Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e57af6d0264134e1a162bcfb3aa14cc30aa29fa31a292f9ff45b9499a1218c3f
+oid sha256:7483e50dce88817d8232c8fd5c48d5a30b3681ab61be54c68b95b08bbfd05df7
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:034a233bc1d79601e0eb13ff5bc45f0821be2f8026e4748c83964a8ac7a7afa7
+oid sha256:d164f4e4d5b28be3491c5a7cac45517ffc781c6e15164967ae02a6be530ea501
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4902fcfb33d73ecfa5cb7dbd3cfd13500058abf1d6eae05ae197780b6416694
+oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43495fd59fd541eb94253a07f3e011c2581153d25d7fa1816722e70a1a8e7f7f
+oid sha256:173f4a2433232f77939b4d77264600e6f898939c018c908fe5f061eb1c76ed9b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04127802699804306,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-7000",
-  "epoch": 3.4516765285996054,
+  "best_metric": 0.0398826077580452,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-8000",
+  "epoch": 3.9447731755424065,
   "eval_steps": 1000,
-  "global_step": 7000,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,32 @@
       "eval_samples_per_second": 559.446,
       "eval_steps_per_second": 2.207,
       "step": 7000
+    },
+    {
+      "epoch": 3.698224852071006,
+      "grad_norm": 0.47940972447395325,
+      "learning_rate": 1.92603550295858e-05,
+      "loss": 0.0394,
+      "step": 7500
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "grad_norm": 0.39106041193008423,
+      "learning_rate": 1.921104536489152e-05,
+      "loss": 0.0385,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "eval_accuracy": 0.9867043666822569,
+      "eval_f1": 0.536168108776267,
+      "eval_loss": 0.0398826077580452,
+      "eval_precision": 0.7647390691114245,
+      "eval_recall": 0.41279025504377614,
+      "eval_runtime": 14.6187,
+      "eval_samples_per_second": 554.767,
+      "eval_steps_per_second": 2.189,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -217,7 +243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 158396435368380.0,
+  "total_flos": 181104234580188.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null