Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b178340e94fc581b56f8d6a4a9d6e3488646ae262c3d40b83cbe4d9dde2db2ce
+oid sha256:f061222cf016032d90e8fff66d174db217bc485e7486e6f11bad338f411ba59f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2025c71fddf8cd2b16a161e620227148461808b1044c26e6f9fd2ec316719ac
+oid sha256:c6668452f88a8142f6a2e30ffc83d3bbc2a43dbac3505d777877a3777f97e420
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de88be6318b528394c4873328ca35b0d7d30d60396593a873b67c289e2c805b1
+oid sha256:5652cdeb5ebbadbe7a41c5bdef0e2c456fe9ce93c4c465bbbfd096c7a45e5ee6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c593d69b250076041f56e5e5b5b7926da7e9d2966997964c90a264036cb10f5
+oid sha256:40c676250ec219860d5697bba17ff8c0d4f32ee4dcb91bcc82789e7b28bcb701
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.045239612460136414,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-5000",
-  "epoch": 2.465483234714004,
+  "best_metric": 0.04268515482544899,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-6000",
+  "epoch": 2.9585798816568047,
   "eval_steps": 1000,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,6 +137,32 @@
       "eval_samples_per_second": 568.853,
       "eval_steps_per_second": 2.245,
       "step": 5000
+    },
+    {
+      "epoch": 2.712031558185404,
+      "grad_norm": 0.41016682982444763,
+      "learning_rate": 1.9457593688362923e-05,
+      "loss": 0.0453,
+      "step": 5500
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 0.30701619386672974,
+      "learning_rate": 1.940828402366864e-05,
+      "loss": 0.044,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "eval_accuracy": 0.986354295108919,
+      "eval_f1": 0.5022231413504291,
+      "eval_loss": 0.04268515482544899,
+      "eval_precision": 0.7752593774940144,
+      "eval_recall": 0.3714154622619867,
+      "eval_runtime": 14.3323,
+      "eval_samples_per_second": 565.856,
+      "eval_steps_per_second": 2.233,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -165,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 112902580652976.0,
+  "total_flos": 135494291061072.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null