Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e72144d54bcc5be126ed76a60d0546279dee7f1a463d94e91f15bf80a5d86ec5
+oid sha256:75c21d45dfcbba804b8703933416297c5591a3551d95994edfcfc887ac19fb5b
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba57df416a78aadf086b9109b9f1564080f49bfa03a033040dba3a5234da3ab0
+oid sha256:93e9c5d52513c81db9d558817efb54e53a680724298245e4738597929d9a01f5
 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:ac39890beed6f47b99e7a6478c8d7f5d405911830cdb68c8f08f50e9a97932b0
+oid sha256:ea016b60dfe8a3c96c631692907950e51071b8de5bfe114266e09bd559511423
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.045466337352991104,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-5000",
-  "epoch": 2.464268112370626,
+  "best_metric": 0.042579714208841324,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-6000",
+  "epoch": 2.957121734844751,
   "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": 572.243,
       "eval_steps_per_second": 2.258,
       "step": 5000
+    },
+    {
+      "epoch": 2.7106949236076883,
+      "grad_norm": 0.35379377007484436,
+      "learning_rate": 1.9457861015278464e-05,
+      "loss": 0.0442,
+      "step": 5500
+    },
+    {
+      "epoch": 2.957121734844751,
+      "grad_norm": 0.3872750997543335,
+      "learning_rate": 1.9408575653031053e-05,
+      "loss": 0.0436,
+      "step": 6000
+    },
+    {
+      "epoch": 2.957121734844751,
+      "eval_accuracy": 0.9860694190512636,
+      "eval_f1": 0.5016478223394008,
+      "eval_loss": 0.042579714208841324,
+      "eval_precision": 0.7523954372623575,
+      "eval_recall": 0.3762549437176757,
+      "eval_runtime": 14.177,
+      "eval_samples_per_second": 572.053,
+      "eval_steps_per_second": 2.257,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -165,7 +191,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 113366676741030.0,
+  "total_flos": 136021614086862.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null