Training in progress, step 22000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed71bea38b1a4b19425083ef77e9c6708923f18049b6ef6e914d3ced810241bf
+oid sha256:77e1b1b9a71fe12de2625aafe17d204c9050cc3b840be974ca9c154f33792600
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7f1e848a4b029622a64cbd0bfe06d78fe250442d6c33ac87e81b55610eb45ed
+oid sha256:5de8a2a93ff5926b05c525f10bff0e9f5f76a365488c859fb45e61589c17c031
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe84531ec109f0f20a1db15d8e59e1379264da3a0908df0b1f889ed5d6aede6
+oid sha256:0428752c882180c63455dd1c620a454ed081701fa3221b2bfb3bfd35c2f26755
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a78dd9b349f1a9020e04c285031112bde568bdc116e1e35c8b5dbcba1e27dbc
+oid sha256:3511d924992961c141b1c147de496d4fa246a86a10dc3bf0866f556b584511e1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.030963797122240067,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-21000",
-  "epoch": 2.5890765626926395,
+  "best_metric": 0.0308150053024292,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-22000",
+  "epoch": 2.7123659228208608,
   "eval_steps": 1000,
-  "global_step": 21000,
+  "global_step": 22000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -553,6 +553,32 @@
       "eval_samples_per_second": 295.997,
       "eval_steps_per_second": 18.502,
       "step": 21000
+    },
+    {
+      "epoch": 2.65072124275675,
+      "grad_norm": 0.40730220079421997,
+      "learning_rate": 1.46985575144865e-05,
+      "loss": 0.0301,
+      "step": 21500
+    },
+    {
+      "epoch": 2.7123659228208608,
+      "grad_norm": 0.36121124029159546,
+      "learning_rate": 1.457526815435828e-05,
+      "loss": 0.0308,
+      "step": 22000
+    },
+    {
+      "epoch": 2.7123659228208608,
+      "eval_accuracy": 0.9891108569744225,
+      "eval_f1": 0.669448507270068,
+      "eval_loss": 0.0308150053024292,
+      "eval_precision": 0.7653191698632832,
+      "eval_recall": 0.5949231592629406,
+      "eval_runtime": 27.2748,
+      "eval_samples_per_second": 297.38,
+      "eval_steps_per_second": 18.589,
+      "step": 22000
     }
   ],
   "logging_steps": 500,
@@ -560,7 +586,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 474998070531168.0,
+  "total_flos": 497722453857792.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null