Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3da96280e1331c1a0b3fdbb63178b204c63147570c36d2d8caa4e5aaf841261
+oid sha256:b2983eaa2eecccbcd454f2740ac9e8e19a2f60bef1cf698c4e9ac7c1a162484b
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8190e7d36220b664948c8cf1a03bb28340c6615c9554514bbe827b6fc524675a
+oid sha256:f4160d2319501b4e79b606f9849a84434f2ddab140fb5701b3a3e012d6befb81
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d726261824dca226482287c3692aca4308c72033a864ea9dd8b4b643276b09
+oid sha256:749f77c3ba8aa807cee2275da408e206106b0440dd6eff1810df2b0ad7678ed8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12bb23042d4407d3a5038be22a7bc334732a1d0432e530de985398332ddb7de5
+oid sha256:89bf2412fc138a51f4062ab775917d39e54f436132316dc7fbb3694aabb37048
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0380592942237854,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-01/checkpoint-14000",
-  "epoch": 8.875739644970414,
+  "epoch": 9.368836291913215,
   "eval_steps": 1000,
-  "global_step": 18000,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,32 @@
       "eval_samples_per_second": 559.969,
       "eval_steps_per_second": 2.209,
       "step": 18000
+    },
+    {
+      "epoch": 9.122287968441814,
+      "grad_norm": 0.14514634013175964,
+      "learning_rate": 1.8175936883629194e-05,
+      "loss": 0.0198,
+      "step": 18500
+    },
+    {
+      "epoch": 9.368836291913215,
+      "grad_norm": 0.44190242886543274,
+      "learning_rate": 1.8126725838264302e-05,
+      "loss": 0.0192,
+      "step": 19000
+    },
+    {
+      "epoch": 9.368836291913215,
+      "eval_accuracy": 0.9874668707569766,
+      "eval_f1": 0.632078219263574,
+      "eval_loss": 0.039640188217163086,
+      "eval_precision": 0.6977128685588316,
+      "eval_recall": 0.5777304533008822,
+      "eval_runtime": 14.7066,
+      "eval_samples_per_second": 551.452,
+      "eval_steps_per_second": 2.176,
+      "step": 19000
     }
   ],
   "logging_steps": 500,
@@ -498,12 +524,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 407138463972036.0,
+  "total_flos": 429748313255712.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null