Training in progress, step 9000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3d01ccbc2f46468952e0767a827e92c923d0fe50acfbf704b2386092cccacb
+oid sha256:ddf1bfc49f8bed6aad2e4c5016354cc52549731b7590469d2197858f225c5564
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33811a66ae2f539db3741cebc74612b4148ddad8e6219231260bf9b7d0bd3be4
+oid sha256:9ad805ac9e0aa08c68c3b2e9a1b4c67ed8df59df43feba14474fa385fa188e3f
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7fcb3233d0cc25d1a48ce8cd416cdb8e7197f92de2264ae7016915d03ce48d
+oid sha256:f1e38a40d1825dfd9a57552feb8e16f14cff45e73fbdbac837799c9b3f9b3eb3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e039ca70063df243e36a1f08dbf7d4436dc130b61c968cb193766016893f85f5
+oid sha256:32298e2a33ad8a6cba203d5a5a0739432575ab280ab1aeeb554c098456f66de4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.037820931524038315,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-8000",
-  "epoch": 0.9863148810257675,
+  "best_metric": 0.03682604432106018,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-9000",
+  "epoch": 1.1096042411539884,
   "eval_steps": 1000,
-  "global_step": 8000,
+  "global_step": 9000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -215,6 +215,32 @@
       "eval_samples_per_second": 306.992,
       "eval_steps_per_second": 19.189,
       "step": 8000
+    },
+    {
+      "epoch": 1.047959561089878,
+      "grad_norm": 0.3540589213371277,
+      "learning_rate": 1.7904080877820246e-05,
+      "loss": 0.0392,
+      "step": 8500
+    },
+    {
+      "epoch": 1.1096042411539884,
+      "grad_norm": 0.27701956033706665,
+      "learning_rate": 1.7780791517692026e-05,
+      "loss": 0.0378,
+      "step": 9000
+    },
+    {
+      "epoch": 1.1096042411539884,
+      "eval_accuracy": 0.9872600994534172,
+      "eval_f1": 0.5714966634890372,
+      "eval_loss": 0.03682604432106018,
+      "eval_precision": 0.7587647133274269,
+      "eval_recall": 0.45836837678721615,
+      "eval_runtime": 26.3246,
+      "eval_samples_per_second": 308.114,
+      "eval_steps_per_second": 19.26,
+      "step": 9000
     }
   ],
   "logging_steps": 500,
@@ -222,7 +248,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 180973116422424.0,
+  "total_flos": 203560680801816.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null