Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9eafc134df51821e99102a2c02021eb6847f0e850e860b489f89486bb303847
+oid sha256:9fb570867b39da8ca5f9dcb5a985b279fec72307f9c34b27d25f5a270d849bb9
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dca2bab1e815bc1120f377c6201b185595d37f6b37b814f735ebac86c9f0302
+oid sha256:7c2a8d621b78697c67005e055c00235f3d9085c1c8d486bb9edd4ae03d403f83
 size 1049049442

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ebe82472181f5e2ac977fc05ac3d706bdf91a6df52d349fe6caf55d98226f0d
+oid sha256:b3dd9835961741b97ed6bc0c71057c6d15eaf84418093825034d870f676dd7ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab8798ab47122f078def382b6a2914797f624615be5bff19e7c962ff24a984b
+oid sha256:6d349b525fc7c7eff553c27846b0059879b2d31c63b4e246efacc449795c47e3
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.26471745967865,
-  "best_model_checkpoint": "./output/checkpoint-300",
-  "epoch": 0.013437849944008958,
+  "best_metric": 1.2499778270721436,
+  "best_model_checkpoint": "./output/checkpoint-450",
+  "epoch": 0.020156774916013438,
   "eval_steps": 150,
-  "global_step": 300,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -233,6 +233,119 @@
       "eval_samples_per_second": 9.656,
       "eval_steps_per_second": 9.656,
       "step": 300
+    },
+    {
+      "epoch": 0.013885778275475923,
+      "grad_norm": 6.256772994995117,
+      "learning_rate": 7.4660616066297565e-06,
+      "loss": 1.2176,
+      "step": 310
+    },
+    {
+      "epoch": 0.01433370660694289,
+      "grad_norm": 7.437366485595703,
+      "learning_rate": 7.462757908684509e-06,
+      "loss": 1.046,
+      "step": 320
+    },
+    {
+      "epoch": 0.014781634938409855,
+      "grad_norm": 8.049488067626953,
+      "learning_rate": 7.459301593803512e-06,
+      "loss": 1.2396,
+      "step": 330
+    },
+    {
+      "epoch": 0.01522956326987682,
+      "grad_norm": 5.115020751953125,
+      "learning_rate": 7.455692804062335e-06,
+      "loss": 1.1018,
+      "step": 340
+    },
+    {
+      "epoch": 0.015677491601343786,
+      "grad_norm": 5.805201530456543,
+      "learning_rate": 7.451931687804189e-06,
+      "loss": 1.0083,
+      "step": 350
+    },
+    {
+      "epoch": 0.01612541993281075,
+      "grad_norm": 5.960669040679932,
+      "learning_rate": 7.448018399633831e-06,
+      "loss": 1.1773,
+      "step": 360
+    },
+    {
+      "epoch": 0.016573348264277716,
+      "grad_norm": 4.82655143737793,
+      "learning_rate": 7.443953100411214e-06,
+      "loss": 1.2279,
+      "step": 370
+    },
+    {
+      "epoch": 0.01702127659574468,
+      "grad_norm": 5.768619060516357,
+      "learning_rate": 7.439735957244862e-06,
+      "loss": 1.0924,
+      "step": 380
+    },
+    {
+      "epoch": 0.017469204927211646,
+      "grad_norm": 4.603348731994629,
+      "learning_rate": 7.435367143485015e-06,
+      "loss": 0.9547,
+      "step": 390
+    },
+    {
+      "epoch": 0.01791713325867861,
+      "grad_norm": 3.802041530609131,
+      "learning_rate": 7.430846838716496e-06,
+      "loss": 1.0569,
+      "step": 400
+    },
+    {
+      "epoch": 0.018365061590145577,
+      "grad_norm": 4.473762035369873,
+      "learning_rate": 7.426175228751328e-06,
+      "loss": 1.1299,
+      "step": 410
+    },
+    {
+      "epoch": 0.018812989921612542,
+      "grad_norm": 4.674028396606445,
+      "learning_rate": 7.421352505621099e-06,
+      "loss": 1.0512,
+      "step": 420
+    },
+    {
+      "epoch": 0.019260918253079507,
+      "grad_norm": 5.1446852684021,
+      "learning_rate": 7.416378867569069e-06,
+      "loss": 1.2024,
+      "step": 430
+    },
+    {
+      "epoch": 0.019708846584546472,
+      "grad_norm": 3.742156744003296,
+      "learning_rate": 7.411254519042017e-06,
+      "loss": 1.1778,
+      "step": 440
+    },
+    {
+      "epoch": 0.020156774916013438,
+      "grad_norm": 4.0376200675964355,
+      "learning_rate": 7.4059796706818396e-06,
+      "loss": 1.1754,
+      "step": 450
+    },
+    {
+      "epoch": 0.020156774916013438,
+      "eval_loss": 1.2499778270721436,
+      "eval_runtime": 51.5995,
+      "eval_samples_per_second": 9.69,
+      "eval_steps_per_second": 9.69,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -252,7 +365,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.8701300386816e+16,
+  "total_flos": 5.76911261749248e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null