Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75f25d8ad92f875a53659d2aa604eab54bc9083bbbead781aa5da3c192cfdc81
+oid sha256:b9b0baeb960dd305488b4d620acbbe73944acf2f3aee6f39ab4f9f2ace9146da
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8883bcd809b17855f5bd75fa68a9ed04c375ce0e9e0384257d097e9cf8c0ddd9
+oid sha256:aae5503ebaf112403941b4ddfc161ae2d74499963b425aa493869fdb99502c7b
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
+oid sha256:d909219cbdd70599a7be8a42aba4df5d7065f7b997b0075bce4834affe89f840
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
+oid sha256:cd937dc5ca4c62f5f5a023ee1555a7a5e140540c1dc517f73c54011163ae049e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0379740335047245,
   "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-16000",
-  "epoch": 7.889546351084813,
+  "epoch": 8.382642998027613,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -423,6 +423,32 @@
       "eval_samples_per_second": 555.63,
       "eval_steps_per_second": 2.192,
       "step": 16000
+    },
+    {
+      "epoch": 8.136094674556213,
+      "grad_norm": 0.13463503122329712,
+      "learning_rate": 1.8373076923076926e-05,
+      "loss": 0.0224,
+      "step": 16500
+    },
+    {
+      "epoch": 8.382642998027613,
+      "grad_norm": 0.25073572993278503,
+      "learning_rate": 1.8323865877712033e-05,
+      "loss": 0.0214,
+      "step": 17000
+    },
+    {
+      "epoch": 8.382642998027613,
+      "eval_accuracy": 0.9875703332057769,
+      "eval_f1": 0.6291754756871036,
+      "eval_loss": 0.03818249702453613,
+      "eval_precision": 0.7049459920409323,
+      "eval_recall": 0.5681124007330483,
+      "eval_runtime": 14.6338,
+      "eval_samples_per_second": 554.198,
+      "eval_steps_per_second": 2.187,
+      "step": 17000
     }
   ],
   "logging_steps": 500,
@@ -451,7 +477,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 361937940787440.0,
+  "total_flos": 384458650453980.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null