Training in progress, step 50, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e56f1b3fdb067e33ce6519cdc1068a8fb24ab0ae9150f0ee3fb8f3df1f4862
+oid sha256:ab8f9a589855dfe062bc55c4cbf43161fdd39434d208ab4da4bb923fc4571543
 size 136989964

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71b4f533d1b2f49dbf9ae3dfb334b624c7ecea13ec371d987b4344882f4f93ca
+oid sha256:bf094d8965184086497516958531cb351a43d5f06289c6b018c968464c0ce7bc
 size 270158266

last-checkpoint/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.1691286563873291,
+  "best_metric": 0.18010935187339783,
   "best_model_checkpoint": "mgh6/TCS_Pair_base/checkpoint-50",
   "epoch": 0.011766090128250382,
   "eval_steps": 50,
@@ -10,17 +10,17 @@
   "log_history": [
     {
       "epoch": 0.011766090128250382,
-      "grad_norm": 0.9559330940246582,
+      "grad_norm": 1.275758147239685,
       "learning_rate": 9.988232525300071e-05,
-      "loss": 0.0558,
+      "loss": 0.0357,
       "step": 50
     },
     {
       "epoch": 0.011766090128250382,
-      "eval_loss": 0.1691286563873291,
-      "eval_runtime": 13.7268,
-      "eval_samples_per_second": 2043.961,
-      "eval_steps_per_second": 8.014,
+      "eval_loss": 0.18010935187339783,
+      "eval_runtime": 13.7184,
+      "eval_samples_per_second": 2045.21,
+      "eval_steps_per_second": 8.018,
       "step": 50
     }
   ],

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27dcd7710730b697986debc919311d1d500e36d98eafbe791513e17b9a041813
+oid sha256:d187f86b312ee0ac18cc1da048188fcd7b3a5f7e615bc0f2367cd66d541aaecd
 size 5240