Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a14ba6d631b491aedf133a76099b0070972351da82405b18ac3450de34336449
+oid sha256:791af0f71e3a9b8e8ae2ddc2902b7686c5f69824bf9684c694143cc9c7a516b2
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ea4bb0360117a07d4f6423fa49546e2503080cd4f5396d578fe653c6c03609
+oid sha256:cb49ff40fbf04fc597f1b5630850feb0b992849099b487836eadc12854f7d18d
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
+oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
+oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0374138318002224,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-03/checkpoint-11000",
-  "epoch": 5.424063116370808,
+  "epoch": 5.9171597633136095,
   "eval_steps": 1000,
-  "global_step": 11000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -293,6 +293,32 @@
       "eval_samples_per_second": 571.214,
       "eval_steps_per_second": 2.254,
       "step": 11000
+    },
+    {
+      "epoch": 5.670611439842209,
+      "grad_norm": 0.42573484778404236,
+      "learning_rate": 1.886597633136095e-05,
+      "loss": 0.0299,
+      "step": 11500
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "grad_norm": 0.4632101058959961,
+      "learning_rate": 1.881666666666667e-05,
+      "loss": 0.0295,
+      "step": 12000
+    },
+    {
+      "epoch": 5.9171597633136095,
+      "eval_accuracy": 0.9874172654733052,
+      "eval_f1": 0.607688908528502,
+      "eval_loss": 0.03787928447127342,
+      "eval_precision": 0.7251634676228643,
+      "eval_recall": 0.5229692728932157,
+      "eval_runtime": 14.2477,
+      "eval_samples_per_second": 569.215,
+      "eval_steps_per_second": 2.246,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -321,7 +347,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 248019064848396.0,
+  "total_flos": 270583826069916.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null