Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cb57c5262035f3705b65d77498506c7c3f841b2173d88195b416d8c623bf46d
+oid sha256:9e9db27c94c28d9b65e466323dfb8bba31f572b48a413d2f3e89efc3b84e022f
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d32136496be5a3316994d4cb6ef4ecbb2134a3b6e7cbaa02f4d54a20975bc0a
+oid sha256:81cb3e60befc0e20897ae1594382838e6bd5ccb886dfbe92df2045b4b97c78a1
 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": 0.037353336811065674,
   "best_model_checkpoint": "doc-topic-model_eval-00_train-01/checkpoint-11000",
-  "epoch": 5.9171597633136095,
+  "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": 570.035,
       "eval_steps_per_second": 2.249,
       "step": 12000
+    },
+    {
+      "epoch": 6.16370808678501,
+      "grad_norm": 0.24124543368816376,
+      "learning_rate": 1.8767455621301777e-05,
+      "loss": 0.0272,
+      "step": 12500
+    },
+    {
+      "epoch": 6.410256410256411,
+      "grad_norm": 0.35210439562797546,
+      "learning_rate": 1.8718145956607497e-05,
+      "loss": 0.0265,
+      "step": 13000
+    },
+    {
+      "epoch": 6.410256410256411,
+      "eval_accuracy": 0.9873733293649106,
+      "eval_f1": 0.6035334431044457,
+      "eval_loss": 0.03765496611595154,
+      "eval_precision": 0.7218437300404513,
+      "eval_recall": 0.5185440085646555,
+      "eval_runtime": 14.1601,
+      "eval_samples_per_second": 572.737,
+      "eval_steps_per_second": 2.26,
+      "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