Training in progress, step 33000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4150ef93e58db4d6308ea29210374a402ff634d26d52ea62de69545ed96a3853
+oid sha256:1c9866f7feb041454f0d884ed22f12a7230ed92133e4442d1eb81d314899347c
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b2708415e149f35205fc2ac049735a0eaa5f155d3a7fe4bba1a4cfa7456f2ae
+oid sha256:108eba50364a89adc79847aab3c673b49e13821b7832fef64cbfa7ff4f082ea2
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c35fea5195e6c48d3ea6c940ae781996f29ddf0579b900158677bba8cb1acae0
+oid sha256:4e67ec7b754d8efaca864900c18163c0550fef5c3a773dc13bcf8dfba5fc5c64
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81177ac3d0d9bc362eb57ca51fb2bd6df328bfd0729899a6040d8b2236e297c
+oid sha256:41c41f6c3fe599a88a19f7677efd7b56c3400526a5584d54045dd78e0116921b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.02959488332271576,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-32000",
-  "epoch": 3.94525952410307,
+  "best_metric": 0.029198406264185905,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-33000",
+  "epoch": 4.068548884231291,
   "eval_steps": 1000,
-  "global_step": 32000,
+  "global_step": 33000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -839,6 +839,32 @@
       "eval_samples_per_second": 307.31,
       "eval_steps_per_second": 19.209,
       "step": 32000
+    },
+    {
+      "epoch": 4.0069042041671805,
+      "grad_norm": 0.43818220496177673,
+      "learning_rate": 1.1986191591665642e-05,
+      "loss": 0.0267,
+      "step": 32500
+    },
+    {
+      "epoch": 4.068548884231291,
+      "grad_norm": 0.440415620803833,
+      "learning_rate": 1.1862902231537418e-05,
+      "loss": 0.0242,
+      "step": 33000
+    },
+    {
+      "epoch": 4.068548884231291,
+      "eval_accuracy": 0.9897754858238492,
+      "eval_f1": 0.695839129884912,
+      "eval_loss": 0.029198406264185905,
+      "eval_precision": 0.77551212178162,
+      "eval_recall": 0.6310115452251701,
+      "eval_runtime": 26.505,
+      "eval_samples_per_second": 306.017,
+      "eval_steps_per_second": 19.128,
+      "step": 33000
     }
   ],
   "logging_steps": 500,
@@ -846,7 +872,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 723655623799980.0,
+  "total_flos": 746325072246276.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null