Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbf9989a447bed277743dcb2ea80a7cb3fcb1bbaa95e58b211d2a73dfea0ffd
+oid sha256:0a17bf60874919302bf060fcfc24b328b624c7c4bd1003f6edc267a3bcfb892a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f649395a4870f6a70a61bc31d55a3c65cb309a97ffaec5349d10a193cffa235
+oid sha256:dcbd23dd70abf19d61c89ac45de7148f6033ec9dd99629a468e285604c3b5133
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a445c512a69801b68e319bfb3cb3702cfd8c222330cff7d4d1380aca05cd09b
+oid sha256:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1600bc22796954bbfe2cfe1a5708dbdc0d32592a1fa22b6a9c5489c11d5fbd8c
+oid sha256:5ac5cca03c5fb2105d752b6c1034ca2d26b6b19fd729ff034cb671359a651884
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03745245933532715,
-  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-12000",
-  "epoch": 5.9171597633136095,
+  "best_metric": 0.03718467801809311,
+  "best_model_checkpoint": "doc-topic-model_eval-00_train-02/checkpoint-13000",
+  "epoch": 6.410256410256411,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -319,6 +319,32 @@
       "eval_samples_per_second": 574.507,
       "eval_steps_per_second": 2.267,
       "step": 12000
+    },
+    {
+      "epoch": 6.16370808678501,
+      "grad_norm": 0.3442145884037018,
+      "learning_rate": 1.8767455621301777e-05,
+      "loss": 0.0268,
+      "step": 12500
+    },
+    {
+      "epoch": 6.410256410256411,
+      "grad_norm": 0.13360050320625305,
+      "learning_rate": 1.8718145956607497e-05,
+      "loss": 0.0263,
+      "step": 13000
+    },
+    {
+      "epoch": 6.410256410256411,
+      "eval_accuracy": 0.9878920589027311,
+      "eval_f1": 0.6160276866376017,
+      "eval_loss": 0.03718467801809311,
+      "eval_precision": 0.7471652856519843,
+      "eval_recall": 0.524049858530244,
+      "eval_runtime": 14.154,
+      "eval_samples_per_second": 572.983,
+      "eval_steps_per_second": 2.261,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -347,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 271026414634068.0,
+  "total_flos": 293677205951196.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null