Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da2692b4ba456f34b0c29a71cad1be3d97e3e15b65ed142d15786c25c3d76062
+oid sha256:b178340e94fc581b56f8d6a4a9d6e3488646ae262c3d40b83cbe4d9dde2db2ce
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a832d3e3f0a95cdb11cb5a0b7bc2a4cb4817b809240fda233afd7addde5bb1
+oid sha256:f2025c71fddf8cd2b16a161e620227148461808b1044c26e6f9fd2ec316719ac
 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": 0.049108367413282394,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-4000",
-  "epoch": 1.972386587771203,
+  "best_metric": 0.045239612460136414,
+  "best_model_checkpoint": "doc-topic-model_eval-00_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": 575.194,
       "eval_steps_per_second": 2.27,
       "step": 4000
+    },
+    {
+      "epoch": 2.2189349112426036,
+      "grad_norm": 0.33267995715141296,
+      "learning_rate": 1.9556213017751483e-05,
+      "loss": 0.0474,
+      "step": 4500
+    },
+    {
+      "epoch": 2.465483234714004,
+      "grad_norm": 0.3178996443748474,
+      "learning_rate": 1.95069033530572e-05,
+      "loss": 0.0467,
+      "step": 5000
+    },
+    {
+      "epoch": 2.465483234714004,
+      "eval_accuracy": 0.9857207647717449,
+      "eval_f1": 0.45265388167544957,
+      "eval_loss": 0.045239612460136414,
+      "eval_precision": 0.7816135084427768,
+      "eval_recall": 0.31857459662001986,
+      "eval_runtime": 14.2568,
+      "eval_samples_per_second": 568.853,
+      "eval_steps_per_second": 2.245,
+      "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