Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2eb707efd45838c999c2a5555ec9f4e3948d1f4bebf0270a24ea3404256d4cc
+oid sha256:e095b06f5c65d9c3c8a3debcf3e6201bbcf41c468b57fd9fe8830b5d51ac4f48
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3af0e4724c98927d8a051181e73393d7a65a3c727af1c5a91618fb92dd27408
+oid sha256:3b9380bb79afa61cdc27180520af86aef9f4d10f83ed2161a4655c0531d4686d
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8305955eac22add53d91f06fc3781aadbba74448cb0b21c58a2f9dadbea85a43
+oid sha256:7fb8b27c24f221351a66f6c36da6c9928049823c3f1134500eb9faea09def09e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3714e917b57b234e811d02cff6475eee9087a5c2b589dd59d17c8602540672
+oid sha256:403e883e32409c0a8b6b9b4a178312db263273af6b84b67a9175809fcce1d74a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7,
+  "epoch": 0.7333333333333333,
   "eval_steps": 500,
-  "global_step": 10500,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -742,6 +742,41 @@
       "learning_rate": 1.5334666666666667e-05,
       "loss": 0.0683,
       "step": 10500
+    },
+    {
+      "epoch": 0.7066666666666667,
+      "grad_norm": 0.22483541071414948,
+      "learning_rate": 1.5290222222222223e-05,
+      "loss": 0.0664,
+      "step": 10600
+    },
+    {
+      "epoch": 0.7133333333333334,
+      "grad_norm": 0.16683422029018402,
+      "learning_rate": 1.524577777777778e-05,
+      "loss": 0.0665,
+      "step": 10700
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.2538510262966156,
+      "learning_rate": 1.5201333333333335e-05,
+      "loss": 0.0688,
+      "step": 10800
+    },
+    {
+      "epoch": 0.7266666666666667,
+      "grad_norm": 0.11596673727035522,
+      "learning_rate": 1.515688888888889e-05,
+      "loss": 0.0724,
+      "step": 10900
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.28537997603416443,
+      "learning_rate": 1.5112444444444445e-05,
+      "loss": 0.068,
+      "step": 11000
     }
   ],
   "logging_steps": 100,
@@ -761,7 +796,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.557623140352e+16,
+  "total_flos": 2.679414718464e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null