Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180c59532e67e2a42ff36f33e417d2684be2f4099397090c274a2291b88d4251
+oid sha256:7893501852c4ebe980b04ff3cc6cdd11f047df483a730cb46b0c1c27fd5daed4
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da38f6314d96ba0c6df902c61eafa71a0bdf1d073b8b7027ae16768d28605572
+oid sha256:b1566d4d27d1386fa7a40b193b2f2fa0dbf7a7e80028db05a7a43fdda8d39990
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2356e526daacaf3cddef386079df98ea0601ca2882bbb34b98fe16bdae5145ee
+oid sha256:4dbd14664314587e06b50737451db97e76c60f7d3508ac8353b4bd7838898fa0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd2c3e094b5ddaeb89ee4b7c0b707aa950f4b94460991a5994dffa66d0682ac2
+oid sha256:f1260cc57e4a88ded88aecf62897d2b8b66c617e64f4670367137ba73628600a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.057068832218647,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-3000",
-  "epoch": 0.3698680803846628,
+  "best_metric": 0.04972168058156967,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-4000",
+  "epoch": 0.49315744051288374,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,32 @@
       "eval_samples_per_second": 299.987,
       "eval_steps_per_second": 18.751,
       "step": 3000
+    },
+    {
+      "epoch": 0.4315127604487733,
+      "grad_norm": 0.3704540431499481,
+      "learning_rate": 1.9136974479102454e-05,
+      "loss": 0.0573,
+      "step": 3500
+    },
+    {
+      "epoch": 0.49315744051288374,
+      "grad_norm": 0.36780521273612976,
+      "learning_rate": 1.9013685118974234e-05,
+      "loss": 0.055,
+      "step": 4000
+    },
+    {
+      "epoch": 0.49315744051288374,
+      "eval_accuracy": 0.9837343071775665,
+      "eval_f1": 0.28778853313477293,
+      "eval_loss": 0.04972168058156967,
+      "eval_precision": 0.7635824827132038,
+      "eval_recall": 0.17730713357290312,
+      "eval_runtime": 26.1019,
+      "eval_samples_per_second": 310.744,
+      "eval_steps_per_second": 19.424,
+      "step": 4000
     }
   ],
   "logging_steps": 500,
@@ -92,7 +118,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 67961702515968.0,
+  "total_flos": 90679866799536.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null