Training in progress, step 1000

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857c207e688a96a1a5e883ff5542ef5f4ad2f935746b7a0f07e9013d92ea3fc8
+oid sha256:9169c18fe6ab1d35cc81db6d46d303cd839fd2d5478f7e6c93b153bd39b56bd4
 size 268290900

run-3/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c89e1b305aca1af63f0856728d70c825280e83ef09ae55dfaa5eb077df8ceb6
+oid sha256:9169c18fe6ab1d35cc81db6d46d303cd839fd2d5478f7e6c93b153bd39b56bd4
 size 268290900

run-3/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b325d3c001a1b92f5834a1445544e42cac6e26e0219b0de1b6d15c8469f996a3
+oid sha256:9916b9668bdb6a3048f5951502299919b5abb28cc16de4ff073243ad2cd9fc3d
 size 536643898

run-3/checkpoint-1000/tokenizer.json

@@ -1,11 +1,6 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
+  "truncation": null,
   "padding": null,
   "added_tokens": [
     {

run-3/checkpoint-1000/trainer_state.json

@@ -10,43 +10,43 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.582258064516129,
-      "eval_loss": 0.22278250753879547,
-      "eval_runtime": 14.0007,
-      "eval_samples_per_second": 221.418,
-      "eval_steps_per_second": 27.713,
+      "eval_accuracy": 0.5741935483870968,
+      "eval_loss": 0.21085834503173828,
+      "eval_runtime": 16.9112,
+      "eval_samples_per_second": 183.311,
+      "eval_steps_per_second": 22.943,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5593786239624023,
+      "grad_norm": 0.5454378724098206,
       "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3474,
+      "loss": 0.3294,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8080645161290323,
-      "eval_loss": 0.11308418214321136,
-      "eval_runtime": 14.7627,
-      "eval_samples_per_second": 209.988,
-      "eval_steps_per_second": 26.282,
+      "eval_accuracy": 0.805483870967742,
+      "eval_loss": 0.10886585712432861,
+      "eval_runtime": 17.9646,
+      "eval_samples_per_second": 172.561,
+      "eval_steps_per_second": 21.598,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8680645161290322,
-      "eval_loss": 0.07942821085453033,
-      "eval_runtime": 14.9523,
-      "eval_samples_per_second": 207.326,
-      "eval_steps_per_second": 25.949,
+      "eval_accuracy": 0.8641935483870967,
+      "eval_loss": 0.07757259905338287,
+      "eval_runtime": 16.7496,
+      "eval_samples_per_second": 185.079,
+      "eval_steps_per_second": 23.165,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5294380187988281,
+      "grad_norm": 0.5058844685554504,
       "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1306,
+      "loss": 0.1255,
       "step": 1000
     }
   ],
@@ -59,8 +59,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.5645557808027578,
+    "alpha": 0.9132537559988115,
     "num_train_epochs": 5,
-    "temperature": 7
+    "temperature": 10
   }
 }

run-3/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:680b691392cebb0d600b63a5b93814d3fbbfedd5e88be725429c4eb7bd20e96e
+oid sha256:651d2dfaf598da9232615029aef591cddb19f62ee5e131248da1afc5915c5227
 size 5048

runs/May17_05-23-10_MainPC/events.out.tfevents.1715892449.MainPC.51768.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e778bbfdbbd7d8b6ee90afb112faed54191bd1d9eee9218a3dc8e49348fa28e
-size 13062
+oid sha256:2f3430182fee1733e835c772c25d90960564b3d254866a770b3a40402784bad2
+size 13919