Training in progress, step 19000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec687cb4cf3c1a63b7c0cf984927892a5c40a9016826d6b333cda3c07f247c6d
+oid sha256:486bc78f538a47a7ac2f42a01ccd697c0cdd1c2f50ea50baf94cd2e412cbf5d9
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc99ad5a91c437864a61c3e9c4513dbab499871780ae574daccaf5b662db3387
+oid sha256:6f98b33e444e1ef383d62f368b1a77fb1f24d5b137bd610adec5cfa172629a08
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93f0e9cc44a5d6ccaee93162e56f359da5c2b4c7afde86d9957879ed20b028a3
+oid sha256:ae8e30db558983566b3627c1305b559e52f0e7e07cc4e789102fcad4ec530f11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc5202904cf5915604424b70e014b8084586938c2e29300d7ed606d964f0365
+oid sha256:70905d47b919998eb818b73b74b309c76308f4326c28a1f4477227e0f8486e04
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.0319632813334465,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-18000",
-  "epoch": 2.2192084823079767,
+  "best_metric": 0.03187329322099686,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-19000",
+  "epoch": 2.342497842436198,
   "eval_steps": 1000,
-  "global_step": 18000,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -475,6 +475,32 @@
       "eval_samples_per_second": 303.615,
       "eval_steps_per_second": 18.978,
       "step": 18000
+    },
+    {
+      "epoch": 2.2808531623720874,
+      "grad_norm": 0.47022199630737305,
+      "learning_rate": 1.5438293675255826e-05,
+      "loss": 0.0313,
+      "step": 18500
+    },
+    {
+      "epoch": 2.342497842436198,
+      "grad_norm": 0.2270212471485138,
+      "learning_rate": 1.5315004315127606e-05,
+      "loss": 0.0307,
+      "step": 19000
+    },
+    {
+      "epoch": 2.342497842436198,
+      "eval_accuracy": 0.9889209630174434,
+      "eval_f1": 0.6525642165140876,
+      "eval_loss": 0.03187329322099686,
+      "eval_precision": 0.7791573808765786,
+      "eval_recall": 0.5613579019802737,
+      "eval_runtime": 26.2719,
+      "eval_samples_per_second": 308.733,
+      "eval_steps_per_second": 19.298,
+      "step": 19000
     }
   ],
   "logging_steps": 500,
@@ -482,7 +508,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 407169040933728.0,
+  "total_flos": 429792883064280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null