Training in progress, step 160, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce2f1aa30d5eaf619a3c3e017ed7754121c2ff6be4a774b7691ecc396037c065
+oid sha256:057b49db93b4bb11e49863668fa73539c65d76cca34601fff825c1691bb64851
 size 2471645608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6013018172e8e90f92a7185ecf6723b6d10af651282732a0570dc64f8a2bf781
+oid sha256:d304751a2ea1c94cc1b9b0de681233ea14fc47a301587cfdabe4ca3c3d0e44bc
 size 2510806010

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a0836ed1d1df6a39c52676c50033899f159b2a086f39809f42b2abd08f98f0
+oid sha256:56b323eece943c8be03268f2f2cd0f5781052da6f4d6e81974e7dc0391e6f9b0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72d2f8d4dea78d8ee147023f016cd12fb983dd12869b55735aa35f72144a70de
+oid sha256:e8a5396b6ce82a1fa517dfb220ab4ae7fd088b5d9659632b81104386db9d3bac
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fda2e4ac7ffb91a3ce7e64ea0fe5ed42405c8bcbef18e553f63be66a77fd54
+oid sha256:507e713485c774580f6a9da657c78542ed7cbfe40136e2096ef127927ec8b96e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c98375c9f86a164b7cbbec77ff4614c1313758d8ac8dedbf96faa1321c4d161
+oid sha256:ac3c203718bd461046b02f6c1bbd4eca077b667406a41352c7b69bf3764ca88c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a58dce7b667be31a2849f694e1ec67799fde1d5a6e26353e473a211f9c6e2b03
+oid sha256:91ab173e3ec81f1fcc90a5bec767634b3731350aacc0be314a1243781b9ad361
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.235294117647058,
+  "epoch": 9.411764705882353,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -169,6 +169,28 @@
       "eval_samples_per_second": 105.726,
       "eval_steps_per_second": 2.465,
       "step": 140
+    },
+    {
+      "epoch": 8.823529411764707,
+      "grad_norm": 0.76171875,
+      "learning_rate": 0.00014759473930370736,
+      "loss": 0.0647,
+      "step": 150
+    },
+    {
+      "epoch": 9.411764705882353,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.00014016954246529696,
+      "loss": 0.0456,
+      "step": 160
+    },
+    {
+      "epoch": 9.411764705882353,
+      "eval_loss": 3.7919914722442627,
+      "eval_runtime": 15.5596,
+      "eval_samples_per_second": 96.468,
+      "eval_steps_per_second": 2.249,
+      "step": 160
     }
   ],
   "logging_steps": 10,
@@ -188,7 +210,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.301566917142118e+16,
+  "total_flos": 8.344306217648128e+16,
   "train_batch_size": 11,
   "trial_name": null,
   "trial_params": null