Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4cca5bdfb012fd0f7593bd75cdf753f944075544c69c1b80749032d30975e46
+oid sha256:615812c6039edc87981879f12b45c8ed7ba24244372a4eecfcdd795e5b7dd397
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6ee0a058beb4b6db1c17d95e2fd6cadf3d09b3a23f95df9a486b706ba0ffdf
+oid sha256:43084f1d31da6494bf35a40084f36d88a2ba83e069a262707dbf4ce6692c1144
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
+oid sha256:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:239fa09e124e09df5505eb284e48ffb12e108ec6cdc74ac0c4570827a7cff8ee
+oid sha256:7770ab36fc118683d75ac831239ef224ccbc0c55abe600db074c2f5741fab05a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.03710732236504555,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-04/checkpoint-11000",
-  "epoch": 6.407097092163627,
+  "epoch": 6.899950714637752,
   "eval_steps": 1000,
-  "global_step": 13000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -345,6 +345,32 @@
       "eval_samples_per_second": 568.17,
       "eval_steps_per_second": 2.242,
       "step": 13000
+    },
+    {
+      "epoch": 6.65352390340069,
+      "grad_norm": 0.5648388266563416,
+      "learning_rate": 1.8669492360768852e-05,
+      "loss": 0.0264,
+      "step": 13500
+    },
+    {
+      "epoch": 6.899950714637752,
+      "grad_norm": 0.4413442015647888,
+      "learning_rate": 1.862020699852144e-05,
+      "loss": 0.0273,
+      "step": 14000
+    },
+    {
+      "epoch": 6.899950714637752,
+      "eval_accuracy": 0.9875703332057769,
+      "eval_f1": 0.6136904237512113,
+      "eval_loss": 0.03730667382478714,
+      "eval_precision": 0.7237402597402598,
+      "eval_recall": 0.5326909841706814,
+      "eval_runtime": 14.3016,
+      "eval_samples_per_second": 567.07,
+      "eval_steps_per_second": 2.238,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -373,7 +399,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 294847422552900.0,
+  "total_flos": 317495104348500.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null