Training in progress, step 21000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9f51a783df8cd4184c8ff6322283ae5b7793d6c9193bbf60e1261cd4e2663c
+oid sha256:ed71bea38b1a4b19425083ef77e9c6708923f18049b6ef6e914d3ced810241bf
 size 567860028

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86f00b741bf0124136a44f7bf6d1fcd9a8a0633a83dd3007eca0567fb88fac08
+oid sha256:a7f1e848a4b029622a64cbd0bfe06d78fe250442d6c33ac87e81b55610eb45ed
 size 1135783354

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5739ad1470dd61f60c847b4c724972fef526d7699c4e508ced265ccae5231b88
+oid sha256:ffe84531ec109f0f20a1db15d8e59e1379264da3a0908df0b1f889ed5d6aede6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6513724227630151c79051ec6207366b00d809ac45184982374810ca6fb630
+oid sha256:5a78dd9b349f1a9020e04c285031112bde568bdc116e1e35c8b5dbcba1e27dbc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.03158288821578026,
-  "best_model_checkpoint": "doc-topic-model/checkpoint-20000",
-  "epoch": 2.4657872025644187,
+  "best_metric": 0.030963797122240067,
+  "best_model_checkpoint": "doc-topic-model/checkpoint-21000",
+  "epoch": 2.5890765626926395,
   "eval_steps": 1000,
-  "global_step": 20000,
+  "global_step": 21000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -527,6 +527,32 @@
       "eval_samples_per_second": 308.714,
       "eval_steps_per_second": 19.297,
       "step": 20000
+    },
+    {
+      "epoch": 2.5274318826285294,
+      "grad_norm": 0.37221288681030273,
+      "learning_rate": 1.4945136234742942e-05,
+      "loss": 0.0307,
+      "step": 20500
+    },
+    {
+      "epoch": 2.5890765626926395,
+      "grad_norm": 0.37331074476242065,
+      "learning_rate": 1.4821846874614722e-05,
+      "loss": 0.031,
+      "step": 21000
+    },
+    {
+      "epoch": 2.5890765626926395,
+      "eval_accuracy": 0.9891434507133069,
+      "eval_f1": 0.6675346092088703,
+      "eval_loss": 0.030963797122240067,
+      "eval_precision": 0.7718787635487756,
+      "eval_recall": 0.5880418992277697,
+      "eval_runtime": 27.4023,
+      "eval_samples_per_second": 295.997,
+      "eval_steps_per_second": 18.502,
+      "step": 21000
     }
   ],
   "logging_steps": 500,
@@ -534,7 +560,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 10,
   "save_steps": 1000,
-  "total_flos": 452435382324000.0,
+  "total_flos": 474998070531168.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null