Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5de0b5f9d9e76a98c2e6888ea997e7db312eaa8a2fcba275b6b6ded1e0a116c8
+oid sha256:d2dd66d0b8c7a186e9008078ca3d6fe21f2891b5161a36901aca7a385fb017ac
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f39fa5338c97b5d5557e8e9567f8db6e2e0d56b17bbad34aea4907992e36042
+oid sha256:c3dec126f4ec0b2b6a8ea60ad3d2edc5ef2b550a3751bbede769ea8b4b6f8f95
 size 27273018

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a90f2ed015b8c5680f7df68fc79d87a6cf38bf3907db297738d34c64d5c9635
+oid sha256:6d7dce7e0170aa34175b5269717b961d1ffe522fb28bfeef670f097012d24db8
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981bbea8034bbbae85baf44fc3a7f5bd1463eae4931e71f483cdca42e7a37e82
+oid sha256:e37fdc46c9ceacc4f09fb079980eedde483f3261a807a717ac38bb84282cfbc0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cca749a55d863ce18a73bc0ef2f3abbffa81b687698aff70716c9f05ebb977e
+oid sha256:18dd44bba8ec82bdc5a999dd503ca41e696d9d7a9a02f9a40556aba1f7d284e1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce143f3192cb1b2e626d251c64dac68350718e07c33521f586159568d189c078
+oid sha256:3c9f53c748ab56977e5d0b2dabfb603fcb816a36a8711e81b4f65d5a8fb7d27c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89ffc445067fef9d6d02bb3ff9e61d5e3209e6fa67c7259b3b364b90dbaa2cd
+oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2881844380403458,
+  "epoch": 0.4322766570605187,
   "eval_steps": 9,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -405,6 +405,205 @@
       "learning_rate": 5.868240888334653e-05,
       "loss": 3.3902,
       "step": 50
+    },
+    {
+      "epoch": 0.29394812680115273,
+      "grad_norm": 1.1657159328460693,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 3.2061,
+      "step": 51
+    },
+    {
+      "epoch": 0.29971181556195964,
+      "grad_norm": 2.5311169624328613,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 3.4019,
+      "step": 52
+    },
+    {
+      "epoch": 0.30547550432276654,
+      "grad_norm": 0.9755938053131104,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 3.3383,
+      "step": 53
+    },
+    {
+      "epoch": 0.3112391930835735,
+      "grad_norm": 1.1348779201507568,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 3.291,
+      "step": 54
+    },
+    {
+      "epoch": 0.3112391930835735,
+      "eval_loss": 3.400496244430542,
+      "eval_runtime": 0.8408,
+      "eval_samples_per_second": 693.404,
+      "eval_steps_per_second": 22.598,
+      "step": 54
+    },
+    {
+      "epoch": 0.3170028818443804,
+      "grad_norm": 1.2503737211227417,
+      "learning_rate": 5e-05,
+      "loss": 3.3476,
+      "step": 55
+    },
+    {
+      "epoch": 0.3227665706051873,
+      "grad_norm": 1.3162040710449219,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.2786,
+      "step": 56
+    },
+    {
+      "epoch": 0.3285302593659942,
+      "grad_norm": 0.9366883635520935,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 3.1063,
+      "step": 57
+    },
+    {
+      "epoch": 0.33429394812680113,
+      "grad_norm": 1.1236789226531982,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.2441,
+      "step": 58
+    },
+    {
+      "epoch": 0.3400576368876081,
+      "grad_norm": 1.0356336832046509,
+      "learning_rate": 4.3041344951996746e-05,
+      "loss": 3.2383,
+      "step": 59
+    },
+    {
+      "epoch": 0.345821325648415,
+      "grad_norm": 0.9869205355644226,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.285,
+      "step": 60
+    },
+    {
+      "epoch": 0.3515850144092219,
+      "grad_norm": 0.9632741808891296,
+      "learning_rate": 3.960441545911204e-05,
+      "loss": 3.3328,
+      "step": 61
+    },
+    {
+      "epoch": 0.3573487031700288,
+      "grad_norm": 1.1241796016693115,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 3.2734,
+      "step": 62
+    },
+    {
+      "epoch": 0.3631123919308357,
+      "grad_norm": 0.957284152507782,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 3.1737,
+      "step": 63
+    },
+    {
+      "epoch": 0.3631123919308357,
+      "eval_loss": 3.323737621307373,
+      "eval_runtime": 0.8415,
+      "eval_samples_per_second": 692.849,
+      "eval_steps_per_second": 22.58,
+      "step": 63
+    },
+    {
+      "epoch": 0.3688760806916426,
+      "grad_norm": 0.9445111751556396,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.3264,
+      "step": 64
+    },
+    {
+      "epoch": 0.3746397694524496,
+      "grad_norm": 0.8956809043884277,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 3.2459,
+      "step": 65
+    },
+    {
+      "epoch": 0.3804034582132565,
+      "grad_norm": 0.9865849018096924,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.1544,
+      "step": 66
+    },
+    {
+      "epoch": 0.3861671469740634,
+      "grad_norm": 0.9300174117088318,
+      "learning_rate": 2.9663167846209998e-05,
+      "loss": 3.2718,
+      "step": 67
+    },
+    {
+      "epoch": 0.3919308357348703,
+      "grad_norm": 0.9978016018867493,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 3.238,
+      "step": 68
+    },
+    {
+      "epoch": 0.3976945244956772,
+      "grad_norm": 1.1084285974502563,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 3.1262,
+      "step": 69
+    },
+    {
+      "epoch": 0.4034582132564842,
+      "grad_norm": 0.9832095503807068,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.1283,
+      "step": 70
+    },
+    {
+      "epoch": 0.4092219020172911,
+      "grad_norm": 0.9915679693222046,
+      "learning_rate": 2.350403678833976e-05,
+      "loss": 3.2205,
+      "step": 71
+    },
+    {
+      "epoch": 0.414985590778098,
+      "grad_norm": 1.198361873626709,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 3.3567,
+      "step": 72
+    },
+    {
+      "epoch": 0.414985590778098,
+      "eval_loss": 3.2791378498077393,
+      "eval_runtime": 0.8409,
+      "eval_samples_per_second": 693.297,
+      "eval_steps_per_second": 22.595,
+      "step": 72
+    },
+    {
+      "epoch": 0.4207492795389049,
+      "grad_norm": 1.0045987367630005,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 3.1023,
+      "step": 73
+    },
+    {
+      "epoch": 0.4265129682997118,
+      "grad_norm": 0.8780484795570374,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 2.9411,
+      "step": 74
+    },
+    {
+      "epoch": 0.4322766570605187,
+      "grad_norm": 0.9004272818565369,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 3.1457,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -424,7 +623,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2776751721676800.0,
+  "total_flos": 4165127582515200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null