Training in progress, step 31000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200b998b368c5e03deb5a46079d27bd6bfeb127cb7478a1f826abe16e3859b87
+oid sha256:bacf8a7eab59fb1966c2948f6183a87b1e12612562c43e3e00be0845f7dfd3a9
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2ec8cdc4580a142ebac5e5b13f36ee4b4ac51a3bdadfa8fdc82d2d89d48533a
+oid sha256:84b2fd565ca572922065d0ca702f1af7af2ba8bef22f6dac651b24a5e385367d
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a536d8021983dc8ddd5749b3c7268784df09edd584c2a4cefb49b35a14b723b
+oid sha256:d68ccaff5a373330ed15f4450e2f0f4e7ec0f2a426a61b0b530e080dd32f44ed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4172e62d60e6611e586aefafe5c3cb9d66704232378d7f9895f5ee27089afad
+oid sha256:a4e103e890947dce8b5cc8f45d5f7726e35dcc2af236d3ec8833bd262720ccd6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.029792238026857376,
   "best_model_checkpoint": "doc-topic-model/checkpoint-29000",
-  "epoch": 3.698680803846628,
+  "epoch": 3.821970163974849,
   "eval_steps": 1000,
-  "global_step": 30000,
+  "global_step": 31000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -787,6 +787,32 @@
       "eval_samples_per_second": 304.981,
       "eval_steps_per_second": 19.064,
       "step": 30000
+    },
+    {
+      "epoch": 3.7603254839107385,
+      "grad_norm": 0.4146226942539215,
+      "learning_rate": 1.2479349032178524e-05,
+      "loss": 0.0266,
+      "step": 30500
+    },
+    {
+      "epoch": 3.821970163974849,
+      "grad_norm": 0.2495744824409485,
+      "learning_rate": 1.2356059672050302e-05,
+      "loss": 0.0265,
+      "step": 31000
+    },
+    {
+      "epoch": 3.821970163974849,
+      "eval_accuracy": 0.9894934791265445,
+      "eval_f1": 0.6934843724160741,
+      "eval_loss": 0.029959995299577713,
+      "eval_precision": 0.7549734449545413,
+      "eval_recall": 0.6412569768330912,
+      "eval_runtime": 26.4331,
+      "eval_samples_per_second": 306.851,
+      "eval_steps_per_second": 19.181,
+      "step": 31000
     }
   ],
   "logging_steps": 500,
@@ -794,7 +820,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 678379953845124.0,
+  "total_flos": 700958189659932.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null