Training in progress, step 7000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c21d45dfcbba804b8703933416297c5591a3551d95994edfcfc887ac19fb5b
+oid sha256:6696d19dd1af5a4b5fe88fb64bbde2651a949b0a6a6c1dcf12734e21979d1f34
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e9c5d52513c81db9d558817efb54e53a680724298245e4738597929d9a01f5
+oid sha256:ca258020d8ee8dd24ca225723f357c7875efabaf0ff2b1cd7edf5145bac62883
 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:ea016b60dfe8a3c96c631692907950e51071b8de5bfe114266e09bd559511423
+oid sha256:cca0968ced7c542658d18cbe2b8492512ae721a8edd083db895fdfc19d743c20
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.042579714208841324,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-6000",
-  "epoch": 2.957121734844751,
+  "best_metric": 0.04068835824728012,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-7000",
+  "epoch": 3.449975357318876,
   "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": 572.053,
       "eval_steps_per_second": 2.257,
       "step": 6000
+    },
+    {
+      "epoch": 3.2035485460818136,
+      "grad_norm": 0.4312683939933777,
+      "learning_rate": 1.9359290290783638e-05,
+      "loss": 0.0399,
+      "step": 6500
+    },
+    {
+      "epoch": 3.449975357318876,
+      "grad_norm": 0.46780943870544434,
+      "learning_rate": 1.9310004928536227e-05,
+      "loss": 0.0389,
+      "step": 7000
+    },
+    {
+      "epoch": 3.449975357318876,
+      "eval_accuracy": 0.9865073628413906,
+      "eval_f1": 0.5336533751347114,
+      "eval_loss": 0.04068835824728012,
+      "eval_precision": 0.7496559317368566,
+      "eval_recall": 0.4142835412229997,
+      "eval_runtime": 14.2131,
+      "eval_samples_per_second": 570.6,
+      "eval_steps_per_second": 2.251,
+      "step": 7000
     }
   ],
   "logging_steps": 500,
@@ -191,7 +217,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 136021614086862.0,
+  "total_flos": 158618507030838.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null