Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7893501852c4ebe980b04ff3cc6cdd11f047df483a730cb46b0c1c27fd5daed4
+oid sha256:5348d2393066d4c6f6d98b99d5ac798f79e13400c498941a12da3a4f6a76dbea
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1566d4d27d1386fa7a40b193b2f2fa0dbf7a7e80028db05a7a43fdda8d39990
+oid sha256:09e30b8649b7b5a11efefdbe9b5eb7549cfce856efa5c154b1a1f4bc8a3b26e8
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dbd14664314587e06b50737451db97e76c60f7d3508ac8353b4bd7838898fa0
+oid sha256:a3e7c16db59721aea2b47c2269764fae7399d4a794f4f6442f42ff4514c3e44e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1260cc57e4a88ded88aecf62897d2b8b66c617e64f4670367137ba73628600a
+oid sha256:2a8a67c34da9d806e20456efe3535d49ffebd2cae0e0aa1b56dc6c7c3655acde
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.04972168058156967,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-4000",
-  "epoch": 0.49315744051288374,
+  "best_metric": 0.04525615647435188,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-5000",
+  "epoch": 0.6164468006411047,
   "eval_steps": 1000,
-  "global_step": 4000,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,32 @@
       "eval_samples_per_second": 310.744,
       "eval_steps_per_second": 19.424,
       "step": 4000
+    },
+    {
+      "epoch": 0.5548021205769942,
+      "grad_norm": 0.35589325428009033,
+      "learning_rate": 1.8890395758846014e-05,
+      "loss": 0.0523,
+      "step": 4500
+    },
+    {
+      "epoch": 0.6164468006411047,
+      "grad_norm": 0.4649755358695984,
+      "learning_rate": 1.876710639871779e-05,
+      "loss": 0.0485,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6164468006411047,
+      "eval_accuracy": 0.9850139657085525,
+      "eval_f1": 0.4096466253558868,
+      "eval_loss": 0.04525615647435188,
+      "eval_precision": 0.7589987587918908,
+      "eval_recall": 0.2805260341004664,
+      "eval_runtime": 27.21,
+      "eval_samples_per_second": 298.089,
+      "eval_steps_per_second": 18.633,
+      "step": 5000
     }
   ],
   "logging_steps": 500,
@@ -118,7 +144,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 90679866799536.0,
+  "total_flos": 113262248643048.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null