Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a69f4ecb5de3c6ad5332ebcbf40332459649ad91d55d650d1ff6377a78d0291
+oid sha256:db3186390ad438c7b0494839975b0c84b9377f4176e8af7e88f305ecb73994c4
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9439a2bd16b9e038a0d7e9f8dfecd38dec4f5b4b1255895c231167396723572f
+oid sha256:2837b23275b182c3f3a9afc2f06ee97f7bfc3bcf6b533ea744dda23ad6eaaeb6
 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": 0.04996015876531601,
-  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-4000",
-  "epoch": 1.972386587771203,
+  "best_metric": 0.04658225178718567,
+  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/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": 563.78,
       "eval_steps_per_second": 2.224,
       "step": 4000
+    },
+    {
+      "epoch": 2.2189349112426036,
+      "grad_norm": 0.24940212070941925,
+      "learning_rate": 1.9556213017751483e-05,
+      "loss": 0.0499,
+      "step": 4500
+    },
+    {
+      "epoch": 2.465483234714004,
+      "grad_norm": 0.40094295144081116,
+      "learning_rate": 1.95069033530572e-05,
+      "loss": 0.0478,
+      "step": 5000
+    },
+    {
+      "epoch": 2.465483234714004,
+      "eval_accuracy": 0.9853151816794672,
+      "eval_f1": 0.4339468079296598,
+      "eval_loss": 0.04658225178718567,
+      "eval_precision": 0.7566177870881737,
+      "eval_recall": 0.30421133231240427,
+      "eval_runtime": 14.4801,
+      "eval_samples_per_second": 560.288,
+      "eval_steps_per_second": 2.21,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -139,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 90589690675224.0,
+  "total_flos": 113179328068968.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null