Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7525456e4718a8232324e17900847eb138c40eb8a13f08af30897b05d4dbb20a
+oid sha256:34c58a50c849b52be08129cef2729104b91f5ebaf46457436ac0e5ddb0274590
 size 268290900

run-0/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b5c40bf565de678a7b2a120dc1b48cba67e6b742a649cde4ea668d3e60bc100
+oid sha256:34c58a50c849b52be08129cef2729104b91f5ebaf46457436ac0e5ddb0274590
 size 268290900

run-0/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97225c2f2d815f8567fac7963b89ed02ee2749b92ed6a734c122b9b4c52f59c7
+oid sha256:d28a1e8094eb6ab9663cd2fb830933ca60972e0ea885d2d509150b1efcbf6e84
 size 536643898

run-0/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a61c60e2a1f354f14fb973803108ea16a9c8c66946147c407c26a5211c4f3d
+oid sha256:e4f75fa3851d3548c8bbed0ee7c49e6a23f30f028b074a4398b38c7ecbd0f8e9
 size 1064

run-0/checkpoint-500/trainer_state.json

@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5664516129032258,
-      "eval_loss": 0.19607746601104736,
-      "eval_runtime": 14.7084,
-      "eval_samples_per_second": 210.764,
-      "eval_steps_per_second": 26.379,
+      "eval_accuracy": 0.5770967741935484,
+      "eval_loss": 0.21370309591293335,
+      "eval_runtime": 14.6609,
+      "eval_samples_per_second": 211.447,
+      "eval_steps_per_second": 26.465,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5254400372505188,
-      "learning_rate": 1.4758909853249476e-05,
-      "loss": 0.3095,
+      "grad_norm": 0.547938346862793,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.3338,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1908,
+  "max_steps": 1590,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
+  "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 150592805137236.0,
+  "total_flos": 213410670227832.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.37415226279908675,
-    "num_train_epochs": 6,
-    "temperature": 20
+    "alpha": 0.15887174499778411,
+    "num_train_epochs": 5,
+    "temperature": 9
   }
 }

run-0/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a23fbbc540f85f85c231e04787b50ee9cff5606fe542b5374adee325a60a5381
+oid sha256:278f8d33f8210fa6267daa5ada1e98b5fd52b1bb1fcfcfeeb3b0875f77b14e08
 size 5048

run-13/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39ba0586f9a77e8d868d7bf991235379f6b2e6dbd4e3ef95b7a111f800a6afba
+size 268290900

run-13/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42b0c005cb28c18d3c090c34b1183eeb25d71d214062ed329d6c9128a426a0be
+size 536643898

runs/May16_18-43-59_MainPC/events.out.tfevents.1715856619.MainPC.47240.15

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74a6b75fb7ceb6c4089e701b660f2416bed354782ad1f77b2dd3c68fbbf9a0d6
+size 25714

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288344ea2c5a779b9a25234da8b122db9300e5dd4f5af9aeef0293ff5355089b
+oid sha256:278f8d33f8210fa6267daa5ada1e98b5fd52b1bb1fcfcfeeb3b0875f77b14e08
 size 5048