Training in progress, step 4650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89096aa0386bd07d2645f68b9a29bafea399f79871d40185060fa68039636b1f
+oid sha256:3c38b95ab4aac2f796998b2cfae140f7979cade13adf03e7235fd1703458464a
 size 1482788592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da854ce99198fc748d7dc94ec6e70f668228ef91b0f8c29002a2372a254620c5
+oid sha256:8f2403d6ad34d7bc46cc37f112101c35525ca09ffdb487a561af0837bd32f6f7
 size 2897966842

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2acbf6096e071e41d5582e116888a7c6ecc44cbafa614aca8be409b37f1ebc9a
+oid sha256:52314eeefbaa59acf058c36cd4c74c081929976886aaef2fb3ee73049c9effaf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f72d12e08f2981b12196a00ff48fe5cac0ba4d9d1aa54f91464a195ecde87c8
+oid sha256:931d38342b692c160fcb90f4d9acb8e6f6634f499984cdd5b99b0563194d400a
 size 1256

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2155283689498901,
-  "best_model_checkpoint": "./output/checkpoint-4500",
-  "epoch": 0.297441998810232,
+  "best_metric": 1.2152043581008911,
+  "best_model_checkpoint": "./output/checkpoint-4650",
+  "epoch": 0.3073567321039064,
   "eval_steps": 150,
-  "global_step": 4500,
+  "global_step": 4650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3397,6 +3397,119 @@
       "eval_samples_per_second": 10.436,
       "eval_steps_per_second": 10.436,
       "step": 4500
+    },
+    {
+      "epoch": 0.2981029810298103,
+      "grad_norm": 10.411969184875488,
+      "learning_rate": 5.472047830984499e-07,
+      "loss": 1.1499,
+      "step": 4510
+    },
+    {
+      "epoch": 0.2987639632493886,
+      "grad_norm": 6.937885761260986,
+      "learning_rate": 5.252725889984403e-07,
+      "loss": 1.0297,
+      "step": 4520
+    },
+    {
+      "epoch": 0.29942494546896686,
+      "grad_norm": 10.743237495422363,
+      "learning_rate": 5.037783829820298e-07,
+      "loss": 1.1198,
+      "step": 4530
+    },
+    {
+      "epoch": 0.3000859276885452,
+      "grad_norm": 5.665622234344482,
+      "learning_rate": 4.827230485918372e-07,
+      "loss": 1.0459,
+      "step": 4540
+    },
+    {
+      "epoch": 0.30074690990812347,
+      "grad_norm": 9.720799446105957,
+      "learning_rate": 4.6210745133019236e-07,
+      "loss": 1.1943,
+      "step": 4550
+    },
+    {
+      "epoch": 0.30140789212770175,
+      "grad_norm": 11.57904052734375,
+      "learning_rate": 4.419324386235529e-07,
+      "loss": 1.2007,
+      "step": 4560
+    },
+    {
+      "epoch": 0.3020688743472801,
+      "grad_norm": 10.47191333770752,
+      "learning_rate": 4.2219883978767386e-07,
+      "loss": 1.1754,
+      "step": 4570
+    },
+    {
+      "epoch": 0.30272985656685836,
+      "grad_norm": 8.371639251708984,
+      "learning_rate": 4.029074659935082e-07,
+      "loss": 1.0829,
+      "step": 4580
+    },
+    {
+      "epoch": 0.30339083878643663,
+      "grad_norm": 11.640840530395508,
+      "learning_rate": 3.8405911023387444e-07,
+      "loss": 1.0573,
+      "step": 4590
+    },
+    {
+      "epoch": 0.3040518210060149,
+      "grad_norm": 14.082575798034668,
+      "learning_rate": 3.6565454729085526e-07,
+      "loss": 1.2711,
+      "step": 4600
+    },
+    {
+      "epoch": 0.30471280322559324,
+      "grad_norm": 8.940695762634277,
+      "learning_rate": 3.4769453370394753e-07,
+      "loss": 1.1595,
+      "step": 4610
+    },
+    {
+      "epoch": 0.3053737854451715,
+      "grad_norm": 7.7234954833984375,
+      "learning_rate": 3.301798077389637e-07,
+      "loss": 1.2151,
+      "step": 4620
+    },
+    {
+      "epoch": 0.3060347676647498,
+      "grad_norm": 4.756081581115723,
+      "learning_rate": 3.1311108935768926e-07,
+      "loss": 1.173,
+      "step": 4630
+    },
+    {
+      "epoch": 0.30669574988432813,
+      "grad_norm": 10.524628639221191,
+      "learning_rate": 2.964890801882817e-07,
+      "loss": 1.0992,
+      "step": 4640
+    },
+    {
+      "epoch": 0.3073567321039064,
+      "grad_norm": 6.618716716766357,
+      "learning_rate": 2.8031446349643393e-07,
+      "loss": 1.1152,
+      "step": 4650
+    },
+    {
+      "epoch": 0.3073567321039064,
+      "eval_loss": 1.2152043581008911,
+      "eval_runtime": 53.4713,
+      "eval_samples_per_second": 9.37,
+      "eval_steps_per_second": 9.37,
+      "step": 4650
     }
   ],
   "logging_steps": 10,
@@ -3416,7 +3529,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.104694939554611e+17,
+  "total_flos": 3.2041141329494016e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null