Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9524abf571f381ab467394332b60f92d8a68f46c1e26127034ed52a5bf5b7c6f
+oid sha256:e57af6d0264134e1a162bcfb3aa14cc30aa29fa31a292f9ff45b9499a1218c3f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f564e11824fd13f47c0e8b598087bcb5bd2c2abcb35bd00154ba446a413a23
+oid sha256:034a233bc1d79601e0eb13ff5bc45f0821be2f8026e4748c83964a8ac7a7afa7
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5652cdeb5ebbadbe7a41c5bdef0e2c456fe9ce93c4c465bbbfd096c7a45e5ee6
+oid sha256:f4902fcfb33d73ecfa5cb7dbd3cfd13500058abf1d6eae05ae197780b6416694
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c676250ec219860d5697bba17ff8c0d4f32ee4dcb91bcc82789e7b28bcb701
+oid sha256:43495fd59fd541eb94253a07f3e011c2581153d25d7fa1816722e70a1a8e7f7f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04325457662343979,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-6000",
-  "epoch": 2.9585798816568047,
+  "best_metric": 0.04127802699804306,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-7000",
+  "epoch": 3.4516765285996054,
   "eval_steps": 1000,
-  "global_step": 6000,
+  "global_step": 7000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -163,6 +163,32 @@
       "eval_samples_per_second": 560.003,
       "eval_steps_per_second": 2.21,
       "step": 6000
+    },
+    {
+      "epoch": 3.2051282051282053,
+      "grad_norm": 0.3562796711921692,
+      "learning_rate": 1.935897435897436e-05,
+      "loss": 0.0412,
+      "step": 6500
+    },
+    {
+      "epoch": 3.4516765285996054,
+      "grad_norm": 0.24857360124588013,
+      "learning_rate": 1.930966469428008e-05,
+      "loss": 0.0384,
+      "step": 7000
+    },
+    {
+      "epoch": 3.4516765285996054,
+      "eval_accuracy": 0.9864563402639001,
+      "eval_f1": 0.5389366013702596,
+      "eval_loss": 0.04127802699804306,
+      "eval_precision": 0.7357396917402187,
+      "eval_recall": 0.425199847735059,
+      "eval_runtime": 14.4965,
+      "eval_samples_per_second": 559.446,
+      "eval_steps_per_second": 2.207,
+      "step": 7000
     }
   ],
   "logging_steps": 500,
@@ -191,7 +217,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 135828564625332.0,
+  "total_flos": 158396435368380.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null