Training in progress, step 28500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff193c75cfe266a4454f3b865f678cd0068e31d158d56f3a08c31bd1c8ca8180
+oid sha256:3614617ee76c86000db29cd744353eb118d9a3d06e5a97f4af361b3577a0b872
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058172c34ee10347ff67ff2341a5f4bfdcee6c70e269830728adf925c422cbcb
+oid sha256:e5ba13f67cae6dd4ea0abf5c768c7bd8aaa350d6c17a47580822772f8d79c646
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0242710dd76fcfc259b7718df92653875f59a11b4f0133d9bd37c3e685163566
+oid sha256:606d09e46c381a6ca79c1c2761e1f43da7a02f07449ea8dc08c4fd55302f6057
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117137eaff655ce606b81582da9e0c028be111ad40ac1072d2fad13931816255
+oid sha256:cf940af0b3fe4a79522e2cb3cee03ca9bdc7bb9e1119203316379171ea473573
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8666666666666667,
+  "epoch": 1.9,
   "eval_steps": 500,
-  "global_step": 28000,
+  "global_step": 28500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1975,6 +1975,41 @@
       "learning_rate": 7.5595555555555565e-06,
       "loss": 0.056,
       "step": 28000
+    },
+    {
+      "epoch": 1.8733333333333333,
+      "grad_norm": 0.38631588220596313,
+      "learning_rate": 7.515111111111112e-06,
+      "loss": 0.0554,
+      "step": 28100
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.3035646677017212,
+      "learning_rate": 7.470666666666667e-06,
+      "loss": 0.0554,
+      "step": 28200
+    },
+    {
+      "epoch": 1.8866666666666667,
+      "grad_norm": 0.2283605933189392,
+      "learning_rate": 7.426222222222222e-06,
+      "loss": 0.0584,
+      "step": 28300
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 0.10160692036151886,
+      "learning_rate": 7.381777777777779e-06,
+      "loss": 0.0538,
+      "step": 28400
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.704264223575592,
+      "learning_rate": 7.337777777777778e-06,
+      "loss": 0.0541,
+      "step": 28500
     }
   ],
   "logging_steps": 100,
@@ -1994,7 +2029,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.820328374272e+16,
+  "total_flos": 6.942119952384e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null