Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8edb6bc652ecf8d8b92148bf158d74d215cf39e93698c3cc1dc292a00fa77c20
+oid sha256:20fd6b0054d1f056bdd1f068136faf6ae936a9917ce75d20eb97a5588d22cf17
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afd60e4bb235de62341215451cdba1253c241ce49458a0fd6fdfa8847c6d9c92
+oid sha256:978241794f0765cf1904aaf145ce5b4c824548d741ec93437d45849535a4ab04
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29ed82ba21af44a36d8e59405dc8d62a827ba1626cee944f74dd401606bce37
+oid sha256:e79bcfaf683538279e39272f16342dfc788f3ded86099a7f67e3c0cbc2e642c8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8cd62b06b1b0d4df8a23768d02bad43aa10b569b79d6231c3ee6daaff17e07
+oid sha256:ab6c69dd439a3fb69dcb9250bb4485f8f30f907b01e32d0bd8204147e7413181
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.29390034079551697,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-1500",
-  "epoch": 2.493765586034913,
+  "best_metric": 0.288575142621994,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-2000",
+  "epoch": 3.3250207813798838,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -337,6 +337,116 @@
       "eval_samples_per_second": 12.917,
       "eval_steps_per_second": 1.621,
       "step": 1500
+    },
+    {
+      "epoch": 2.57689110556941,
+      "grad_norm": 42211.703125,
+      "learning_rate": 1.776206322795341e-05,
+      "loss": 0.3199,
+      "step": 1550
+    },
+    {
+      "epoch": 2.660016625103907,
+      "grad_norm": 41404.1953125,
+      "learning_rate": 1.6722129783693842e-05,
+      "loss": 0.3321,
+      "step": 1600
+    },
+    {
+      "epoch": 2.660016625103907,
+      "eval_loss": 0.2914765477180481,
+      "eval_runtime": 38.3949,
+      "eval_samples_per_second": 12.866,
+      "eval_steps_per_second": 1.615,
+      "step": 1600
+    },
+    {
+      "epoch": 2.743142144638404,
+      "grad_norm": 65816.5546875,
+      "learning_rate": 1.5682196339434277e-05,
+      "loss": 0.3314,
+      "step": 1650
+    },
+    {
+      "epoch": 2.826267664172901,
+      "grad_norm": 80084.921875,
+      "learning_rate": 1.464226289517471e-05,
+      "loss": 0.3163,
+      "step": 1700
+    },
+    {
+      "epoch": 2.826267664172901,
+      "eval_loss": 0.29080235958099365,
+      "eval_runtime": 38.4641,
+      "eval_samples_per_second": 12.843,
+      "eval_steps_per_second": 1.612,
+      "step": 1700
+    },
+    {
+      "epoch": 2.9093931837073983,
+      "grad_norm": 41843.58203125,
+      "learning_rate": 1.3602329450915141e-05,
+      "loss": 0.3334,
+      "step": 1750
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "grad_norm": 46427.6796875,
+      "learning_rate": 1.2562396006655574e-05,
+      "loss": 0.3196,
+      "step": 1800
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "eval_loss": 0.2890726923942566,
+      "eval_runtime": 38.2139,
+      "eval_samples_per_second": 12.927,
+      "eval_steps_per_second": 1.622,
+      "step": 1800
+    },
+    {
+      "epoch": 3.0756442227763925,
+      "grad_norm": 45502.953125,
+      "learning_rate": 1.1522462562396007e-05,
+      "loss": 0.3226,
+      "step": 1850
+    },
+    {
+      "epoch": 3.1587697423108896,
+      "grad_norm": 57836.49609375,
+      "learning_rate": 1.048252911813644e-05,
+      "loss": 0.3216,
+      "step": 1900
+    },
+    {
+      "epoch": 3.1587697423108896,
+      "eval_loss": 0.2888147532939911,
+      "eval_runtime": 38.2133,
+      "eval_samples_per_second": 12.927,
+      "eval_steps_per_second": 1.622,
+      "step": 1900
+    },
+    {
+      "epoch": 3.2418952618453867,
+      "grad_norm": 51613.7734375,
+      "learning_rate": 9.442595673876873e-06,
+      "loss": 0.3169,
+      "step": 1950
+    },
+    {
+      "epoch": 3.3250207813798838,
+      "grad_norm": 53367.69921875,
+      "learning_rate": 8.402662229617304e-06,
+      "loss": 0.3183,
+      "step": 2000
+    },
+    {
+      "epoch": 3.3250207813798838,
+      "eval_loss": 0.288575142621994,
+      "eval_runtime": 38.3741,
+      "eval_samples_per_second": 12.873,
+      "eval_steps_per_second": 1.616,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -356,7 +466,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.461377145765888e+16,
+  "total_flos": 1.948482562424832e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null