Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4914014d0048ad419fae9de3c869e8a9a3d01941ac99d4fb0d4e64993586925
+oid sha256:5c18809a2a8524e90e4ddf568d1d17bb67d1937003a32e0da3eb60d17f7f9e89
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0d6710d4838767ab1eabb79915f8d054b5869aa459ff20b6ec3b53afb8931b9
+oid sha256:83ad02ce37e2b4dcfde5be370954593d1a517fdabb1afb6bf5cf71dbfbf597a9
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:686e4f08928bc0c19b99582b6c5fe9ffd12480ee988aecee97f880477c357d0e
+oid sha256:ee7003d2d3db8b5d062c3280168e1b356926dfcb2c85d0b9bea95ac9bb64d84f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0190d5e62eedbb928211e3640963587aa6f015e5105ee6ffcc852c37876753
+oid sha256:f97d58893698126522dba56d68d161fa3998d8e44e4b677f658d8d5c7b316319
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.12485189735889435,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
-  "epoch": 0.1756388864494599,
+  "best_metric": 0.11999432742595673,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1500",
+  "epoch": 0.26345832967418986,
   "eval_steps": 100,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -227,6 +227,116 @@
       "eval_samples_per_second": 25.513,
       "eval_steps_per_second": 3.192,
       "step": 1000
+    },
+    {
+      "epoch": 0.18442083077193291,
+      "grad_norm": 20060.55859375,
+      "learning_rate": 2.8616722290532233e-05,
+      "loss": 0.1303,
+      "step": 1050
+    },
+    {
+      "epoch": 0.1932027750944059,
+      "grad_norm": 10244.4052734375,
+      "learning_rate": 2.855085192341472e-05,
+      "loss": 0.1413,
+      "step": 1100
+    },
+    {
+      "epoch": 0.1932027750944059,
+      "eval_loss": 0.12359971553087234,
+      "eval_runtime": 175.122,
+      "eval_samples_per_second": 25.468,
+      "eval_steps_per_second": 3.186,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2019847194168789,
+      "grad_norm": 36993.25,
+      "learning_rate": 2.848498155629721e-05,
+      "loss": 0.1275,
+      "step": 1150
+    },
+    {
+      "epoch": 0.2107666637393519,
+      "grad_norm": 11102.2646484375,
+      "learning_rate": 2.8419111189179697e-05,
+      "loss": 0.1377,
+      "step": 1200
+    },
+    {
+      "epoch": 0.2107666637393519,
+      "eval_loss": 0.12276890873908997,
+      "eval_runtime": 175.1309,
+      "eval_samples_per_second": 25.467,
+      "eval_steps_per_second": 3.186,
+      "step": 1200
+    },
+    {
+      "epoch": 0.21954860806182488,
+      "grad_norm": 10398.369140625,
+      "learning_rate": 2.835324082206218e-05,
+      "loss": 0.1356,
+      "step": 1250
+    },
+    {
+      "epoch": 0.2283305523842979,
+      "grad_norm": 14664.177734375,
+      "learning_rate": 2.828737045494467e-05,
+      "loss": 0.1309,
+      "step": 1300
+    },
+    {
+      "epoch": 0.2283305523842979,
+      "eval_loss": 0.1219501867890358,
+      "eval_runtime": 174.8703,
+      "eval_samples_per_second": 25.505,
+      "eval_steps_per_second": 3.191,
+      "step": 1300
+    },
+    {
+      "epoch": 0.23711249670677087,
+      "grad_norm": 9694.1875,
+      "learning_rate": 2.8221500087827156e-05,
+      "loss": 0.1271,
+      "step": 1350
+    },
+    {
+      "epoch": 0.24589444102924388,
+      "grad_norm": 17376.810546875,
+      "learning_rate": 2.8155629720709643e-05,
+      "loss": 0.1434,
+      "step": 1400
+    },
+    {
+      "epoch": 0.24589444102924388,
+      "eval_loss": 0.12065327912569046,
+      "eval_runtime": 174.9734,
+      "eval_samples_per_second": 25.49,
+      "eval_steps_per_second": 3.189,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2546763853517169,
+      "grad_norm": 13443.2255859375,
+      "learning_rate": 2.808975935359213e-05,
+      "loss": 0.1383,
+      "step": 1450
+    },
+    {
+      "epoch": 0.26345832967418986,
+      "grad_norm": 10927.8994140625,
+      "learning_rate": 2.802388898647462e-05,
+      "loss": 0.125,
+      "step": 1500
+    },
+    {
+      "epoch": 0.26345832967418986,
+      "eval_loss": 0.11999432742595673,
+      "eval_runtime": 174.9084,
+      "eval_samples_per_second": 25.499,
+      "eval_steps_per_second": 3.19,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -246,7 +356,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4871663124480000.0,
+  "total_flos": 7307494686720000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null