Training in progress, step 18000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:784619966569654c1096fb81eebce432699a2de0b3c41084eb413002eb3613b2
+oid sha256:25330a42b5c3150f58fd46529cb0e6268cde632c23da0680768e0a745ed4a81f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0163dd19e33027451329a11df232114840545d8c7e740df6d9e0616de5bbfd2
+oid sha256:6ee9909c93f79ad6531d3437f170f468f4fc8bdd7bc22e2eaa681218b152798b
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
+oid sha256:74d726261824dca226482287c3692aca4308c72033a864ea9dd8b4b643276b09
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f812a1b6a357735ef9df3af32728c85d0df9e178f3a70d3bbfd9db194d6d6c
+oid sha256:12bb23042d4407d3a5038be22a7bc334732a1d0432e530de985398332ddb7de5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03650856390595436,
   "best_model_checkpoint": "doc-topic-model_eval-04_train-00/checkpoint-14000",
-  "epoch": 8.382642998027613,
+  "epoch": 8.875739644970414,
   "eval_steps": 1000,
-  "global_step": 17000,
+  "global_step": 18000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -449,6 +449,32 @@
       "eval_samples_per_second": 564.417,
       "eval_steps_per_second": 2.226,
       "step": 17000
+    },
+    {
+      "epoch": 8.629191321499015,
+      "grad_norm": 0.46473428606987,
+      "learning_rate": 1.8274457593688362e-05,
+      "loss": 0.0204,
+      "step": 17500
+    },
+    {
+      "epoch": 8.875739644970414,
+      "grad_norm": 0.5553109049797058,
+      "learning_rate": 1.822524654832347e-05,
+      "loss": 0.0216,
+      "step": 18000
+    },
+    {
+      "epoch": 8.875739644970414,
+      "eval_accuracy": 0.9878001957975776,
+      "eval_f1": 0.632181453163043,
+      "eval_loss": 0.03807205334305763,
+      "eval_precision": 0.7149067722925321,
+      "eval_recall": 0.5666156202143952,
+      "eval_runtime": 14.3955,
+      "eval_samples_per_second": 563.577,
+      "eval_steps_per_second": 2.223,
+      "step": 18000
     }
   ],
   "logging_steps": 500,
@@ -477,7 +503,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 384839566841160.0,
+  "total_flos": 407491394665464.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null