Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8735d2e1c53fa856dfc9969a49ba3f211797bc86a889b9c72bf12ef517cd8500
+oid sha256:116ad19701dd5f5d25256a2a51f43d15d1202fcb04be6d0cf5615275c8222ed1
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01127c9de53af7661c659a9b05e5fe0b35aa187ea4a4a78f5aee56c8629a2308
+oid sha256:51360f45d7bedb6864a54ed42a9923f51c5e6db51f3c8efc1885c1b4170a858f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b5b8eb805933fe8f900e32fd375bcc66cfa8e06b254a11fc2a80b5c9b6018d
+oid sha256:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac5cca03c5fb2105d752b6c1034ca2d26b6b19fd729ff034cb671359a651884
+oid sha256:33ec0c6c7881febe86af83de0fd1c05de3d6b8cdacbf1d5a88958d9ee8777f33
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.037345413118600845,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-12000",
-  "epoch": 6.410256410256411,
+  "best_metric": 0.037242207676172256,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-00/checkpoint-14000",
+  "epoch": 6.903353057199211,
   "eval_steps": 1000,
-  "global_step": 13000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -345,6 +345,32 @@
       "eval_samples_per_second": 542.988,
       "eval_steps_per_second": 2.142,
       "step": 13000
+    },
+    {
+      "epoch": 6.65680473372781,
+      "grad_norm": 0.2560911774635315,
+      "learning_rate": 1.8668836291913217e-05,
+      "loss": 0.0273,
+      "step": 13500
+    },
+    {
+      "epoch": 6.903353057199211,
+      "grad_norm": 0.4542127549648285,
+      "learning_rate": 1.8619526627218937e-05,
+      "loss": 0.0261,
+      "step": 14000
+    },
+    {
+      "epoch": 6.903353057199211,
+      "eval_accuracy": 0.987696472355684,
+      "eval_f1": 0.6137829781554478,
+      "eval_loss": 0.037242207676172256,
+      "eval_precision": 0.7383857846285592,
+      "eval_recall": 0.5251617814998096,
+      "eval_runtime": 14.4235,
+      "eval_samples_per_second": 562.276,
+      "eval_steps_per_second": 2.219,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -373,7 +399,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 294355599897888.0,
+  "total_flos": 317002245186312.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null