Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d3a07ae6da47a6ffe951aea757172b91a104ade84e1133f83bdc65dbf0fced
+oid sha256:200b998b368c5e03deb5a46079d27bd6bfeb127cb7478a1f826abe16e3859b87
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84045260341781fd5db950741d3fad85d3e3ffa7a7b222322201c5e8b6f847ce
+oid sha256:b2ec8cdc4580a142ebac5e5b13f36ee4b4ac51a3bdadfa8fdc82d2d89d48533a
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e73cb909220f314d8bb2ce3c6b11d2d3d5ceafeda564a5681c9a84b2f38e70b
+oid sha256:1a536d8021983dc8ddd5749b3c7268784df09edd584c2a4cefb49b35a14b723b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c76e3ea474774b61d4cea19e7b0ce1e01ae99b8e67a194b3fa352d29ccf26585
+oid sha256:a4172e62d60e6611e586aefafe5c3cb9d66704232378d7f9895f5ee27089afad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.029792238026857376,
   "best_model_checkpoint": "doc-topic-model/checkpoint-29000",
-  "epoch": 3.575391443718407,
+  "epoch": 3.698680803846628,
   "eval_steps": 1000,
-  "global_step": 29000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -761,6 +761,32 @@
       "eval_samples_per_second": 308.757,
       "eval_steps_per_second": 19.3,
       "step": 29000
+    },
+    {
+      "epoch": 3.6370361237825177,
+      "grad_norm": 0.24183115363121033,
+      "learning_rate": 1.2725927752434966e-05,
+      "loss": 0.0276,
+      "step": 29500
+    },
+    {
+      "epoch": 3.698680803846628,
+      "grad_norm": 0.2443745732307434,
+      "learning_rate": 1.2602638392306746e-05,
+      "loss": 0.0268,
+      "step": 30000
+    },
+    {
+      "epoch": 3.698680803846628,
+      "eval_accuracy": 0.9894552169113323,
+      "eval_f1": 0.6908728345311786,
+      "eval_loss": 0.02983880043029785,
+      "eval_precision": 0.7564592430858806,
+      "eval_recall": 0.6357519688049545,
+      "eval_runtime": 26.5951,
+      "eval_samples_per_second": 304.981,
+      "eval_steps_per_second": 19.064,
+      "step": 30000
     }
   ],
   "logging_steps": 500,
@@ -768,7 +794,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 655800681523140.0,
+  "total_flos": 678379953845124.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null