Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2983eaa2eecccbcd454f2740ac9e8e19a2f60bef1cf698c4e9ac7c1a162484b
+oid sha256:1cb8908b36d53267daa6b1c19c0f79889b634a80860d824372a3056b7d871286
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4160d2319501b4e79b606f9849a84434f2ddab140fb5701b3a3e012d6befb81
+oid sha256:2e28f021c73463e4442bd785612d072912429af19628c61b7f5b80b31f266ad2
 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": 0.03719973564147949,
   "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-16000",
-  "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": 562.509,
       "eval_steps_per_second": 2.219,
       "step": 19000
+    },
+    {
+      "epoch": 9.615384615384615,
+      "grad_norm": 0.3838333785533905,
+      "learning_rate": 1.8077416173570022e-05,
+      "loss": 0.0193,
+      "step": 19500
+    },
+    {
+      "epoch": 9.861932938856016,
+      "grad_norm": 0.36484745144844055,
+      "learning_rate": 1.802810650887574e-05,
+      "loss": 0.0189,
+      "step": 20000
+    },
+    {
+      "epoch": 9.861932938856016,
+      "eval_accuracy": 0.9877888616396843,
+      "eval_f1": 0.6364978280123149,
+      "eval_loss": 0.039096660912036896,
+      "eval_precision": 0.708478077175852,
+      "eval_recall": 0.5777947932618683,
+      "eval_runtime": 14.4016,
+      "eval_samples_per_second": 563.339,
+      "eval_steps_per_second": 2.222,
+      "step": 20000
     }
   ],
   "logging_steps": 500,
@@ -529,7 +555,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 429748313255712.0,
+  "total_flos": 452312037970056.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null