Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a21612915d6048919c6c6fa540383add9560f3e355dabb28be9845e4fba73a80
+oid sha256:041ce8f32ce552119e7b1d4237f62d551c007214b038e2e85e9201a6801f1604
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d3b24a54a28fc1b501395caa28685b2dbe3f72b3754fd34c574c93993e2ab37
+oid sha256:2eccf747ca8c8c8db9575b2956c6dd997a8eb4b5311ef905ec24ee3407e8cf61
 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": 0.046487729996442795,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-5000",
-  "epoch": 2.465483234714004,
+  "best_metric": 0.04352094233036041,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/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": 558.563,
       "eval_steps_per_second": 2.204,
       "step": 5000
+    },
+    {
+      "epoch": 2.712031558185404,
+      "grad_norm": 0.39123860001564026,
+      "learning_rate": 1.9457593688362923e-05,
+      "loss": 0.0456,
+      "step": 5500
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "grad_norm": 0.4525609016418457,
+      "learning_rate": 1.940828402366864e-05,
+      "loss": 0.0441,
+      "step": 6000
+    },
+    {
+      "epoch": 2.9585798816568047,
+      "eval_accuracy": 0.9860793401079978,
+      "eval_f1": 0.48790406673618353,
+      "eval_loss": 0.04352094233036041,
+      "eval_precision": 0.7666721284614124,
+      "eval_recall": 0.3578037776248375,
+      "eval_runtime": 14.4967,
+      "eval_samples_per_second": 559.439,
+      "eval_steps_per_second": 2.207,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -165,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 112700461753656.0,
+  "total_flos": 135256930917768.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null