Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:247cf5f905f54795bc77743ea33f7a5b8df568c4bbcc6f2156898066c750ffa8
+oid sha256:ec655a72dba81932329ab4f3afb82b4e0488e7cb4b4a4dbe5afb4947793e3534
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e0b12c3846ccb075c6d845df28284bee77133d72781129359a9258cb59147b1
+oid sha256:6f9680331d95e21d10dceac05f9cf274119be88d64788f484e683d76f87c471e
 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": 0.03775615990161896,
-  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/checkpoint-13000",
-  "epoch": 6.410256410256411,
+  "best_metric": 0.03744753450155258,
+  "best_model_checkpoint": "doc-topic-model_eval-04_train-01/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": 556.661,
       "eval_steps_per_second": 2.196,
       "step": 13000
+    },
+    {
+      "epoch": 6.65680473372781,
+      "grad_norm": 0.3162294924259186,
+      "learning_rate": 1.8668836291913217e-05,
+      "loss": 0.0267,
+      "step": 13500
+    },
+    {
+      "epoch": 6.903353057199211,
+      "grad_norm": 0.3698256313800812,
+      "learning_rate": 1.8619526627218937e-05,
+      "loss": 0.0282,
+      "step": 14000
+    },
+    {
+      "epoch": 6.903353057199211,
+      "eval_accuracy": 0.9875990144949712,
+      "eval_f1": 0.6094328677881398,
+      "eval_loss": 0.03744753450155258,
+      "eval_precision": 0.7302962250026735,
+      "eval_recall": 0.5228943338437979,
+      "eval_runtime": 14.4711,
+      "eval_samples_per_second": 560.633,
+      "eval_steps_per_second": 2.211,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -373,7 +399,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 293969500974828.0,
+  "total_flos": 316659679564644.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null