Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e9b2d6969dd83bc1c43996563873904653a70fa8a0de29bcd1b7f7ddd8775f7
+oid sha256:a21612915d6048919c6c6fa540383add9560f3e355dabb28be9845e4fba73a80
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d78afae041207d004fc4f244d7c3f8f3af6e6fe32125d24890dd0317f62e40
+oid sha256:4d3b24a54a28fc1b501395caa28685b2dbe3f72b3754fd34c574c93993e2ab37
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8a5b7fde4c37eeccbe4aca8abd49518b2e855ca1720563c5af4866d40338cb0
+oid sha256:de88be6318b528394c4873328ca35b0d7d30d60396593a873b67c289e2c805b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4834ce2586dc426079f90c930b0e0d6ec21ad9d8a256946c64bb3fc73152baa
+oid sha256:3c593d69b250076041f56e5e5b5b7926da7e9d2966997964c90a264036cb10f5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04972199350595474,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-4000",
-  "epoch": 1.972386587771203,
+  "best_metric": 0.046487729996442795,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-5000",
+  "epoch": 2.465483234714004,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,32 @@
       "eval_samples_per_second": 553.191,
       "eval_steps_per_second": 2.183,
       "step": 4000
+    },
+    {
+      "epoch": 2.2189349112426036,
+      "grad_norm": 0.39391544461250305,
+      "learning_rate": 1.9556213017751483e-05,
+      "loss": 0.0488,
+      "step": 4500
+    },
+    {
+      "epoch": 2.465483234714004,
+      "grad_norm": 0.2698710858821869,
+      "learning_rate": 1.95069033530572e-05,
+      "loss": 0.0468,
+      "step": 5000
+    },
+    {
+      "epoch": 2.465483234714004,
+      "eval_accuracy": 0.9852672307496066,
+      "eval_f1": 0.42163244867300953,
+      "eval_loss": 0.046487729996442795,
+      "eval_precision": 0.7738970588235294,
+      "eval_recall": 0.28974535443909155,
+      "eval_runtime": 14.5194,
+      "eval_samples_per_second": 558.563,
+      "eval_steps_per_second": 2.204,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -139,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 90160058450772.0,
+  "total_flos": 112700461753656.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null