Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f30b65fafc5113397b5aa493d99d9c08095596017bd3a37b950f14e2a78d413
+oid sha256:d06f2712c41b8a531592806eabe6259f22061ace0b4c4cd7e57555cff51d1725
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a392ac812c5aac34281634eb9887c7b02c19fc92ae87930e902e159863653b10
+oid sha256:f1aee718b7dc819eef73e6ab21fb4cb59467343a40233e7daf99abf11c6ceaee
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4902fcfb33d73ecfa5cb7dbd3cfd13500058abf1d6eae05ae197780b6416694
+oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43495fd59fd541eb94253a07f3e011c2581153d25d7fa1816722e70a1a8e7f7f
+oid sha256:173f4a2433232f77939b4d77264600e6f898939c018c908fe5f061eb1c76ed9b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04075852409005165,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-7000",
-  "epoch": 3.4516765285996054,
+  "best_metric": 0.03952678292989731,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-8000",
+  "epoch": 3.9447731755424065,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,32 @@
       "eval_samples_per_second": 570.09,
       "eval_steps_per_second": 2.249,
       "step": 7000
+    },
+    {
+      "epoch": 3.698224852071006,
+      "grad_norm": 0.45788881182670593,
+      "learning_rate": 1.92603550295858e-05,
+      "loss": 0.0381,
+      "step": 7500
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "grad_norm": 0.3994843363761902,
+      "learning_rate": 1.921104536489152e-05,
+      "loss": 0.0378,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "eval_accuracy": 0.9867312952648214,
+      "eval_f1": 0.5526994744386049,
+      "eval_loss": 0.03952678292989731,
+      "eval_precision": 0.7365338087355151,
+      "eval_recall": 0.4423032805689378,
+      "eval_runtime": 14.2307,
+      "eval_samples_per_second": 569.894,
+      "eval_steps_per_second": 2.249,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -217,7 +243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 157815991349820.0,
+  "total_flos": 180338255777124.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null