Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b01285a843120ba7ed07c3b635d0b9c12f1bd1a012476f6d6399b1ebb428f613
+oid sha256:48e8ffaebfd6ef605ed7a70d898584f2d78a8d777d3176ef4dce697bcdef898c
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c64aa2fa830f9a105805231b81df9bad87e08045f07f00f99e8178f0ad45c467
+oid sha256:f3d35e2adfee94a3f11af486d31ba30fb618502f9c1f33b283e9c6c61b50868f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2ba8d6eeeac1e2a3c2b4bf6a1a6da24d5e75e0c7e0c4a320806088cc6a5239f
+oid sha256:b2ed4580c3880e0fb178fd3387bc120234bd8b0c5f80ab76ddf25a7512d7b4b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e3991895adc0982abbe1eaf294042aa9cc197b13c08fe21c235f8d50ffdc14
+oid sha256:b7100428e35f211c455e0edf66e71a9c6844c13e9f45aabcb2c136afe45ca3ce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.039172105491161346,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-9000",
-  "epoch": 4.437869822485207,
+  "best_metric": 0.03805544227361679,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-10000",
+  "epoch": 4.930966469428008,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,6 +241,32 @@
       "eval_samples_per_second": 304.881,
       "eval_steps_per_second": 19.06,
       "step": 9000
+    },
+    {
+      "epoch": 4.684418145956608,
+      "grad_norm": 0.43250563740730286,
+      "learning_rate": 1.0631163708086787e-05,
+      "loss": 0.0352,
+      "step": 9500
+    },
+    {
+      "epoch": 4.930966469428008,
+      "grad_norm": 0.49166053533554077,
+      "learning_rate": 1.0138067061143987e-05,
+      "loss": 0.035,
+      "step": 10000
+    },
+    {
+      "epoch": 4.930966469428008,
+      "eval_accuracy": 0.9873464007823461,
+      "eval_f1": 0.5759475634083785,
+      "eval_loss": 0.03805544227361679,
+      "eval_precision": 0.7600601729973674,
+      "eval_recall": 0.46363844918559305,
+      "eval_runtime": 26.4106,
+      "eval_samples_per_second": 307.074,
+      "eval_steps_per_second": 19.197,
+      "step": 10000
     }
   ],
   "logging_steps": 500,
@@ -260,7 +286,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 203241954845196.0,
+  "total_flos": 225936279463716.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null