Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1c5d02bf9b01e0c5f1540f954297d63621fbdac6f6c570ec5765a1db7c15b64
+oid sha256:a339bd470013c8491ebf0d72fc3ee02df1ef2e6cd7b107d451f5ab1060a88f2e
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f3019f5bcc0d2eea7266f4548fb320a29faca7083d50ded305c123dd9b8a16
+oid sha256:35a3999d734c354e3c99f99c8060ac2985872124b38cf5e0c86f51c610e3425e
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:008375a0cc671d0e1c0f8976d480a3388a0d027af1650425d6c4d02940510b98
+oid sha256:886034beaadedc8c14b848859c00bafbf6ac1fe7936754759a2ece8f7c66229f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82024a11f598f8b76f243f46b3e14fa06e234755e8f77084e55d553c6e34a0d3
+oid sha256:8fda17ccbaef24102552407afe26348887346d6be2aa1770720ba332a543beee
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03880663216114044,
   "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-10000",
-  "epoch": 94.48818897637796,
+  "epoch": 102.36220472440945,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -319,6 +319,32 @@
       "eval_samples_per_second": 574.434,
       "eval_steps_per_second": 2.267,
       "step": 12000
+    },
+    {
+      "epoch": 98.4251968503937,
+      "grad_norm": 0.15036757290363312,
+      "learning_rate": 1.924212598425197e-06,
+      "loss": 0.0227,
+      "step": 12500
+    },
+    {
+      "epoch": 102.36220472440945,
+      "grad_norm": 0.14854416251182556,
+      "learning_rate": 1.801181102362205e-06,
+      "loss": 0.022,
+      "step": 13000
+    },
+    {
+      "epoch": 102.36220472440945,
+      "eval_accuracy": 0.987407344416571,
+      "eval_f1": 0.6050584522380762,
+      "eval_loss": 0.03925173729658127,
+      "eval_precision": 0.7269814142277291,
+      "eval_recall": 0.5181575942139323,
+      "eval_runtime": 14.1509,
+      "eval_samples_per_second": 573.11,
+      "eval_steps_per_second": 2.261,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -338,7 +364,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5391592640102556.0,
+  "total_flos": 5841706246352316.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null