Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:584527770bbf61e7d3b9f5f5d7f0c7a2aed0cb0bbeab1852ed5dfa972751a3a6
+oid sha256:a2d552abe54bc8b78698f085328cba7d4ca9faffbe5c176d69ae6298a741dc1f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5913ee9284fa8aa307711a2e744c4df8b62a0ed34b254b5187e266b9a990b3a6
+oid sha256:23a4a556c668ac483f251fb2542a9567fdbeee24015d2afebd6c40ac1db320d9
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0db314fbdae64c2adb9ae851d5b0fd06db20205c5b2a3393b31aa089ac9035
+oid sha256:d44945f90b9153cb2a69f9475450a2111e7f4db9372411c8f14f263baffa58d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e60a31f38c722952d958f95680b7f288aeccf8a56dab49290f6f451d5b392c
+oid sha256:5115d8af133b4318a75821bef26ae5de84c140c9bd70b7ac727a7737d85cfbd6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08279111981391907,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-8500",
-  "epoch": 1.3599999999999999,
+  "best_metric": 0.08268450945615768,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-9000",
+  "epoch": 1.44,
   "eval_steps": 500,
-  "global_step": 8500,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1333,6 +1333,84 @@
       "eval_samples_per_second": 17.143,
       "eval_steps_per_second": 2.143,
       "step": 8500
+    },
+    {
+      "epoch": 1.3679999999999999,
+      "grad_norm": 6076.61865234375,
+      "learning_rate": 1.6320000000000003e-05,
+      "loss": 0.0566,
+      "step": 8550
+    },
+    {
+      "epoch": 1.376,
+      "grad_norm": 6356.2578125,
+      "learning_rate": 1.624e-05,
+      "loss": 0.0527,
+      "step": 8600
+    },
+    {
+      "epoch": 1.384,
+      "grad_norm": 8593.4482421875,
+      "learning_rate": 1.6159999999999998e-05,
+      "loss": 0.0611,
+      "step": 8650
+    },
+    {
+      "epoch": 1.392,
+      "grad_norm": 6525.712890625,
+      "learning_rate": 1.6080000000000002e-05,
+      "loss": 0.0508,
+      "step": 8700
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 6376.82177734375,
+      "learning_rate": 1.6e-05,
+      "loss": 0.0554,
+      "step": 8750
+    },
+    {
+      "epoch": 1.408,
+      "grad_norm": 7890.4990234375,
+      "learning_rate": 1.592e-05,
+      "loss": 0.0546,
+      "step": 8800
+    },
+    {
+      "epoch": 1.416,
+      "grad_norm": 5426.74267578125,
+      "learning_rate": 1.584e-05,
+      "loss": 0.0558,
+      "step": 8850
+    },
+    {
+      "epoch": 1.424,
+      "grad_norm": 8708.7294921875,
+      "learning_rate": 1.576e-05,
+      "loss": 0.0597,
+      "step": 8900
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 7744.2490234375,
+      "learning_rate": 1.568e-05,
+      "loss": 0.0553,
+      "step": 8950
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 4320.080078125,
+      "learning_rate": 1.56e-05,
+      "loss": 0.0602,
+      "step": 9000
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.08268450945615768,
+      "eval_runtime": 116.8196,
+      "eval_samples_per_second": 17.12,
+      "eval_steps_per_second": 2.14,
+      "step": 9000
     }
   ],
   "logging_steps": 50,
@@ -1352,7 +1430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.140913655808e+16,
+  "total_flos": 4.384496812032e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null