Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b561852c7a2760391730922ad15cca84211b928b3355d82427553ddf0689dc1a
+oid sha256:890abeeecfac3ee4906db72e869dddfa13a5d1f29a30899ea0f29e9df998867a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:935d9a8a7ad0a5baaf59253fd1faac16f656f3e19ec1cf0e6cdf507d54ae8d9a
+oid sha256:14aead3b58b5ed7c3680187d775bc8cef17b8a9351b84a4750461996cfb529bf
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
+oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d4e0d33a262ad4f64c2ce77b757798ccbd7d82035d16a8a99e7def08d07a9c
+oid sha256:c3c3f1ac50882defeade258e77931f3038c02d6276451a81f8ef210f495feca4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03959447145462036,
-  "best_model_checkpoint": "doc-topic-model_eval-02_train-00/checkpoint-9000",
-  "epoch": 4.437869822485207,
+  "best_metric": 0.038809314370155334,
+  "best_model_checkpoint": "doc-topic-model_eval-02_train-00/checkpoint-11000",
+  "epoch": 5.424063116370808,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,58 @@
       "eval_samples_per_second": 557.678,
       "eval_steps_per_second": 2.2,
       "step": 9000
+    },
+    {
+      "epoch": 4.684418145956608,
+      "grad_norm": 0.3310143053531647,
+      "learning_rate": 1.906311637080868e-05,
+      "loss": 0.0343,
+      "step": 9500
+    },
+    {
+      "epoch": 4.930966469428008,
+      "grad_norm": 0.5156289935112,
+      "learning_rate": 1.90138067061144e-05,
+      "loss": 0.0343,
+      "step": 10000
+    },
+    {
+      "epoch": 4.930966469428008,
+      "eval_accuracy": 0.9872230962200774,
+      "eval_f1": 0.57721708952774,
+      "eval_loss": 0.03884171321988106,
+      "eval_precision": 0.752782874617737,
+      "eval_recall": 0.46805597809552785,
+      "eval_runtime": 14.5796,
+      "eval_samples_per_second": 556.255,
+      "eval_steps_per_second": 2.195,
+      "step": 10000
+    },
+    {
+      "epoch": 5.177514792899408,
+      "grad_norm": 0.3030126988887787,
+      "learning_rate": 1.896459566074951e-05,
+      "loss": 0.0314,
+      "step": 10500
+    },
+    {
+      "epoch": 5.424063116370808,
+      "grad_norm": 0.49180835485458374,
+      "learning_rate": 1.891528599605523e-05,
+      "loss": 0.0304,
+      "step": 11000
+    },
+    {
+      "epoch": 5.424063116370808,
+      "eval_accuracy": 0.9870983743639894,
+      "eval_f1": 0.5816059199338144,
+      "eval_loss": 0.038809314370155334,
+      "eval_precision": 0.7349285631316065,
+      "eval_recall": 0.48121387283236994,
+      "eval_runtime": 14.3105,
+      "eval_samples_per_second": 566.716,
+      "eval_steps_per_second": 2.236,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -269,7 +321,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 203651375179716.0,
+  "total_flos": 249047798220576.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null