Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dccbf4c3f6e341672db71a01c1df57bb14442b38a8f4a018b03c614dedab95b0
+oid sha256:ed574e6146e933eb3a3ee7c8db9b460d874216c1e941646df36a6c42ad2d82fe
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eef323e22749f742da51cfe9d474e46780fcd637e19f1a4f663db634cb9452a
+oid sha256:1b222d9016496fffa03a3616511b831738289197202235dd1f567066cdbfa317
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
+oid sha256:257882d778b7ee81778c5c372a17241451c183798e27c011c1764580527db4bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ba7656f2677e9d4a517320301deeaf9502c6f8f9c04d35a107ff5b3063e9135
+oid sha256:b383cee6a8b310b70be569cfc8af334eaeb0c2fb37d6fe24dbd7ccca37a08dab
 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": 7.396449704142012,
+  "epoch": 7.889546351084813,
   "eval_steps": 1000,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,32 @@
       "eval_samples_per_second": 558.998,
       "eval_steps_per_second": 2.206,
       "step": 15000
+    },
+    {
+      "epoch": 7.642998027613412,
+      "grad_norm": 0.44261014461517334,
+      "learning_rate": 1.8471696252465485e-05,
+      "loss": 0.0225,
+      "step": 15500
+    },
+    {
+      "epoch": 7.889546351084813,
+      "grad_norm": 0.721012532711029,
+      "learning_rate": 1.8422386587771205e-05,
+      "loss": 0.0236,
+      "step": 16000
+    },
+    {
+      "epoch": 7.889546351084813,
+      "eval_accuracy": 0.9878041866859418,
+      "eval_f1": 0.6205406358865811,
+      "eval_loss": 0.03788597509264946,
+      "eval_precision": 0.7373716202054077,
+      "eval_recall": 0.5356680624286259,
+      "eval_runtime": 14.537,
+      "eval_samples_per_second": 557.887,
+      "eval_steps_per_second": 2.201,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -425,7 +451,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 339639561910152.0,
+  "total_flos": 362359799208072.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null