Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2265efdbd127f32817bf80110d8d6f541a55048b2e22b7e0e6227a688a9ef047
+oid sha256:f09ba02af072f6dab1b31924b201f644e12e95c27ead4dc9623741e011906d93
 size 268290900

run-0/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:278c22619c47ca29f599e7780b2b974771cc416649b263f524b88bb8b1ed6ac4
+oid sha256:f09ba02af072f6dab1b31924b201f644e12e95c27ead4dc9623741e011906d93
 size 268290900

run-0/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da1f08b5f90a40897bed8c4857f5874a16eb498c2423dd4769c586a7c878c84f
+oid sha256:875d936002e9ba81a59c4d5636d51888d66a375fc0c698deb36655a1e91c1333
 size 536643898

run-0/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d97f7c1be085852e2ffd2fe2f8a493a080e2b2858e2f3baf642fe214e035a0
+oid sha256:693ec081eb0fa0af7d13e289edb194450dd19fdada23346e2af4292ea228535f
 size 1064

run-0/checkpoint-1500/trainer_state.json

@@ -10,66 +10,66 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6083870967741936,
-      "eval_loss": 0.26111724972724915,
-      "eval_runtime": 5.07,
-      "eval_samples_per_second": 611.445,
-      "eval_steps_per_second": 12.821,
+      "eval_accuracy": 0.5887096774193549,
+      "eval_loss": 0.19886387884616852,
+      "eval_runtime": 5.1732,
+      "eval_samples_per_second": 599.241,
+      "eval_steps_per_second": 12.565,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.612690269947052,
-      "learning_rate": 1.371069182389937e-05,
-      "loss": 0.4067,
+      "grad_norm": 0.5294517874717712,
+      "learning_rate": 1.650593990216632e-05,
+      "loss": 0.3203,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8261290322580646,
-      "eval_loss": 0.1251312643289566,
-      "eval_runtime": 5.2675,
-      "eval_samples_per_second": 588.512,
-      "eval_steps_per_second": 12.34,
+      "eval_accuracy": 0.8193548387096774,
+      "eval_loss": 0.09618715196847916,
+      "eval_runtime": 5.2244,
+      "eval_samples_per_second": 593.365,
+      "eval_steps_per_second": 12.442,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8719354838709678,
-      "eval_loss": 0.08443494886159897,
-      "eval_runtime": 5.1546,
-      "eval_samples_per_second": 601.399,
-      "eval_steps_per_second": 12.61,
+      "eval_accuracy": 0.8783870967741936,
+      "eval_loss": 0.06421981006860733,
+      "eval_runtime": 5.1205,
+      "eval_samples_per_second": 605.405,
+      "eval_steps_per_second": 12.694,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5761224031448364,
-      "learning_rate": 7.421383647798742e-06,
-      "loss": 0.1453,
+      "grad_norm": 0.44660821557044983,
+      "learning_rate": 1.3011879804332637e-05,
+      "loss": 0.1116,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.8880645161290323,
-      "eval_loss": 0.06863659620285034,
-      "eval_runtime": 5.2147,
-      "eval_samples_per_second": 594.479,
-      "eval_steps_per_second": 12.465,
+      "eval_accuracy": 0.8996774193548387,
+      "eval_loss": 0.04962550476193428,
+      "eval_runtime": 5.0817,
+      "eval_samples_per_second": 610.038,
+      "eval_steps_per_second": 12.791,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.40807998180389404,
-      "learning_rate": 1.1320754716981133e-06,
-      "loss": 0.0989,
+      "grad_norm": 0.3033629357814789,
+      "learning_rate": 9.517819706498952e-06,
+      "loss": 0.0713,
       "step": 1500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1590,
+  "max_steps": 2862,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 9,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -83,12 +83,12 @@
       "attributes": {}
     }
   },
-  "total_flos": 391368939443328.0,
+  "total_flos": 501007715336436.0,
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.006505868879858823,
-    "num_train_epochs": 5,
-    "temperature": 4
+    "alpha": 0.260556849082234,
+    "num_train_epochs": 9,
+    "temperature": 11
   }
 }

run-0/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe43401e68c8a3628adf33b38f6ac638a3a3f3bc1dcbe05d52f58aece31629f
+oid sha256:a815016dfca6056394449b7eec53142e869a6e9ff738e6f9557bb4382010c025
 size 5240

runs/Oct11_17-03-17_c179252869f4/events.out.tfevents.1728666603.c179252869f4.732.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e4607fd143d4548a3c3e4f485b963b6458f636733bf845fc8a3470c8ce7d81a
-size 26509
+oid sha256:fb736dc40b96ecda84b56e9177f908f9af50a03867c66f1e4cfac792703f5f00
+size 27043