Training in progress, step 100, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63489c1e38f1ac5a2629813f26123fa744473881124f9e98887d7060c3c099d6
+oid sha256:28b34625a8715b00a596425b15ee66b124a4a7c3839e8e8697370b2b5307b014
 size 4990951248

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d1646b92d5f7acc41fc74dccc5ebd7e37ff62d6dd42249826fea2808dd90f21
+oid sha256:e102159806ad9af0c0ec6c0199516dcc7b34bd576b8eec9fe119f832253f214a
 size 559197598

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daebfbcaf4226179e95a7a2928839a94f01a317bcb32a0021d250f6a3602bfce
+oid sha256:fa5fe98727f7cf6b7ef710f9d8b2f8806f581b27b46fa2671c2078a23ec08ffa
 size 5640674860

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37ebc224a7a4705cea1613dd8fd1f8f471218f082721f531c7167abec9ee3a5
+oid sha256:d4aa11e1920a65bd6f9d3d7705a39b4eb273d4b1d13425f4d93bdc9a32a38cf4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce78d042223b902aa422256a43e83b469f7892bf3a43f13e3a19d2fa900c9406
+oid sha256:b16a3f4fd0bbb2ef54173b8f8f9b473c05114aa603c01260cd9c7f8be1b6a9da
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f719e5477984d5abea386f4b60be21f4d2ad98970ac0de30ce8a64b3cdb8cb02
+oid sha256:47fb916367dfd73f6e83cfd68c3949b4fc2131be1fd25bfd542ffd71c9e3d87b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ed4133b2ea99a43dbced219876975f15888ea761a0db49a0afa3f636f6ca78
+oid sha256:98bbea1742a7fc36512eb73ae38f6fa9b654a9feabba8b189726de9331137352
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776a540436bd1dedef12a8b7642374faac449931a1c15952fb54741875421490
+oid sha256:898092e0bf0f6dbc7c89ddc78136fe76ce924561e71751216da91be467d8b5d1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.5806451612903225,
+  "epoch": 3.225806451612903,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -103,6 +103,28 @@
       "eval_samples_per_second": 73.94,
       "eval_steps_per_second": 3.103,
       "step": 80
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 32.25,
+      "learning_rate": 0.00019090065350491626,
+      "loss": 2.4592,
+      "step": 90
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 61.25,
+      "learning_rate": 0.0001879473751206489,
+      "loss": 2.3718,
+      "step": 100
+    },
+    {
+      "epoch": 3.225806451612903,
+      "eval_loss": 2.7737066745758057,
+      "eval_runtime": 20.2807,
+      "eval_samples_per_second": 74.011,
+      "eval_steps_per_second": 3.106,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -122,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.236887688885043e+16,
+  "total_flos": 7.791231950965965e+16,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null