Training in progress, step 37000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9245d84373d3b12c27df7cecfd5cb67f503038217a09a8fa66c6ed11fabdb66d
+oid sha256:f8627cad5c624f2fb26b4f942ae71819338c569907663ae0a83bfe7382ac3366
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f393e50657c26885a52a8001da713333d43f6c421fad3acc87275790b0eede21
+oid sha256:6ffcc3d1d5e065cf01a0ffd0ff08d02cdf9cb2f2396b22ebf252cae3f8953fb0
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b686a640da84061f259c5a5a5135b005a1c3602970c796a5b2db1de5bbc4c327
+oid sha256:9fded32cfeef319ee8873f69bcab2da6809640bc4620c8fa8555c8101ccc25a0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:913eadf36f83dad6af3b7da8337c81eb368b5e4165fc481d8542ba2714a66944
+oid sha256:16e145b4cdcceb527960a8d79717273f4ffdd2ea856488ec0e35536163459bd8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.029198406264185905,
   "best_model_checkpoint": "doc-topic-model/checkpoint-33000",
-  "epoch": 4.4384169646159535,
+  "epoch": 4.561706324744175,
   "eval_steps": 1000,
-  "global_step": 36000,
+  "global_step": 37000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -943,6 +943,32 @@
       "eval_samples_per_second": 305.485,
       "eval_steps_per_second": 19.095,
       "step": 36000
+    },
+    {
+      "epoch": 4.5000616446800645,
+      "grad_norm": 0.3777313530445099,
+      "learning_rate": 1.0999876710639872e-05,
+      "loss": 0.0233,
+      "step": 36500
+    },
+    {
+      "epoch": 4.561706324744175,
+      "grad_norm": 0.43268105387687683,
+      "learning_rate": 1.0876587350511652e-05,
+      "loss": 0.0239,
+      "step": 37000
+    },
+    {
+      "epoch": 4.561706324744175,
+      "eval_accuracy": 0.9896252712011643,
+      "eval_f1": 0.6914485607114258,
+      "eval_loss": 0.029605692252516747,
+      "eval_precision": 0.7703794139744553,
+      "eval_recall": 0.6271886229834085,
+      "eval_runtime": 26.473,
+      "eval_samples_per_second": 306.388,
+      "eval_steps_per_second": 19.152,
+      "step": 37000
     }
   ],
   "logging_steps": 500,
@@ -950,7 +976,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 814212146245572.0,
+  "total_flos": 836798674117788.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null