Training in progress, step 16000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5da07f01d11e7cf1f124df9dd2f52c4e20bf0c9bf3ba44386b1292846989a5e
+oid sha256:888f30c08fc871ee89b2ed65aa59014c51e45b84bf83ac3179b9deb9ed86470e
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a32b964788782d25c5cfaf98526f2525f15670d397a29b03a398f483d05036
+oid sha256:119d4d9a4c44dda0c9536517afae5273a65c3c1343185258bd68b1f9c6c0eca7
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99a9bfbfc42ab3ded4bf2d279ab34d2bb4755b1bd960316b66d8bb34b600c9e5
+oid sha256:569537b3349a1263ef5364a44403c07c16a743e01891e82c4eec71160306f641
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13ceccea3d47e3b422f8ecdba99d0d05619c28f4d13687698def4c8f457b9cad
+oid sha256:8ab36b245ea824451ef011c271839e80b2973196a36f183104d5550cef0ba7cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03276761621236801,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-15000",
-  "epoch": 1.849340401923314,
+  "best_metric": 0.0323067270219326,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-16000",
+  "epoch": 1.972629762051535,
   "eval_steps": 1000,
-  "global_step": 15000,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -397,6 +397,32 @@
       "eval_samples_per_second": 305.291,
       "eval_steps_per_second": 19.083,
       "step": 15000
+    },
+    {
+      "epoch": 1.9109850819874246,
+      "grad_norm": 0.3464473783969879,
+      "learning_rate": 1.6178029836025154e-05,
+      "loss": 0.0338,
+      "step": 15500
+    },
+    {
+      "epoch": 1.972629762051535,
+      "grad_norm": 0.2982787489891052,
+      "learning_rate": 1.605474047589693e-05,
+      "loss": 0.0347,
+      "step": 16000
+    },
+    {
+      "epoch": 1.972629762051535,
+      "eval_accuracy": 0.9886233680102373,
+      "eval_f1": 0.6415111190497456,
+      "eval_loss": 0.0323067270219326,
+      "eval_precision": 0.7711218464841654,
+      "eval_recall": 0.5492010092514719,
+      "eval_runtime": 26.354,
+      "eval_samples_per_second": 307.771,
+      "eval_steps_per_second": 19.238,
+      "step": 16000
     }
   ],
   "logging_steps": 500,
@@ -404,7 +430,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 339274711384200.0,
+  "total_flos": 361961780452488.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null