Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdc2f6a93d757c3f03bbfac4447d28115c84e5bb9305075abf6e5d9857143a6
+oid sha256:fe68f4577286b85cbc5c6a48af902103215e6d0a6d1406ab180a643234b19700
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:312874010f15b448bda5615dad16cfc5a539a05750da1abce24e599ec7466ef9
+oid sha256:f0177ee53022f715e3a3e89ac556dbf20c1d9fd7f663800df2375e52c0556c37
 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": 0.04173528403043747,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/checkpoint-7000",
-  "epoch": 3.4516765285996054,
+  "best_metric": 0.040070790797472,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-03/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": 554.772,
       "eval_steps_per_second": 2.189,
       "step": 7000
+    },
+    {
+      "epoch": 3.698224852071006,
+      "grad_norm": 0.46907347440719604,
+      "learning_rate": 1.92603550295858e-05,
+      "loss": 0.0382,
+      "step": 7500
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "grad_norm": 0.3860171437263489,
+      "learning_rate": 1.921104536489152e-05,
+      "loss": 0.0384,
+      "step": 8000
+    },
+    {
+      "epoch": 3.9447731755424065,
+      "eval_accuracy": 0.9866335019912978,
+      "eval_f1": 0.5599776046283768,
+      "eval_loss": 0.040070790797472,
+      "eval_precision": 0.7181665868836764,
+      "eval_recall": 0.4588973006041141,
+      "eval_runtime": 14.6864,
+      "eval_samples_per_second": 552.213,
+      "eval_steps_per_second": 2.179,
+      "step": 8000
     }
   ],
   "logging_steps": 500,
@@ -217,7 +243,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 157815991349820.0,
+  "total_flos": 180338255777124.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null