Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0261c797ffae126153cbbb1467b83780ff91dc1912396077fc38e284df689975
+oid sha256:dd1cbb26c77bdd11b36482bc270b8c0a4e7a62a2232b00bd25d82d2b56ce9d8c
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1d631affb6dccd4f3fd4cfc3390be46f868b7efccefa2043b4f74f85561c51c
+oid sha256:33082566925f313648e53bff28b4b27c2bf5a0db666be841cf6868e256abdce0
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34649568145f465443beb487f2295ab3dad9e5f49f758646dd823029413e18fe
+oid sha256:69797e619b7f76fc3c65d1346887cd92f6a036b8a8ff866da9ca1a335d274133
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e136870ce715682b288c29fb4d05a0aec61f1a74b2cc393d7fb9e66e4965261
+oid sha256:de10e3ea9e9f590bd00b7f01055683747e52076430fd0eff98a7f3083d4ae0fc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.08976549655199051,
-  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-1000",
-  "epoch": 0.4930966469428008,
+  "best_metric": 0.07017117738723755,
+  "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-2000",
+  "epoch": 0.9861932938856016,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -33,6 +33,32 @@
       "eval_samples_per_second": 673.996,
       "eval_steps_per_second": 2.659,
       "step": 1000
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 0.4097365140914917,
+      "learning_rate": 1.9852071005917162e-05,
+      "loss": 0.0869,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "grad_norm": 0.3858756422996521,
+      "learning_rate": 1.980276134122288e-05,
+      "loss": 0.0764,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9861932938856016,
+      "eval_accuracy": 0.981383845685049,
+      "eval_f1": 0.0,
+      "eval_loss": 0.07017117738723755,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 12.2763,
+      "eval_samples_per_second": 660.624,
+      "eval_steps_per_second": 2.607,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -61,7 +87,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 22523300934480.0,
+  "total_flos": 45024835218264.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null