Upload 13 files

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45a04fe9da5fd31874472d45fcb72767481687b988e020568d52016e2cbc7f2
+oid sha256:436f36528e0cbad453619703d49a29667fa0654be011985336d1c2b872f526f8
 size 645975704

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce61d0ea58235490c4825f4090dd94b9e8512c88786dcf095db98da30c4d1b0
-size 1292087499
+oid sha256:1d2149a123e2aa314e8d5a4ff1af83d0915c9962275cc6c598c987ae667380d5
+size 1292087115

rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9129f688522cbf5074ed3368e37129e6207c159ca1fa46c55499c8edd77f43
+oid sha256:16b1f30ed08c0cb1f6faa13f9adf57b5673e7f65618010fb242bd0a3c4bb0882
 size 16389

rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21de8159d1625b9d3b0bc58aaf0f5d7a08041f34848b02531ede2496e95c4b22
+oid sha256:7758845bdfcf8fb1634f7caf35462f13639e0941bd48712fadea60c710ba3072
 size 16389

rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a368a4902b82f670aeadc98044d7d89a3418d2f388b2e5716f699f17c1ba4734
+oid sha256:4cf8621df71a49229ce61172ca361f37587ea13b70aa2190bf8d87a833f8ee10
 size 16389

rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e83bd6c48291dbb29300128d5147f1a762b2e5716f690ce6e45a98ec9894099f
+oid sha256:8384fc2bd470fae280e01edd29cc9a2e4a86f8bc2f8d3a58a46b96c73349e6db
 size 16389

rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:361985b39f1284b5feb5d413263eb65082264988a9165d0861070486596c40ab
+oid sha256:ddff82bc26542fb05efdcf2df590ed29e9d88dbb01de689d83c4414f8885608b
 size 16389

rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e903c9e955adb623d41954e6913b29513486d96d0842b4227e58c17af5983a
+oid sha256:209b7d10ef86fe6e7f8d1749c24e88e06e11f4d90000c239905b4be42662d348
 size 16389

rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f87836a1fd83de48b6db7a2199667192f87082204913bc584cd2ebb322d567a
+oid sha256:e5a2629cdd3b6c3a387977b70399124e4c1f9fe420cd68bca306733f6790d5e1
 size 16389

rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334fb0db4018fb69a8ca2d36ce9a89336f5a66162c5c652a516eed7b9d6beb18
+oid sha256:ef570fd2e0fd44060a913d5dfadb2f9f6ae4f10cfb213d7e257e5f528ff6a899
 size 16389

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43250e56e4270c5f004d1452fba91772f612821b91b33492716896d2d6057469
+oid sha256:13c878b5181f107dfcc1437e1d485b47bb6612c1058d82c3d92ef97b6425cab6
 size 1465

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 260,
+  "global_step": 156,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,62 +92,6 @@
       "eval_samples_per_second": 8.675,
       "eval_steps_per_second": 1.105,
       "step": 156
-    },
-    {
-      "epoch": 3.3662650602409636,
-      "grad_norm": 0.07343257963657379,
-      "learning_rate": 0.0002861234766624867,
-      "loss": 0.0345,
-      "mean_token_accuracy": 0.9456785363168573,
-      "num_tokens": 71027426.0,
-      "step": 175
-    },
-    {
-      "epoch": 3.8481927710843373,
-      "grad_norm": 0.04622579738497734,
-      "learning_rate": 0.0002293960964917063,
-      "loss": 0.0259,
-      "mean_token_accuracy": 0.9330729904770851,
-      "num_tokens": 81341930.0,
-      "step": 200
-    },
-    {
-      "epoch": 4.0,
-      "eval_loss": NaN,
-      "eval_mean_token_accuracy": 0.9852228583173549,
-      "eval_num_tokens": 84250831.0,
-      "eval_runtime": 41.6702,
-      "eval_samples_per_second": 8.855,
-      "eval_steps_per_second": 1.128,
-      "step": 208
-    },
-    {
-      "epoch": 4.327710843373494,
-      "grad_norm": 0.04485568404197693,
-      "learning_rate": 0.0001739556124639496,
-      "loss": 0.0208,
-      "mean_token_accuracy": 0.9436070158253962,
-      "num_tokens": 91589095.0,
-      "step": 225
-    },
-    {
-      "epoch": 4.809638554216868,
-      "grad_norm": 0.03364564850926399,
-      "learning_rate": 0.00012253518458496144,
-      "loss": 0.0185,
-      "mean_token_accuracy": 0.9403582978248596,
-      "num_tokens": 101826338.0,
-      "step": 250
-    },
-    {
-      "epoch": 5.0,
-      "eval_loss": NaN,
-      "eval_mean_token_accuracy": 0.9858830913584283,
-      "eval_num_tokens": 105323752.0,
-      "eval_runtime": 41.5429,
-      "eval_samples_per_second": 8.882,
-      "eval_steps_per_second": 1.131,
-      "step": 260
     }
   ],
   "logging_steps": 25,
@@ -167,7 +111,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.624520070050087e+18,
+  "total_flos": 2.7746000370139136e+18,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null