Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb49ad2962852fa948fe5f25affadde9bcd99ad695564a6a9463ee265e40db1
+oid sha256:247cf5f905f54795bc77743ea33f7a5b8df568c4bbcc6f2156898066c750ffa8
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154a9123225a4c0569c1288cf34bffc4e955e914fe3bd3f59d8e10728d986226
+oid sha256:3e0b12c3846ccb075c6d845df28284bee77133d72781129359a9258cb59147b1
 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": 0.03807613626122475,
-  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-11000",
-  "epoch": 5.9171597633136095,
+  "best_metric": 0.03775615990161896,
+  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/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": 563.816,
       "eval_steps_per_second": 2.224,
       "step": 12000
+    },
+    {
+      "epoch": 6.16370808678501,
+      "grad_norm": 0.4404219686985016,
+      "learning_rate": 1.876735700197239e-05,
+      "loss": 0.0281,
+      "step": 12500
+    },
+    {
+      "epoch": 6.410256410256411,
+      "grad_norm": 0.39860355854034424,
+      "learning_rate": 1.8718145956607497e-05,
+      "loss": 0.027,
+      "step": 13000
+    },
+    {
+      "epoch": 6.410256410256411,
+      "eval_accuracy": 0.987472921988408,
+      "eval_f1": 0.6029636281993713,
+      "eval_loss": 0.03775615990161896,
+      "eval_precision": 0.7289902280130293,
+      "eval_recall": 0.5140888208269525,
+      "eval_runtime": 14.5744,
+      "eval_samples_per_second": 556.661,
+      "eval_steps_per_second": 2.196,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -347,7 +373,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 271450346069052.0,
+  "total_flos": 293969500974828.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null