Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70104e7a602b7beb6cdb5f82e63553c1542797c2a14628cd9e9bd62225b3517
+oid sha256:feafb2107affe6fdf4c45264861a1909ef3735a26a9c5ada27dbc7dc8ba845d9
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b0bfbec5d5b0f625a6583ae8349d17995c8d548305f249dbe94d5630dd4283a
+oid sha256:0ccbbfeea057fc532f3d46d99f6f4f20db7279e6a5eb62846aee8e261f1d659b
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
+oid sha256:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b33ca44a0afbaac8fba4219410a4b0716db16d80a594374cc1a02724225c0e
+oid sha256:6da7d5a2ae8f209d8c7dd162056a124c933df3dbc8839879a1816c27a0c4446e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03750571236014366,
   "best_model_checkpoint": "doc-topic-model_eval-02_train-04/checkpoint-13000",
-  "epoch": 7.885657959586003,
+  "epoch": 8.378511582060128,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -423,6 +423,32 @@
       "eval_samples_per_second": 571.194,
       "eval_steps_per_second": 2.254,
       "step": 16000
+    },
+    {
+      "epoch": 8.132084770823065,
+      "grad_norm": 0.48524007201194763,
+      "learning_rate": 1.8373878758008873e-05,
+      "loss": 0.0217,
+      "step": 16500
+    },
+    {
+      "epoch": 8.378511582060128,
+      "grad_norm": 0.3671877384185791,
+      "learning_rate": 1.8324593395761462e-05,
+      "loss": 0.0208,
+      "step": 17000
+    },
+    {
+      "epoch": 8.378511582060128,
+      "eval_accuracy": 0.9877219836444293,
+      "eval_f1": 0.6341484015372271,
+      "eval_loss": 0.037882279604673386,
+      "eval_precision": 0.7129427404804862,
+      "eval_recall": 0.5710374201399452,
+      "eval_runtime": 14.1368,
+      "eval_samples_per_second": 573.681,
+      "eval_steps_per_second": 2.264,
+      "step": 17000
     }
   ],
   "logging_steps": 500,
@@ -451,7 +477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 362872352006604.0,
+  "total_flos": 385542059579694.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null