Training in progress, step 24000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:930d03daaada0ff5224634c3dea06f9de32e18a2542da3cc088b00a8e4bd551d
+oid sha256:ca0198ee7059c347160690c553d247336d24eb495722d177cedb32f54c9e357a
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efea08f3c6c6a9a3a89f4c5e8bbac3cd91ffecea14d84ceb27b8ebcf88f2570f
+oid sha256:5d143e47900c9b23372846634318a106311c5a735b9c0a978595ae5c988e8504
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6967da4512793ef6e21426b52cd19c3eb4b1b256a3d6b476438f0ef1f49d148a
+oid sha256:b0c47bc6814f3b2cc652539b879c8dd04a01b11a1d74628bcdc13005dca3efe8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:150212d20150d1c5b5ff61b4eed271faa1889b1591145619dfddb6c46eaf02ea
+oid sha256:dc4979df536fde7ecfc0fbbf848b5153088756d28c508a484bc722499762180f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.030529338866472244,
   "best_model_checkpoint": "doc-topic-model/checkpoint-23000",
-  "epoch": 2.8356552829490815,
+  "epoch": 2.9589446430773023,
   "eval_steps": 1000,
-  "global_step": 23000,
+  "global_step": 24000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -605,6 +605,32 @@
       "eval_samples_per_second": 297.439,
       "eval_steps_per_second": 18.592,
       "step": 23000
+    },
+    {
+      "epoch": 2.897299963013192,
+      "grad_norm": 0.44624337553977966,
+      "learning_rate": 1.4205400073973616e-05,
+      "loss": 0.029,
+      "step": 23500
+    },
+    {
+      "epoch": 2.9589446430773023,
+      "grad_norm": 0.19307683408260345,
+      "learning_rate": 1.4082110713845396e-05,
+      "loss": 0.0295,
+      "step": 24000
+    },
+    {
+      "epoch": 2.9589446430773023,
+      "eval_accuracy": 0.9891717930949455,
+      "eval_f1": 0.6669862715188494,
+      "eval_loss": 0.030626777559518814,
+      "eval_precision": 0.7755929454692885,
+      "eval_recall": 0.5850600198791956,
+      "eval_runtime": 26.6782,
+      "eval_samples_per_second": 304.031,
+      "eval_steps_per_second": 19.004,
+      "step": 24000
     }
   ],
   "logging_steps": 500,
@@ -612,7 +638,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 520245754792272.0,
+  "total_flos": 542875815965880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null