Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e29a49901521a90229a6d6bd1f78357ef074d640e55e549b59758c52f941978a
+oid sha256:acb892f83419d4e38d0bb3ed94fce2202d1437ceb7d80d32d3772092b10841f0
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d73d12e9b5758fa83605c54e63cc7843dfb4d124a6ee579b82b9c67b08dc40
+oid sha256:20c5f6d2dc851673379f59bdb3ee7e85f545962c8f3050698e72b9dbba1a65d8
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749f77c3ba8aa807cee2275da408e206106b0440dd6eff1810df2b0ad7678ed8
+oid sha256:155ad12ff52df5f6bd601bf6db8835e792082e2ea71e126fb23e84367e27ff3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89bf2412fc138a51f4062ab775917d39e54f436132316dc7fbb3694aabb37048
+oid sha256:269db43e729ed0472aa01beafe0cac4ffe78f8c5279a6ce5b3a8d14f0a831d61
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037335559725761414,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-15000",
-  "epoch": 9.368836291913215,
+  "epoch": 9.861932938856016,
   "eval_steps": 1000,
-  "global_step": 19000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -501,6 +501,32 @@
       "eval_samples_per_second": 565.571,
       "eval_steps_per_second": 2.232,
       "step": 19000
+    },
+    {
+      "epoch": 9.615384615384615,
+      "grad_norm": 0.3235713541507721,
+      "learning_rate": 1.8077416173570022e-05,
+      "loss": 0.0183,
+      "step": 19500
+    },
+    {
+      "epoch": 9.861932938856016,
+      "grad_norm": 0.3706725239753723,
+      "learning_rate": 1.802810650887574e-05,
+      "loss": 0.0182,
+      "step": 20000
+    },
+    {
+      "epoch": 9.861932938856016,
+      "eval_accuracy": 0.9877574159899088,
+      "eval_f1": 0.6321124361158432,
+      "eval_loss": 0.03977630287408829,
+      "eval_precision": 0.7133519177160434,
+      "eval_recall": 0.5674848971476638,
+      "eval_runtime": 14.1791,
+      "eval_samples_per_second": 571.968,
+      "eval_steps_per_second": 2.257,
+      "step": 20000
     }
   ],
   "logging_steps": 500,
@@ -524,12 +550,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 429748313255712.0,
+  "total_flos": 452312037970056.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null