Training in progress, step 8500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43ee6984f5f990cd4d1d7d439666b7dfa7b56da1d97ae91a2c6727d6281cb2d
+oid sha256:9d940b624e42af265966f792f158b5e6dff6cf498a4c59d70a1629ae2fdc2efc
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f67eef48f1db3ec75565c0e239b37d2a1a24b92d26f253f611940b1cf185dbb
+oid sha256:8a2bec32040a69e58023b5509b0fb90efe9794b8b9079e790fb6687d3ff55f17
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91eae2fa3fc02ee15efef1884ec4e560ef910ecd5d82acb8671a8d4707b80a43
+oid sha256:08998c919fed10f9ef4173715a99abc07523cdf2197bb7756b598ec6ecad7017
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6a8aa79fcfebce03524e9b1b6b5ceec390e3bb9a2a198149bb646d26309c9b
+oid sha256:1a2d7ef4474f599b4e657eaa32ef5df2560c025d5712ce31e544f317cb28ad99
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5333333333333333,
+  "epoch": 0.5666666666666667,
   "eval_steps": 500,
-  "global_step": 8000,
+  "global_step": 8500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -567,6 +567,41 @@
       "learning_rate": 1.644577777777778e-05,
       "loss": 0.0699,
       "step": 8000
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.03966674581170082,
+      "learning_rate": 1.6401333333333335e-05,
+      "loss": 0.0634,
+      "step": 8100
+    },
+    {
+      "epoch": 0.5466666666666666,
+      "grad_norm": 0.25476112961769104,
+      "learning_rate": 1.635688888888889e-05,
+      "loss": 0.0725,
+      "step": 8200
+    },
+    {
+      "epoch": 0.5533333333333333,
+      "grad_norm": 0.25321516394615173,
+      "learning_rate": 1.6312444444444446e-05,
+      "loss": 0.0683,
+      "step": 8300
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.25231412053108215,
+      "learning_rate": 1.6268e-05,
+      "loss": 0.0735,
+      "step": 8400
+    },
+    {
+      "epoch": 0.5666666666666667,
+      "grad_norm": 0.08408234268426895,
+      "learning_rate": 1.6223555555555556e-05,
+      "loss": 0.0677,
+      "step": 8500
     }
   ],
   "logging_steps": 100,
@@ -586,7 +621,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.948665249792e+16,
+  "total_flos": 2.070456827904e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null