Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc272e9a8e261ed2bdbeebd910f8b7fa802c0ab2771de97deb7426c0a34a46d4
+oid sha256:4fcb0b12d80922acf2ee11edfa317445b89d6ea898d7004e49308eab044ae29f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:444082af6890f7fa4945fa47555e1290f6ca308e03915d60b4c7f291b3071486
+oid sha256:6bef9e44e257616711808e8eccedc362b9ac2a971c10fdc4ca87f4f7d96f3c34
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56f4ef3ec6475612038b659c4ace802fdab90a52ad47a95114fd963780c200ae
+oid sha256:651d1232597f5c3e9197278fb6bc58c260307b3b5a878a7a3eef0561cd79931c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06f25b2e82d5726321480e2bb4450422006a39d571b32467918f1ed8e55e4db
+oid sha256:ed05c2781030d49f708235d0b4004a9dd014c1dad90b888053a7b20bddc62e8a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03934308886528015,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-8000",
-  "epoch": 62.99212598425197,
+  "best_metric": 0.038920916616916656,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-9000",
+  "epoch": 70.86614173228347,
   "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": 572.936,
       "eval_steps_per_second": 2.261,
       "step": 8000
+    },
+    {
+      "epoch": 66.92913385826772,
+      "grad_norm": 0.13788625597953796,
+      "learning_rate": 2.908464566929134e-06,
+      "loss": 0.0302,
+      "step": 8500
+    },
+    {
+      "epoch": 70.86614173228347,
+      "grad_norm": 0.12086493521928787,
+      "learning_rate": 2.785433070866142e-06,
+      "loss": 0.029,
+      "step": 9000
+    },
+    {
+      "epoch": 70.86614173228347,
+      "eval_accuracy": 0.9874427767620505,
+      "eval_f1": 0.5916297935103245,
+      "eval_loss": 0.038920916616916656,
+      "eval_precision": 0.7496787758439435,
+      "eval_recall": 0.4886181956604492,
+      "eval_runtime": 14.1532,
+      "eval_samples_per_second": 573.016,
+      "eval_steps_per_second": 2.261,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -234,7 +260,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3596066806725396.0,
+  "total_flos": 4045469369052420.0,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null