Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1c8f434ea18d3b22fd15254827178bbe3ed96c6503f495dffba91cdd8f6000a
+oid sha256:5c7c809bfb9e0c09a991cbc751afbd7d153af1ea8be3d21c60d821e480d58397
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bfe40ca2e2f7716947536cdec78ff3399a93f458d287f2974b9aa308cf568d4
+oid sha256:54c71b342dcaf811b4743acd66cc3b8dab74d01a77947a9e074165554a191a3f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7ddd132ae0c177184ed8a4f1a9ac2f3b51a04d85a111aa5717d5124f81bcd9e
+oid sha256:4c6930021eee2ce84b130095d62c41e90293ccc2830acaf7c168280128912a1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de1891a9bbbac025ea7d704b1888c3c146080478050b5c9e6f8305f0eea645f
+oid sha256:abe099e1b5028bec45c9b921f52c62bf9191fdd92a0c19da1f44a14388797be1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.035947080701589584,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-19000",
-  "epoch": 9.368836291913215,
+  "best_metric": 0.03578707203269005,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-20000",
+  "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": 308.608,
       "eval_steps_per_second": 19.293,
       "step": 19000
+    },
+    {
+      "epoch": 9.615384615384615,
+      "grad_norm": 0.4185117185115814,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 0.0233,
+      "step": 19500
+    },
+    {
+      "epoch": 9.861932938856016,
+      "grad_norm": 0.34625717997550964,
+      "learning_rate": 2.7613412228796843e-07,
+      "loss": 0.0229,
+      "step": 20000
+    },
+    {
+      "epoch": 9.861932938856016,
+      "eval_accuracy": 0.987977096531882,
+      "eval_f1": 0.6214467401490472,
+      "eval_loss": 0.03578707203269005,
+      "eval_precision": 0.7461423060437206,
+      "eval_recall": 0.5324615737554484,
+      "eval_runtime": 27.6359,
+      "eval_samples_per_second": 293.458,
+      "eval_steps_per_second": 18.346,
+      "step": 20000
     }
   ],
   "logging_steps": 500,
@@ -520,7 +546,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 429748313255712.0,
+  "total_flos": 452312037970056.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null