Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23c0612ad5dddfadcdb2b879901305d100ce5db6de83b8784684c964517cf79f
+oid sha256:d25040acf885f7e2920c47759e972a9c964c43aa59fe6576736ecb99705b9e7f
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c61f1cdd59dbbfa29aaa648b120dc6b7a5660b6947962206ed3d139f3045b83e
+oid sha256:fc841690d9edeb441c534cb39ba0e0b76571370a7dc70d911503af4a861ef3c3
 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 sha256:9537cb1bb802ef9061fb4a55063dce9ed288df8d5f1ce5dca106b05ee393ba0e
+oid sha256:1d51f93e5e4e2970e1d4467bbc53489257074e326323db890e39b7a999de6e4d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.11499012261629105,
-  "best_model_checkpoint": "./fine-tuned/checkpoint-1000",
-  "epoch": 0.08782329952136302,
+  "best_metric": 0.11325465887784958,
+  "best_model_checkpoint": "./fine-tuned/checkpoint-1500",
+  "epoch": 0.13173494928204452,
   "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": 54.079,
       "eval_steps_per_second": 13.52,
       "step": 1000
+    },
+    {
+      "epoch": 0.09221446449743116,
+      "grad_norm": 0.3713476359844208,
+      "learning_rate": 4.884726857544353e-05,
+      "loss": 0.1251,
+      "step": 1050
+    },
+    {
+      "epoch": 0.09660562947349932,
+      "grad_norm": 0.37777256965637207,
+      "learning_rate": 4.8792376602845605e-05,
+      "loss": 0.1153,
+      "step": 1100
+    },
+    {
+      "epoch": 0.09660562947349932,
+      "eval_loss": 0.11525405198335648,
+      "eval_runtime": 85.5526,
+      "eval_samples_per_second": 52.132,
+      "eval_steps_per_second": 13.033,
+      "step": 1100
+    },
+    {
+      "epoch": 0.10099679444956747,
+      "grad_norm": 0.48114562034606934,
+      "learning_rate": 4.873748463024767e-05,
+      "loss": 0.1242,
+      "step": 1150
+    },
+    {
+      "epoch": 0.10538795942563563,
+      "grad_norm": 0.7776908278465271,
+      "learning_rate": 4.868259265764974e-05,
+      "loss": 0.1237,
+      "step": 1200
+    },
+    {
+      "epoch": 0.10538795942563563,
+      "eval_loss": 0.11445864289999008,
+      "eval_runtime": 82.4683,
+      "eval_samples_per_second": 54.081,
+      "eval_steps_per_second": 13.52,
+      "step": 1200
+    },
+    {
+      "epoch": 0.10977912440170377,
+      "grad_norm": 0.34126266837120056,
+      "learning_rate": 4.8627700685051817e-05,
+      "loss": 0.1331,
+      "step": 1250
+    },
+    {
+      "epoch": 0.11417028937777192,
+      "grad_norm": 0.32315969467163086,
+      "learning_rate": 4.857280871245389e-05,
+      "loss": 0.1167,
+      "step": 1300
+    },
+    {
+      "epoch": 0.11417028937777192,
+      "eval_loss": 0.11452117562294006,
+      "eval_runtime": 82.4936,
+      "eval_samples_per_second": 54.065,
+      "eval_steps_per_second": 13.516,
+      "step": 1300
+    },
+    {
+      "epoch": 0.11856145435384008,
+      "grad_norm": 0.7266770005226135,
+      "learning_rate": 4.8517916739855967e-05,
+      "loss": 0.1183,
+      "step": 1350
+    },
+    {
+      "epoch": 0.12295261932990822,
+      "grad_norm": 0.4979361295700073,
+      "learning_rate": 4.8463024767258035e-05,
+      "loss": 0.126,
+      "step": 1400
+    },
+    {
+      "epoch": 0.12295261932990822,
+      "eval_loss": 0.11409644037485123,
+      "eval_runtime": 82.4146,
+      "eval_samples_per_second": 54.117,
+      "eval_steps_per_second": 13.529,
+      "step": 1400
+    },
+    {
+      "epoch": 0.12734378430597637,
+      "grad_norm": 0.45280951261520386,
+      "learning_rate": 4.840813279466011e-05,
+      "loss": 0.1152,
+      "step": 1450
+    },
+    {
+      "epoch": 0.13173494928204452,
+      "grad_norm": 0.9963550567626953,
+      "learning_rate": 4.8353240822062185e-05,
+      "loss": 0.1214,
+      "step": 1500
+    },
+    {
+      "epoch": 0.13173494928204452,
+      "eval_loss": 0.11325465887784958,
+      "eval_runtime": 82.4565,
+      "eval_samples_per_second": 54.089,
+      "eval_steps_per_second": 13.522,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -246,7 +356,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2435831562240000.0,
+  "total_flos": 3653747343360000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null