Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80683dcd7bad6070adbf4a6cffeae9bd86f1e04d3dd349da72feb2cb66c2f5e7
+oid sha256:f0cc4778c604548cc03ed426cc23687a92f886997199dd2cf98d6ba3dcdbfe3b
 size 268290900

run-4/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34c58a50c849b52be08129cef2729104b91f5ebaf46457436ac0e5ddb0274590
+oid sha256:f0cc4778c604548cc03ed426cc23687a92f886997199dd2cf98d6ba3dcdbfe3b
 size 268290900

run-4/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d28a1e8094eb6ab9663cd2fb830933ca60972e0ea885d2d509150b1efcbf6e84
+oid sha256:2219825dffd50ded2ac97c5ef392d5520e0cd579c8dac0addd5b05f923a40510
 size 536643898

run-4/checkpoint-500/scheduler.pt

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

run-4/checkpoint-500/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-4/checkpoint-500/trainer_state.json

@@ -10,32 +10,32 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5770967741935484,
-      "eval_loss": 0.21370309591293335,
-      "eval_runtime": 13.9985,
-      "eval_samples_per_second": 221.453,
-      "eval_steps_per_second": 27.717,
+      "eval_accuracy": 0.5816129032258065,
+      "eval_loss": 0.20736075937747955,
+      "eval_runtime": 17.0342,
+      "eval_samples_per_second": 181.987,
+      "eval_steps_per_second": 22.778,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.547938346862793,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.3338,
+      "grad_norm": 0.5436314940452576,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3269,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 1908,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "total_flos": 130072209152340.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.6150671860788094,
-    "num_train_epochs": 5,
-    "temperature": 9
+    "alpha": 0.1269072763270631,
+    "num_train_epochs": 6,
+    "temperature": 10
   }
 }

run-4/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278f8d33f8210fa6267daa5ada1e98b5fd52b1bb1fcfcfeeb3b0875f77b14e08
+oid sha256:853140cfe9700b0f73b0cfadaae534b2ccf66ea184486e4df0f7ec3edaf66498
 size 5048

runs/May17_05-23-10_MainPC/events.out.tfevents.1715892747.MainPC.51768.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c14eef6632bfc8e9c26a557e1d5bab585b9c485c0494c22febfa56cbda88b114
+size 13062

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:651d2dfaf598da9232615029aef591cddb19f62ee5e131248da1afc5915c5227
+oid sha256:853140cfe9700b0f73b0cfadaae534b2ccf66ea184486e4df0f7ec3edaf66498
 size 5048