Training in progress, step 15000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:116ad19701dd5f5d25256a2a51f43d15d1202fcb04be6d0cf5615275c8222ed1
+oid sha256:dccbf4c3f6e341672db71a01c1df57bb14442b38a8f4a018b03c614dedab95b0
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51360f45d7bedb6864a54ed42a9923f51c5e6db51f3c8efc1885c1b4170a858f
+oid sha256:1eef323e22749f742da51cfe9d474e46780fcd637e19f1a4f663db634cb9452a
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
+oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33ec0c6c7881febe86af83de0fd1c05de3d6b8cdacbf1d5a88958d9ee8777f33
+oid sha256:8ba7656f2677e9d4a517320301deeaf9502c6f8f9c04d35a107ff5b3063e9135
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.037242207676172256,
   "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-14000",
-  "epoch": 6.903353057199211,
+  "epoch": 7.396449704142012,
   "eval_steps": 1000,
-  "global_step": 14000,
+  "global_step": 15000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,6 +371,32 @@
       "eval_samples_per_second": 562.276,
       "eval_steps_per_second": 2.219,
       "step": 14000
+    },
+    {
+      "epoch": 7.149901380670611,
+      "grad_norm": 0.2716215252876282,
+      "learning_rate": 1.8570216962524657e-05,
+      "loss": 0.025,
+      "step": 14500
+    },
+    {
+      "epoch": 7.396449704142012,
+      "grad_norm": 0.2959195077419281,
+      "learning_rate": 1.8520907297830377e-05,
+      "loss": 0.0236,
+      "step": 15000
+    },
+    {
+      "epoch": 7.396449704142012,
+      "eval_accuracy": 0.9875859234377878,
+      "eval_f1": 0.6186599329531107,
+      "eval_loss": 0.037820491939783096,
+      "eval_precision": 0.7224933902786251,
+      "eval_recall": 0.5409212028930339,
+      "eval_runtime": 14.5081,
+      "eval_samples_per_second": 558.998,
+      "eval_steps_per_second": 2.206,
+      "step": 15000
     }
   ],
   "logging_steps": 500,
@@ -399,7 +425,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 317002245186312.0,
+  "total_flos": 339639561910152.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null