Training in progress, step 20000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486bc78f538a47a7ac2f42a01ccd697c0cdd1c2f50ea50baf94cd2e412cbf5d9
+oid sha256:fb9f51a783df8cd4184c8ff6322283ae5b7793d6c9193bbf60e1261cd4e2663c
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f98b33e444e1ef383d62f368b1a77fb1f24d5b137bd610adec5cfa172629a08
+oid sha256:86f00b741bf0124136a44f7bf6d1fcd9a8a0633a83dd3007eca0567fb88fac08
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae8e30db558983566b3627c1305b559e52f0e7e07cc4e789102fcad4ec530f11
+oid sha256:5739ad1470dd61f60c847b4c724972fef526d7699c4e508ced265ccae5231b88
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70905d47b919998eb818b73b74b309c76308f4326c28a1f4477227e0f8486e04
+oid sha256:0c6513724227630151c79051ec6207366b00d809ac45184982374810ca6fb630
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03187329322099686,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-19000",
-  "epoch": 2.342497842436198,
+  "best_metric": 0.03158288821578026,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-20000",
+  "epoch": 2.4657872025644187,
   "eval_steps": 1000,
-  "global_step": 19000,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -501,6 +501,32 @@
       "eval_samples_per_second": 308.733,
       "eval_steps_per_second": 19.298,
       "step": 19000
+    },
+    {
+      "epoch": 2.404142522500308,
+      "grad_norm": 0.3840814232826233,
+      "learning_rate": 1.5191714954999386e-05,
+      "loss": 0.0306,
+      "step": 19500
+    },
+    {
+      "epoch": 2.4657872025644187,
+      "grad_norm": 0.27500978112220764,
+      "learning_rate": 1.5068425594871164e-05,
+      "loss": 0.0305,
+      "step": 20000
+    },
+    {
+      "epoch": 2.4657872025644187,
+      "eval_accuracy": 0.9888160962053802,
+      "eval_f1": 0.6618680377035132,
+      "eval_loss": 0.03158288821578026,
+      "eval_precision": 0.7527531429685216,
+      "eval_recall": 0.5905650279073323,
+      "eval_runtime": 26.2735,
+      "eval_samples_per_second": 308.714,
+      "eval_steps_per_second": 19.297,
+      "step": 20000
     }
   ],
   "logging_steps": 500,
@@ -508,7 +534,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 429792883064280.0,
+  "total_flos": 452435382324000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null