Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7483e50dce88817d8232c8fd5c48d5a30b3681ab61be54c68b95b08bbfd05df7
+oid sha256:b561852c7a2760391730922ad15cca84211b928b3355d82427553ddf0689dc1a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d164f4e4d5b28be3491c5a7cac45517ffc781c6e15164967ae02a6be530ea501
+oid sha256:935d9a8a7ad0a5baaf59253fd1faac16f656f3e19ec1cf0e6cdf507d54ae8d9a
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f40c0d9a49a814dc52082f9054fc2ffb694380fb521f25163384314e1e0b22ae
+oid sha256:1128d67de3d4d8e3dd8bc8b4bca4f59bef7d1d2c35b978700b48aaaa3a3cb733
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173f4a2433232f77939b4d77264600e6f898939c018c908fe5f061eb1c76ed9b
+oid sha256:f1d4e0d33a262ad4f64c2ce77b757798ccbd7d82035d16a8a99e7def08d07a9c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0398826077580452,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-8000",
-  "epoch": 3.9447731755424065,
+  "best_metric": 0.03963331878185272,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-9000",
+  "epoch": 4.437869822485207,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,6 +215,32 @@
       "eval_samples_per_second": 554.767,
       "eval_steps_per_second": 2.189,
       "step": 8000
+    },
+    {
+      "epoch": 4.191321499013807,
+      "grad_norm": 0.4470931887626648,
+      "learning_rate": 1.916173570019724e-05,
+      "loss": 0.0342,
+      "step": 8500
+    },
+    {
+      "epoch": 4.437869822485207,
+      "grad_norm": 0.33709824085235596,
+      "learning_rate": 1.911242603550296e-05,
+      "loss": 0.0343,
+      "step": 9000
+    },
+    {
+      "epoch": 4.437869822485207,
+      "eval_accuracy": 0.986877276528197,
+      "eval_f1": 0.5599125433718333,
+      "eval_loss": 0.03963331878185272,
+      "eval_precision": 0.7451923076923077,
+      "eval_recall": 0.4484202512371526,
+      "eval_runtime": 14.6638,
+      "eval_samples_per_second": 553.061,
+      "eval_steps_per_second": 2.182,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -243,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 181104234580188.0,
+  "total_flos": 203651375179716.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null