Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acf0b2d1d26bf33682e967b6b91bdcf5446cccfd49cd15453c916d790a9c6982
+oid sha256:b0d790ea68d77ef3d1d7fb05de8c161bc92e51cd462a79c33cdc4f084e2e650c
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ec8f59145b666c3d41dfe265796bfa85e7e9c39ccccbc992c0bab0d8337d19
+oid sha256:1af70a843c8ffebff58005144ee6a3a52f834ab4cc7cf4913d054fb186bd4cc2
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b3034c5b6516d233c5af2fea54728bfff878bec317e58b6d92ba886ec31a21b
+oid sha256:cd480c50602ef45bc90ce5c46d666493f12dce9ec32352aaa0b938ad19afca1c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcd4f053ce950a9e578d4e070881875c02e1cb9a7028bdaed37519a73ac227e9
+oid sha256:b70978d56cb08da58d27c0b422243f003e8813e8b855d1f2a64e9ad00321ef7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03590531274676323,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-10000",
-  "epoch": 1.2328936012822094,
+  "best_metric": 0.034964971244335175,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-11000",
+  "epoch": 1.3561829614104304,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,32 @@
       "eval_samples_per_second": 303.556,
       "eval_steps_per_second": 18.975,
       "step": 10000
+    },
+    {
+      "epoch": 1.2945382813463198,
+      "grad_norm": 0.3471441864967346,
+      "learning_rate": 1.7410923437307362e-05,
+      "loss": 0.0375,
+      "step": 10500
+    },
+    {
+      "epoch": 1.3561829614104304,
+      "grad_norm": 0.43855801224708557,
+      "learning_rate": 1.728763407717914e-05,
+      "loss": 0.0369,
+      "step": 11000
+    },
+    {
+      "epoch": 1.3561829614104304,
+      "eval_accuracy": 0.9877617596084216,
+      "eval_f1": 0.601660516605166,
+      "eval_loss": 0.034964971244335175,
+      "eval_precision": 0.7582839204743634,
+      "eval_recall": 0.4986619772153834,
+      "eval_runtime": 26.523,
+      "eval_samples_per_second": 305.81,
+      "eval_steps_per_second": 19.115,
+      "step": 11000
     }
   ],
   "logging_steps": 500,
@@ -274,7 +300,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 226142026138152.0,
+  "total_flos": 248713006402728.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null