Training in progress, step 28000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7245803078fac2f6255059cb485ab88160cd760360b664789085d780d2500207
+oid sha256:62738e68c380b84e7ba5e70ed74beaef6dca37767638644ad9080404c2bc289d
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32e26a150bf4dd6f1ce2b2121ef1b2bd1b961eec79f861a295ea1c13e225ce5e
+oid sha256:0bc2b2d9610345b393e6a11d4aa099c4db304e875ebd163d9077cf1d6e12b09e
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11a441c71135cb22b0428492e00c565a64170f2a3da561a8d3a1b52db0b9efbc
+oid sha256:c2b9d03691297dc71e66ee41b307397d343b7d27a3f7ccd654ec08e89e0e9ad3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b921d2b6bf7a59d1fc691704cd7a4e3a1229a1cb800d6477437d3eb81e3bf9
+oid sha256:43b205b52a82ca38a3bbc35d27e64c93a0ac87167c9e077557ca8c95371c1062
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.030225617811083794,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-27000",
-  "epoch": 3.328812723461965,
+  "best_metric": 0.029832862317562103,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-28000",
+  "epoch": 3.4521020835901863,
   "eval_steps": 1000,
-  "global_step": 27000,
+  "global_step": 28000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -709,6 +709,32 @@
       "eval_samples_per_second": 308.564,
       "eval_steps_per_second": 19.288,
       "step": 27000
+    },
+    {
+      "epoch": 3.3904574035260757,
+      "grad_norm": 0.3788999021053314,
+      "learning_rate": 1.3219085192947848e-05,
+      "loss": 0.0271,
+      "step": 27500
+    },
+    {
+      "epoch": 3.4521020835901863,
+      "grad_norm": 0.41983020305633545,
+      "learning_rate": 1.3095795832819628e-05,
+      "loss": 0.0267,
+      "step": 28000
+    },
+    {
+      "epoch": 3.4521020835901863,
+      "eval_accuracy": 0.9894623025067419,
+      "eval_f1": 0.68241223199795,
+      "eval_loss": 0.029832862317562103,
+      "eval_precision": 0.7730043541364296,
+      "eval_recall": 0.6108265157886689,
+      "eval_runtime": 28.4628,
+      "eval_samples_per_second": 284.968,
+      "eval_steps_per_second": 17.813,
+      "step": 28000
     }
   ],
   "logging_steps": 500,
@@ -716,7 +742,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 610656647979636.0,
+  "total_flos": 633129160062492.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null