oid sha256:9da56afab166cb01805fb08f77164c54bb9f01376e88d545d9f7d4a3e6c7f528
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d244a2deb00d692097678c7d39b922d3d50456307ac1e0c30012031346000f69
+oid sha256:a8a1bac9c3d7424a0ec2af16484aea0b93a1f8e34ad9ea9ff8b01d003b64aca4
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e8471e657dd25a52d5b26c516ea481cc4691210d002d706f47e19ea6a45959
+oid sha256:8462f87da0cd589acb4f3244d880cd8e2e7f0f4e43c89dd5fa9ee942ead34988
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.0017,
+  "epoch": 8.000599999999999,
   "eval_steps": 500,
-  "global_step": 26000,
+  "global_step": 26500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3648,6 +3648,76 @@
       "learning_rate": 1.3477485853005988e-06,
       "loss": 1.1393611907958985,
       "step": 26000
+    },
+    {
+      "epoch": 1.0016666666666667,
+      "grad_norm": 1.8052189350128174,
+      "learning_rate": 1.3148534303842473e-06,
+      "loss": 0.6258907699584961,
+      "step": 26050
+    },
+    {
+      "epoch": 1.0033333333333334,
+      "grad_norm": 1.859277606010437,
+      "learning_rate": 1.2823462865672564e-06,
+      "loss": 0.6151887893676757,
+      "step": 26100
+    },
+    {
+      "epoch": 1.005,
+      "grad_norm": 1.9823532104492188,
+      "learning_rate": 1.2502280755154994e-06,
+      "loss": 0.5917576980590821,
+      "step": 26150
+    },
+    {
+      "epoch": 1.0066666666666666,
+      "grad_norm": 1.922063946723938,
+      "learning_rate": 1.2184997078675525e-06,
+      "loss": 0.5746277236938476,
+      "step": 26200
+    },
+    {
+      "epoch": 1.0083333333333333,
+      "grad_norm": 2.231234073638916,
+      "learning_rate": 1.187162083208867e-06,
+      "loss": 0.597679443359375,
+      "step": 26250
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 2.0167667865753174,
+      "learning_rate": 1.1562160900462793e-06,
+      "loss": 0.5644707489013672,
+      "step": 26300
+    },
+    {
+      "epoch": 1.0116666666666667,
+      "grad_norm": 2.836120128631592,
+      "learning_rate": 1.1256626057827961e-06,
+      "loss": 0.6299059677124024,
+      "step": 26350
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 2.149437665939331,
+      "learning_rate": 1.0955024966927418e-06,
+      "loss": 0.9067845153808594,
+      "step": 26400
+    },
+    {
+      "epoch": 1.015,
+      "grad_norm": 2.1338465213775635,
+      "learning_rate": 1.065736617897175e-06,
+      "loss": 0.9151818084716797,
+      "step": 26450
+    },
+    {
+      "epoch": 2.0004,
+      "grad_norm": 1.5150409936904907,
+      "learning_rate": 1.0363658133396608e-06,
+      "loss": 0.8027437591552734,
+      "step": 26500
     }
   ],
   "logging_steps": 50,
@@ -3667,7 +3737,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.329784730112819e+18,
+  "total_flos": 2.37679163923329e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null