Training in progress, step 28000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fbf8423ff110283327b1f8b90f9081b1058c9376cd2711b7771ceec771519e1
+oid sha256:ff193c75cfe266a4454f3b865f678cd0068e31d158d56f3a08c31bd1c8ca8180
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef9caf61392dd46c560c432d5d06b4ae3b7fe098c753ce284032c427faa732e
+oid sha256:058172c34ee10347ff67ff2341a5f4bfdcee6c70e269830728adf925c422cbcb
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e92aea66aa69545e4cc667c6773e4db275b023af14af95463bf526993dcaef01
+oid sha256:0242710dd76fcfc259b7718df92653875f59a11b4f0133d9bd37c3e685163566
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d7857c6094c610d98d2faa905fca5f4d7aec2a9e3d0f066c66f0a11bdc1413e
+oid sha256:117137eaff655ce606b81582da9e0c028be111ad40ac1072d2fad13931816255
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8333333333333335,
+  "epoch": 1.8666666666666667,
   "eval_steps": 500,
-  "global_step": 27500,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1940,6 +1940,41 @@
       "learning_rate": 7.781777777777778e-06,
       "loss": 0.0593,
       "step": 27500
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.24254228174686432,
+      "learning_rate": 7.737333333333335e-06,
+      "loss": 0.057,
+      "step": 27600
+    },
+    {
+      "epoch": 1.8466666666666667,
+      "grad_norm": 0.0748680830001831,
+      "learning_rate": 7.69288888888889e-06,
+      "loss": 0.0574,
+      "step": 27700
+    },
+    {
+      "epoch": 1.8533333333333335,
+      "grad_norm": 0.2756935656070709,
+      "learning_rate": 7.648444444444445e-06,
+      "loss": 0.0592,
+      "step": 27800
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 0.26682248711586,
+      "learning_rate": 7.604e-06,
+      "loss": 0.0607,
+      "step": 27900
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.2434193342924118,
+      "learning_rate": 7.5595555555555565e-06,
+      "loss": 0.056,
+      "step": 28000
     }
   ],
   "logging_steps": 100,
@@ -1959,7 +1994,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.69853679616e+16,
+  "total_flos": 6.820328374272e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null