Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5675e320d2c4be18cdd9a2e7fa185e892844a6eb982935748b8e37d2a530a6b
+oid sha256:33620587b37c196969d3f412f74ef041dcfeee8258db5933dc3c4540e70b1e43
 size 268290900

run-4/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1de8090ce06ee283276a4164fb3fc1cbb41f07f3933cb5b30a7a520d950cd8bb
+oid sha256:33620587b37c196969d3f412f74ef041dcfeee8258db5933dc3c4540e70b1e43
 size 268290900

run-4/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e69faad0714c984670392e3675174413cae0526b8ba454324c4847ed51c6aa8
+oid sha256:3bab979622485a1e70f82a64c3ec4aae99b0262391ec447afad3b7eae33df5ce
 size 536643898

run-4/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04366f62f8f88f5a8265df59adb051b320463277845db80e7fa43f13110c18c9
+oid sha256:98041bd7cae455426e290a1a0ee683bd5dd30893f7451fec3a464ae8995b17e4
 size 1064

run-4/checkpoint-500/trainer_state.json

@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5838709677419355,
-      "eval_loss": 0.19346614181995392,
-      "eval_runtime": 5.4448,
-      "eval_samples_per_second": 569.354,
-      "eval_steps_per_second": 11.938,
+      "eval_accuracy": 0.5887096774193549,
+      "eval_loss": 0.19886387884616852,
+      "eval_runtime": 5.4179,
+      "eval_samples_per_second": 572.175,
+      "eval_steps_per_second": 11.997,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5179193019866943,
-      "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3125,
+      "grad_norm": 0.5294517874717712,
+      "learning_rate": 1.650593990216632e-05,
+      "loss": 0.3203,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 3180,
+  "max_steps": 2862,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 10,
+  "num_train_epochs": 9,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -46,8 +46,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.022235028872426232,
-    "num_train_epochs": 10,
-    "temperature": 14
+    "alpha": 0.2686953507184725,
+    "num_train_epochs": 9,
+    "temperature": 11
   }
 }

run-4/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:159fa738a88fc0ad0d6dbfae73a0ed7e5769cb4f609b3dbe951019107ed7a999
+oid sha256:4996ee5340c8bdd4a572091ea0810dedaca2cbdaef100327b73cd59a04d73183
 size 5176

runs/Aug28_01-37-39_61274092231a/events.out.tfevents.1724812598.61274092231a.346.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc69ec5828ffcb996db73355af2135774dc2135de0e3a39b609cad2ecbe4226
+size 14088

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acaf4c14e96120a2900b5480a226f035f804f94ffa8a7b7292532c314d649801
+oid sha256:4996ee5340c8bdd4a572091ea0810dedaca2cbdaef100327b73cd59a04d73183
 size 5176