Training in progress, step 3709, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f273e86ecaf143a463e010f3c1027db2e47f7d3526532cfba4f77145ee79f040
+oid sha256:c2faae301c51bf9afe27a5efb035500ac0f1f3e8aba96489672b75ac92bd21a3
 size 3132668808

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49bacab0523adf25453aa4ba8d85ba8b23d85c7604b730d44f0edc6a3f5fa162
+oid sha256:136f0df911cbcdc8a57afb16b156978365648865f387a2f4b397f9ce1779d141
 size 6265681949

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad667a164a35e2820f486626bc7f4c131332a14307c3cfc69a9c34f68e2eeae8
+oid sha256:3fb09fa8a03f019938357b8e6dd70c665a6f839ceffe9c4f41bfe23cb0ea6e77
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2176708524de952d0af3e052980f65d3f09eb5ddcc79198ab72c8c435ec6630d
+oid sha256:25d19e1a77f01614e1751ba7d46a821b26e1f95dee82257ac6ee387fe4714209
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 3500,
   "best_metric": 0.021653667092323303,
   "best_model_checkpoint": "gs://text-language-finetuning-vertex/outputs/lim_gec/full/full/checkpoint-3500",
-  "epoch": 0.9438732513062532,
+  "epoch": 1.0,
   "eval_steps": 500,
-  "global_step": 3500,
+  "global_step": 3709,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -309,6 +309,20 @@
       "eval_samples_per_second": 127.579,
       "eval_steps_per_second": 3.989,
       "step": 3500
+    },
+    {
+      "epoch": 0.9708410584864319,
+      "grad_norm": 0.02992485836148262,
+      "learning_rate": 1.0283577438454347e-05,
+      "loss": 0.20760541915893554,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9978088656666105,
+      "grad_norm": 0.05102963000535965,
+      "learning_rate": 9.348706762231224e-07,
+      "loss": 0.19801679611206055,
+      "step": 3700
     }
   ],
   "logging_steps": 100,
@@ -323,12 +337,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.878542338654208e+17,
+  "total_flos": 9.407808395601961e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null