Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:766d04adb5be225c37b37a5464417e7a04c07a2aaab2cdfe053777b6b1a386e5
+oid sha256:0bd32a034cff8c6216a16572ad2d88a8986c1f2a93a7e1bba4db41998b4e69ad
 size 268290900

run-3/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847b25893f634ae7ae19c7fa981b031b671da55fceaff107c9c6fd1535ba9bd9
+oid sha256:866be8cdc735bbe36a639244e641a1ac7cb151100c189abd5e0204a9b16f0c3b
 size 268290900

run-3/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbdf97ee43485482022c7936b134134b1d804f6bddceb5646e66726f0d638653
+oid sha256:0a5957e7a6bfaac777273b29656197645c0696c422bfdd157dc5bc4f63c4e05a
 size 536643898

run-3/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f182501c34e4ea3ebc7617d27edab7e1367582b147e518cd90295ec7f2eaa0f
+oid sha256:60ef01273aaa599804d51a93c6c0c61874ebd50ab9e135a21aab5f7cd0e6487a
 size 1064

run-3/checkpoint-1000/trainer_state.json

@@ -10,50 +10,50 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6083870967741936,
-      "eval_loss": 0.26111724972724915,
-      "eval_runtime": 5.392,
-      "eval_samples_per_second": 574.924,
-      "eval_steps_per_second": 12.055,
+      "eval_accuracy": 0.5980645161290322,
+      "eval_loss": 0.2370469570159912,
+      "eval_runtime": 5.499,
+      "eval_samples_per_second": 563.735,
+      "eval_steps_per_second": 11.82,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.612690269947052,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.4067,
+      "grad_norm": 0.5828151106834412,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3737,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8261290322580646,
-      "eval_loss": 0.1251312643289566,
-      "eval_runtime": 5.4108,
-      "eval_samples_per_second": 572.929,
-      "eval_steps_per_second": 12.013,
+      "eval_accuracy": 0.8264516129032258,
+      "eval_loss": 0.11328593641519547,
+      "eval_runtime": 5.8606,
+      "eval_samples_per_second": 528.955,
+      "eval_steps_per_second": 11.091,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8719354838709678,
-      "eval_loss": 0.08443494886159897,
-      "eval_runtime": 5.5128,
-      "eval_samples_per_second": 562.324,
-      "eval_steps_per_second": 11.791,
+      "eval_accuracy": 0.8780645161290322,
+      "eval_loss": 0.0755920559167862,
+      "eval_runtime": 5.4689,
+      "eval_samples_per_second": 566.841,
+      "eval_steps_per_second": 11.885,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5761224031448364,
-      "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1453,
+      "grad_norm": 0.5158044099807739,
+      "learning_rate": 9.517819706498952e-06,
+      "loss": 0.1316,
       "step": 1000
     }
   ],
   "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,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -71,8 +71,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.4777308452793029,
-    "num_train_epochs": 5,
-    "temperature": 4
+    "alpha": 0.5973659898080927,
+    "num_train_epochs": 6,
+    "temperature": 5
   }
 }

run-3/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef5b259539127ef5ddc697d31b7e7180caca610f845f70ff2cba869a6149cf5
+oid sha256:a9bfc1f73d75af662c164817dfdb380c8286c5e24841175e1b2797e416869742
 size 5240

run-3/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278c22619c47ca29f599e7780b2b974771cc416649b263f524b88bb8b1ed6ac4
+oid sha256:0bd32a034cff8c6216a16572ad2d88a8986c1f2a93a7e1bba4db41998b4e69ad
 size 268290900

run-3/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da1f08b5f90a40897bed8c4857f5874a16eb498c2423dd4769c586a7c878c84f
+oid sha256:2c98e9f0341d0bf3c55c8c70062aec5e4400eeb877ed5dc30dd8c1e7c65951a4
 size 536643898

run-3/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d97f7c1be085852e2ffd2fe2f8a493a080e2b2858e2f3baf642fe214e035a0
+oid sha256:55c8d3ce0734337fc0c187ca5543b4c70ca45d996531f199209b3a0c2a798109
 size 1064

run-3/checkpoint-1500/trainer_state.json

@@ -10,66 +10,66 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6083870967741936,
-      "eval_loss": 0.26111724972724915,
-      "eval_runtime": 5.392,
-      "eval_samples_per_second": 574.924,
-      "eval_steps_per_second": 12.055,
+      "eval_accuracy": 0.5980645161290322,
+      "eval_loss": 0.2370469570159912,
+      "eval_runtime": 5.499,
+      "eval_samples_per_second": 563.735,
+      "eval_steps_per_second": 11.82,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.612690269947052,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.4067,
+      "grad_norm": 0.5828151106834412,
+      "learning_rate": 1.4758909853249476e-05,
+      "loss": 0.3737,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8261290322580646,
-      "eval_loss": 0.1251312643289566,
-      "eval_runtime": 5.4108,
-      "eval_samples_per_second": 572.929,
-      "eval_steps_per_second": 12.013,
+      "eval_accuracy": 0.8264516129032258,
+      "eval_loss": 0.11328593641519547,
+      "eval_runtime": 5.8606,
+      "eval_samples_per_second": 528.955,
+      "eval_steps_per_second": 11.091,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8719354838709678,
-      "eval_loss": 0.08443494886159897,
-      "eval_runtime": 5.5128,
-      "eval_samples_per_second": 562.324,
-      "eval_steps_per_second": 11.791,
+      "eval_accuracy": 0.8780645161290322,
+      "eval_loss": 0.0755920559167862,
+      "eval_runtime": 5.4689,
+      "eval_samples_per_second": 566.841,
+      "eval_steps_per_second": 11.885,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5761224031448364,
-      "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1453,
+      "grad_norm": 0.5158044099807739,
+      "learning_rate": 9.517819706498952e-06,
+      "loss": 0.1316,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8880645161290323,
-      "eval_loss": 0.06863659620285034,
-      "eval_runtime": 5.4981,
-      "eval_samples_per_second": 563.835,
-      "eval_steps_per_second": 11.822,
+      "eval_accuracy": 0.8916129032258064,
+      "eval_loss": 0.0598440058529377,
+      "eval_runtime": 5.4778,
+      "eval_samples_per_second": 565.924,
+      "eval_steps_per_second": 11.866,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.40807998180389404,
-      "learning_rate": 1.1320754716981133e-06,
-      "loss": 0.0989,
+      "grad_norm": 0.3741317093372345,
+      "learning_rate": 4.276729559748428e-06,
+      "loss": 0.0865,
       "step": 1500
     }
   ],
   "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,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -87,8 +87,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.4777308452793029,
-    "num_train_epochs": 5,
-    "temperature": 4
+    "alpha": 0.5973659898080927,
+    "num_train_epochs": 6,
+    "temperature": 5
   }
 }

run-3/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef5b259539127ef5ddc697d31b7e7180caca610f845f70ff2cba869a6149cf5
+oid sha256:a9bfc1f73d75af662c164817dfdb380c8286c5e24841175e1b2797e416869742
 size 5240

runs/Oct12_06-40-39_b76c1be2ae55/events.out.tfevents.1728717921.b76c1be2ae55.1423.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80de71b8d04aa01ccc8b2c7f4385a34db4465102a8954485ac0fa5be99ce3ef5
-size 13832
+oid sha256:db204770a25b61bd1eee1e9fca18f2d640009027731c8ec6dc2dd67bae369588
+size 15366