Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5348d2393066d4c6f6d98b99d5ac798f79e13400c498941a12da3a4f6a76dbea
+oid sha256:8234dae96ba7260c611f7d9702611e59aeab592fd4574af1a5612a44d212b476
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09e30b8649b7b5a11efefdbe9b5eb7549cfce856efa5c154b1a1f4bc8a3b26e8
+oid sha256:d607fab1f4688e5bec6ee2e6ac20d4ab1c590cd9491384d208084d34cac184b4
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3e7c16db59721aea2b47c2269764fae7399d4a794f4f6442f42ff4514c3e44e
+oid sha256:f714de4718c9f1d44807a05241d81ef45fb7284a03e54b16395bd62796dc0d80
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8a67c34da9d806e20456efe3535d49ffebd2cae0e0aa1b56dc6c7c3655acde
+oid sha256:cfa82bd145226380bce05f85478c748b91192c52d2324974f8354d5aa36dd6af
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04525615647435188,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-5000",
-  "epoch": 0.6164468006411047,
+  "best_metric": 0.042106639593839645,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-6000",
+  "epoch": 0.7397361607693256,
   "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": 298.089,
       "eval_steps_per_second": 18.633,
       "step": 5000
+    },
+    {
+      "epoch": 0.6780914807052152,
+      "grad_norm": 0.3579052984714508,
+      "learning_rate": 1.864381703858957e-05,
+      "loss": 0.0467,
+      "step": 5500
+    },
+    {
+      "epoch": 0.7397361607693256,
+      "grad_norm": 0.373826801776886,
+      "learning_rate": 1.852052767846135e-05,
+      "loss": 0.0455,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7397361607693256,
+      "eval_accuracy": 0.9859691039697757,
+      "eval_f1": 0.48744629083190977,
+      "eval_loss": 0.042106639593839645,
+      "eval_precision": 0.7547290798332799,
+      "eval_recall": 0.3599663582842725,
+      "eval_runtime": 26.1757,
+      "eval_samples_per_second": 309.867,
+      "eval_steps_per_second": 19.369,
+      "step": 6000
     }
   ],
   "logging_steps": 500,
@@ -144,7 +170,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 113262248643048.0,
+  "total_flos": 135822863835864.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null