Training in progress, step 13500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d970941693f2a588e9760f579c7f92a3993862857386f4ce7a42732003bed9
+oid sha256:38f7ad03559d709a4e2e50b069ded790243b605bd7f371ff573649b04f3b9ec1
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa728c323613f14720350a34b8de9e9bb0f00feb6895e9763f98b41fc90ba66a
+oid sha256:92b31881fd08d1c5e92f4d85e7ad4bea7caf87612bcfd05226d0426ef46f64b4
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6fa31d853fe83023de7f7f07d4ad55cd60c82617211a8926ae6bb50464d9fc
+oid sha256:fa8e3657fd3e577ff4e755452808dc3c4520d43cd58c493adfa9663f21feb734
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8f1b9bc1d96d7439df35e8166ab30771f48f3a8a26970884d1d49063118f39
+oid sha256:cc96f5c8ec054c4dc9f1608ed0c88e89518d2f17c416476f4efe7bf3b829bb03
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0824647843837738,
   "best_model_checkpoint": "./fine-tuned/checkpoint-12500",
-  "epoch": 1.04,
+  "epoch": 1.08,
   "eval_steps": 500,
-  "global_step": 13000,
+  "global_step": 13500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2035,6 +2035,84 @@
       "eval_samples_per_second": 22.724,
       "eval_steps_per_second": 5.681,
       "step": 13000
+    },
+    {
+      "epoch": 1.044,
+      "grad_norm": 0.09841930866241455,
+      "learning_rate": 1.43424e-05,
+      "loss": 0.0534,
+      "step": 13050
+    },
+    {
+      "epoch": 1.048,
+      "grad_norm": 0.1224198266863823,
+      "learning_rate": 1.42824e-05,
+      "loss": 0.0564,
+      "step": 13100
+    },
+    {
+      "epoch": 1.052,
+      "grad_norm": 0.17220191657543182,
+      "learning_rate": 1.42224e-05,
+      "loss": 0.0567,
+      "step": 13150
+    },
+    {
+      "epoch": 1.056,
+      "grad_norm": 0.08674409985542297,
+      "learning_rate": 1.41636e-05,
+      "loss": 0.0508,
+      "step": 13200
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.12293367087841034,
+      "learning_rate": 1.41036e-05,
+      "loss": 0.0541,
+      "step": 13250
+    },
+    {
+      "epoch": 1.064,
+      "grad_norm": 0.12341846525669098,
+      "learning_rate": 1.40436e-05,
+      "loss": 0.055,
+      "step": 13300
+    },
+    {
+      "epoch": 1.068,
+      "grad_norm": 0.10165009647607803,
+      "learning_rate": 1.39836e-05,
+      "loss": 0.0589,
+      "step": 13350
+    },
+    {
+      "epoch": 1.072,
+      "grad_norm": 0.18138067424297333,
+      "learning_rate": 1.39236e-05,
+      "loss": 0.053,
+      "step": 13400
+    },
+    {
+      "epoch": 1.076,
+      "grad_norm": 0.18615098297595978,
+      "learning_rate": 1.3863599999999999e-05,
+      "loss": 0.0558,
+      "step": 13450
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.06511889398097992,
+      "learning_rate": 1.38036e-05,
+      "loss": 0.062,
+      "step": 13500
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.08285626024007797,
+      "eval_runtime": 88.0463,
+      "eval_samples_per_second": 22.715,
+      "eval_steps_per_second": 5.679,
+      "step": 13500
     }
   ],
   "logging_steps": 50,
@@ -2054,7 +2132,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.166581030912e+16,
+  "total_flos": 3.288372609024e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null