Training in progress, step 180, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057b49db93b4bb11e49863668fa73539c65d76cca34601fff825c1691bb64851
+oid sha256:2c2c0a790064775147df67e3ddcfd62e11584f5aea3f1a9de0417622cbf9c7d4
 size 2471645608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d304751a2ea1c94cc1b9b0de681233ea14fc47a301587cfdabe4ca3c3d0e44bc
+oid sha256:06e4829f9e6629891612b81adb97f878de5fd94c2d2fe978b940f5f80ac0f305
 size 2510806010

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b323eece943c8be03268f2f2cd0f5781052da6f4d6e81974e7dc0391e6f9b0
+oid sha256:5de519c5e2e0ec73ae4a10a32ec71c2d0d5d3982d1fbb16434177a93460b8139
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a5396b6ce82a1fa517dfb220ab4ae7fd088b5d9659632b81104386db9d3bac
+oid sha256:e120a86fc85c4349ce6a6d226cf9080af7941a4f32f9239b536f491d778e55d1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:507e713485c774580f6a9da657c78542ed7cbfe40136e2096ef127927ec8b96e
+oid sha256:420919d56d937c6944ec2c4a3a5402e03840612d53e7914b441877be496558d6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac3c203718bd461046b02f6c1bbd4eca077b667406a41352c7b69bf3764ca88c
+oid sha256:2fbf96f9883e64cb2ab53f35f353ba99bb51455ec52fb6e4f630fe95a589598d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ab173e3ec81f1fcc90a5bec767634b3731350aacc0be314a1243781b9ad361
+oid sha256:9f30eaafe84a25fe4a9dc5723bc034c2757e284325f5eef16f6d75d1c5a09576
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.411764705882353,
+  "epoch": 10.588235294117647,
   "eval_steps": 20,
-  "global_step": 160,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -191,6 +191,28 @@
       "eval_samples_per_second": 96.468,
       "eval_steps_per_second": 2.249,
       "step": 160
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.62109375,
+      "learning_rate": 0.00013246994692046836,
+      "loss": 0.0373,
+      "step": 170
+    },
+    {
+      "epoch": 10.588235294117647,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00012454854871407994,
+      "loss": 0.0152,
+      "step": 180
+    },
+    {
+      "epoch": 10.588235294117647,
+      "eval_loss": 3.9090092182159424,
+      "eval_runtime": 15.4377,
+      "eval_samples_per_second": 97.23,
+      "eval_steps_per_second": 2.267,
+      "step": 180
     }
   ],
   "logging_steps": 10,
@@ -210,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.344306217648128e+16,
+  "total_flos": 9.389437170692915e+16,
   "train_batch_size": 11,
   "trial_name": null,
   "trial_params": null