Training in progress, step 15500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05637d9fe00567351aebe30b8907548391539066a69466b08d62fb0de2c8b6a
+oid sha256:47ec1fd68430fdacb80810ecd09adfa63b256edd752390b582d7134186c11fe5
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd2dde3b7d6cb9a958c80e4da86c9ac7e84d7b0aad33d337c26e27372676e0e8
+oid sha256:7dedc049b8b109e2a1e1d8ca3aa0a4db96cc41f55ad87c5be1b4f1d3b32922bb
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac6d446adeddd129c374743386b9fda911e1104accc0a9ad12d81db0a9913ff
+oid sha256:dc7b29b924630649498d282773659d36f4c79fef1453c3983d39d7e7e53066c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e468fb4a523a6bf7dace3eac71fcc8bc1ed6b95078548573228e864e9505bcd
+oid sha256:0adcdf1185fa7d1b89a354568f52beda1398968ea15296ac3bc948fc9b42fcfd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.08158940076828003,
   "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 2.4,
+  "epoch": 2.48,
   "eval_steps": 500,
-  "global_step": 15000,
+  "global_step": 15500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2347,6 +2347,84 @@
       "eval_samples_per_second": 17.145,
       "eval_steps_per_second": 2.143,
       "step": 15000
+    },
+    {
+      "epoch": 2.408,
+      "grad_norm": 7706.4375,
+      "learning_rate": 5.92e-06,
+      "loss": 0.0513,
+      "step": 15050
+    },
+    {
+      "epoch": 2.416,
+      "grad_norm": 6188.396484375,
+      "learning_rate": 5.84e-06,
+      "loss": 0.0511,
+      "step": 15100
+    },
+    {
+      "epoch": 2.424,
+      "grad_norm": 6621.79345703125,
+      "learning_rate": 5.76e-06,
+      "loss": 0.0506,
+      "step": 15150
+    },
+    {
+      "epoch": 2.432,
+      "grad_norm": 5284.65185546875,
+      "learning_rate": 5.68e-06,
+      "loss": 0.0486,
+      "step": 15200
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 6653.84716796875,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.053,
+      "step": 15250
+    },
+    {
+      "epoch": 2.448,
+      "grad_norm": 6338.93505859375,
+      "learning_rate": 5.52e-06,
+      "loss": 0.0517,
+      "step": 15300
+    },
+    {
+      "epoch": 2.456,
+      "grad_norm": 6020.87548828125,
+      "learning_rate": 5.4400000000000004e-06,
+      "loss": 0.0524,
+      "step": 15350
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 7275.64697265625,
+      "learning_rate": 5.36e-06,
+      "loss": 0.0516,
+      "step": 15400
+    },
+    {
+      "epoch": 2.472,
+      "grad_norm": 5086.87744140625,
+      "learning_rate": 5.279999999999999e-06,
+      "loss": 0.0514,
+      "step": 15450
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 4989.05078125,
+      "learning_rate": 5.2e-06,
+      "loss": 0.0526,
+      "step": 15500
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 0.08169461041688919,
+      "eval_runtime": 116.7302,
+      "eval_samples_per_second": 17.134,
+      "eval_steps_per_second": 2.142,
+      "step": 15500
     }
   ],
   "logging_steps": 50,
@@ -2366,7 +2444,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.30749468672e+16,
+  "total_flos": 7.551077842944e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null