Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a1974192fa534f3f849c9fd4c4a358e6b21217c725ad71f685da803acd57129
+oid sha256:63eb21b9e1cf0bf907284263d4a9338422b7e189e5c909d860a7e71d14a4c2ae
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5e885f911241982e5609dc83fd16dcd61e80867abd847a997c940f9b07ea85
+oid sha256:21a4128037147f3652b538c047a600b904144cfd95ce967abe8a3e0c26a0b50c
 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": 0.05005401372909546,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-4000",
-  "epoch": 1.972386587771203,
+  "best_metric": 0.04508376494050026,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/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": 568.374,
       "eval_steps_per_second": 2.243,
       "step": 4000
+    },
+    {
+      "epoch": 2.2189349112426036,
+      "grad_norm": 0.3222791850566864,
+      "learning_rate": 1.9556213017751483e-05,
+      "loss": 0.0476,
+      "step": 4500
+    },
+    {
+      "epoch": 2.465483234714004,
+      "grad_norm": 0.3560543656349182,
+      "learning_rate": 1.95069033530572e-05,
+      "loss": 0.0466,
+      "step": 5000
+    },
+    {
+      "epoch": 2.465483234714004,
+      "eval_accuracy": 0.9856697421942543,
+      "eval_f1": 0.48531432934588953,
+      "eval_loss": 0.04508376494050026,
+      "eval_precision": 0.7322580645161291,
+      "eval_recall": 0.3629234868671488,
+      "eval_runtime": 14.2501,
+      "eval_samples_per_second": 569.119,
+      "eval_steps_per_second": 2.246,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -139,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 90391717804608.0,
+  "total_flos": 112902580652976.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null