Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5877944b290fb96dd700d88e6bf6115d2b61b2de49a6fd05b90f309adbdd3cf
+oid sha256:8872fada1a981cf6b5a3b4e8ccf8c61843bbeb383d907f5afdf234ab3625087d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffbffc6f494f52a2c2b278f22891947c3e86b127409933bdb1cc6d922059e4d6
+oid sha256:9d3d3afd06995d892904de019bc49182323dd2135abf4e4a204ebe2485e31f61
 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": 0.03680593520402908,
   "best_model_checkpoint": "doc-topic-model_eval-04_train-02/checkpoint-11000",
-  "epoch": 6.410256410256411,
+  "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": 559.778,
       "eval_steps_per_second": 2.208,
       "step": 13000
+    },
+    {
+      "epoch": 6.65680473372781,
+      "grad_norm": 0.3087170124053955,
+      "learning_rate": 1.8668836291913217e-05,
+      "loss": 0.0266,
+      "step": 13500
+    },
+    {
+      "epoch": 6.903353057199211,
+      "grad_norm": 0.2865307033061981,
+      "learning_rate": 1.8619526627218937e-05,
+      "loss": 0.0272,
+      "step": 14000
+    },
+    {
+      "epoch": 6.903353057199211,
+      "eval_accuracy": 0.9874545039818313,
+      "eval_f1": 0.6193526200404075,
+      "eval_loss": 0.03758929669857025,
+      "eval_precision": 0.706066843085367,
+      "eval_recall": 0.5516079632465544,
+      "eval_runtime": 14.5181,
+      "eval_samples_per_second": 558.821,
+      "eval_steps_per_second": 2.204,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -373,7 +399,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 293677205951196.0,
+  "total_flos": 316297938560220.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null