Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb86b7f70b45053cb6d55ae4376642fa03d54495b5c27e78b0cd2d46a00b5c0b
+oid sha256:8edb6bc652ecf8d8b92148bf158d74d215cf39e93698c3cc1dc292a00fa77c20
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d232a9a6c756331696e700546387d842e2067cae42866a06dd49ad2965fbaa1e
+oid sha256:afd60e4bb235de62341215451cdba1253c241ce49458a0fd6fdfa8847c6d9c92
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1952f58fa52e592468a775e85ac7e72d5b2b6d4cdb2766a2b20ab5e3f11899
+oid sha256:a29ed82ba21af44a36d8e59405dc8d62a827ba1626cee944f74dd401606bce37
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e999a568b2d0f01998dabb86d34bac49ae5618451719e3426ca61159d87ee5c4
+oid sha256:5b8cd62b06b1b0d4df8a23768d02bad43aa10b569b79d6231c3ee6daaff17e07
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3063213527202606,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
-  "epoch": 1.6625103906899419,
+  "best_metric": 0.29390034079551697,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1500",
+  "epoch": 2.493765586034913,
   "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": 12.901,
       "eval_steps_per_second": 1.619,
       "step": 1000
+    },
+    {
+      "epoch": 1.745635910224439,
+      "grad_norm": 57559.86328125,
+      "learning_rate": 2.816139767054909e-05,
+      "loss": 0.3649,
+      "step": 1050
+    },
+    {
+      "epoch": 1.828761429758936,
+      "grad_norm": 54892.80078125,
+      "learning_rate": 2.7121464226289517e-05,
+      "loss": 0.3518,
+      "step": 1100
+    },
+    {
+      "epoch": 1.828761429758936,
+      "eval_loss": 0.30387237668037415,
+      "eval_runtime": 38.3202,
+      "eval_samples_per_second": 12.891,
+      "eval_steps_per_second": 1.618,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9118869492934332,
+      "grad_norm": 56018.88671875,
+      "learning_rate": 2.608153078202995e-05,
+      "loss": 0.3515,
+      "step": 1150
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "grad_norm": 46875.38671875,
+      "learning_rate": 2.5041597337770382e-05,
+      "loss": 0.3459,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "eval_loss": 0.29989051818847656,
+      "eval_runtime": 38.3688,
+      "eval_samples_per_second": 12.875,
+      "eval_steps_per_second": 1.616,
+      "step": 1200
+    },
+    {
+      "epoch": 2.0781379883624274,
+      "grad_norm": 46399.90234375,
+      "learning_rate": 2.4001663893510817e-05,
+      "loss": 0.3293,
+      "step": 1250
+    },
+    {
+      "epoch": 2.1612635078969245,
+      "grad_norm": 57348.53515625,
+      "learning_rate": 2.296173044925125e-05,
+      "loss": 0.3387,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1612635078969245,
+      "eval_loss": 0.29858091473579407,
+      "eval_runtime": 38.3821,
+      "eval_samples_per_second": 12.871,
+      "eval_steps_per_second": 1.615,
+      "step": 1300
+    },
+    {
+      "epoch": 2.2443890274314215,
+      "grad_norm": 32873.6796875,
+      "learning_rate": 2.1921797004991683e-05,
+      "loss": 0.3366,
+      "step": 1350
+    },
+    {
+      "epoch": 2.3275145469659186,
+      "grad_norm": 47216.03125,
+      "learning_rate": 2.0881863560732114e-05,
+      "loss": 0.3528,
+      "step": 1400
+    },
+    {
+      "epoch": 2.3275145469659186,
+      "eval_loss": 0.29636165499687195,
+      "eval_runtime": 38.2663,
+      "eval_samples_per_second": 12.91,
+      "eval_steps_per_second": 1.62,
+      "step": 1400
+    },
+    {
+      "epoch": 2.4106400665004157,
+      "grad_norm": 52153.40234375,
+      "learning_rate": 1.9841930116472545e-05,
+      "loss": 0.3379,
+      "step": 1450
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 57533.625,
+      "learning_rate": 1.880199667221298e-05,
+      "loss": 0.3175,
+      "step": 1500
+    },
+    {
+      "epoch": 2.493765586034913,
+      "eval_loss": 0.29390034079551697,
+      "eval_runtime": 38.2441,
+      "eval_samples_per_second": 12.917,
+      "eval_steps_per_second": 1.621,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -246,7 +356,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9742717291069440.0,
+  "total_flos": 1.461377145765888e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null