Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29bb3f7942c2eb3b874802b3ea92fe85d018443c8952c3f3662a252d74b77cff
+oid sha256:cd8e2da575487f0f514d3ac641b54188b83b65293d17518c847ecd0b5e591ca1
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9ef267bf72eef7066eb6f544c4613a25ba21619a89a12b8ad0beb9b5587024d
+oid sha256:86fe37d6452dbda6b773629c24131b2d3eda42a3d4aa1cf384885d4fe03ef892
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
+oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28e35c5a0c1eb4f922a2e3785d5afca45020e4d0fc6713cc20aea6ed31f143e1
+oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.037975214421749115,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-10000",
-  "epoch": 4.930966469428008,
+  "best_metric": 0.03708931431174278,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-11000",
+  "epoch": 5.424063116370808,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,32 @@
       "eval_samples_per_second": 573.711,
       "eval_steps_per_second": 2.264,
       "step": 10000
+    },
+    {
+      "epoch": 5.177514792899408,
+      "grad_norm": 0.2832840085029602,
+      "learning_rate": 1.896459566074951e-05,
+      "loss": 0.0303,
+      "step": 10500
+    },
+    {
+      "epoch": 5.424063116370808,
+      "grad_norm": 0.43404069542884827,
+      "learning_rate": 1.891528599605523e-05,
+      "loss": 0.0301,
+      "step": 11000
+    },
+    {
+      "epoch": 5.424063116370808,
+      "eval_accuracy": 0.9875660813243193,
+      "eval_f1": 0.6041958041958042,
+      "eval_loss": 0.03708931431174278,
+      "eval_precision": 0.7367957746478874,
+      "eval_recall": 0.5120440467997247,
+      "eval_runtime": 14.265,
+      "eval_samples_per_second": 568.525,
+      "eval_steps_per_second": 2.243,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -295,7 +321,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 225449121090996.0,
+  "total_flos": 248019064848396.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null