Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e31aff993bd291d5a5bef1316a97c485edf888c283e5dc5783ddbda0f8d6981
+oid sha256:ac315f3aba39de36517f5d1e6b1194acb90f1e09511101216fef35e74dd23069
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ace691c5a6c544400233309d1934c59d2bb0886b0a7d72bdda8d26d5c5c9f79
+oid sha256:090b8ddfca2ae6cabe8f4ae703475e2034c6d0236505c155f682ff4339c7d06a
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93465e4033b3c4d60efbc25c78cb667183e48d2e3814a97bbdec895fdd2a8c6
+oid sha256:25c48301256e8a87d9fe9c2ebadc2a9fdddb0d525e529a80d0b2a696f175a3bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7ee3ad8033dc89ac477e4347a2567ff89d6c0358e1d7a1b0f70057a3434847
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01192321449862883,
+  "epoch": 0.02384642899725766,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 2.663507823075358e-05,
       "loss": 1.3317,
       "step": 25
+    },
+    {
+      "epoch": 0.012400143078573983,
+      "grad_norm": 2.561760663986206,
+      "learning_rate": 2.5e-05,
+      "loss": 2.078,
+      "step": 26
+    },
+    {
+      "epoch": 0.012877071658519137,
+      "grad_norm": 2.975694179534912,
+      "learning_rate": 2.3364921769246423e-05,
+      "loss": 1.5784,
+      "step": 27
+    },
+    {
+      "epoch": 0.01335400023846429,
+      "grad_norm": 3.220482349395752,
+      "learning_rate": 2.173684519449872e-05,
+      "loss": 1.7665,
+      "step": 28
+    },
+    {
+      "epoch": 0.013830928818409444,
+      "grad_norm": 2.4195404052734375,
+      "learning_rate": 2.0122741949596797e-05,
+      "loss": 1.2464,
+      "step": 29
+    },
+    {
+      "epoch": 0.014307857398354596,
+      "grad_norm": 3.0891129970550537,
+      "learning_rate": 1.852952387243698e-05,
+      "loss": 1.4323,
+      "step": 30
+    },
+    {
+      "epoch": 0.01478478597829975,
+      "grad_norm": 2.1057982444763184,
+      "learning_rate": 1.6964013367420966e-05,
+      "loss": 1.0373,
+      "step": 31
+    },
+    {
+      "epoch": 0.015261714558244903,
+      "grad_norm": 2.6382322311401367,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 1.2615,
+      "step": 32
+    },
+    {
+      "epoch": 0.015738643138190057,
+      "grad_norm": 2.989168405532837,
+      "learning_rate": 1.3942782744524973e-05,
+      "loss": 1.8745,
+      "step": 33
+    },
+    {
+      "epoch": 0.01621557171813521,
+      "grad_norm": 2.9760780334472656,
+      "learning_rate": 1.2500000000000006e-05,
+      "loss": 1.4645,
+      "step": 34
+    },
+    {
+      "epoch": 0.01669250029808036,
+      "grad_norm": 3.531989336013794,
+      "learning_rate": 1.1110744174509952e-05,
+      "loss": 1.5544,
+      "step": 35
+    },
+    {
+      "epoch": 0.017169428878025517,
+      "grad_norm": 3.602961778640747,
+      "learning_rate": 9.780964274781984e-06,
+      "loss": 1.4617,
+      "step": 36
+    },
+    {
+      "epoch": 0.01764635745797067,
+      "grad_norm": 2.5102806091308594,
+      "learning_rate": 8.51635462249828e-06,
+      "loss": 1.4198,
+      "step": 37
+    },
+    {
+      "epoch": 0.018123286037915822,
+      "grad_norm": 2.7395095825195312,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.8911,
+      "step": 38
+    },
+    {
+      "epoch": 0.018600214617860975,
+      "grad_norm": 2.7568724155426025,
+      "learning_rate": 6.204004813025568e-06,
+      "loss": 1.0436,
+      "step": 39
+    },
+    {
+      "epoch": 0.019077143197806127,
+      "grad_norm": 5.96933650970459,
+      "learning_rate": 5.166166492719124e-06,
+      "loss": 1.5069,
+      "step": 40
+    },
+    {
+      "epoch": 0.019554071777751283,
+      "grad_norm": 5.542440414428711,
+      "learning_rate": 4.213259692436367e-06,
+      "loss": 1.3813,
+      "step": 41
+    },
+    {
+      "epoch": 0.020031000357696435,
+      "grad_norm": 3.1913931369781494,
+      "learning_rate": 3.3493649053890326e-06,
+      "loss": 1.0923,
+      "step": 42
+    },
+    {
+      "epoch": 0.020507928937641588,
+      "grad_norm": 3.866119384765625,
+      "learning_rate": 2.578181461682794e-06,
+      "loss": 1.2939,
+      "step": 43
+    },
+    {
+      "epoch": 0.02098485751758674,
+      "grad_norm": 5.512697696685791,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 1.559,
+      "step": 44
+    },
+    {
+      "epoch": 0.021461786097531896,
+      "grad_norm": 6.1839680671691895,
+      "learning_rate": 1.3267467626223606e-06,
+      "loss": 1.8948,
+      "step": 45
+    },
+    {
+      "epoch": 0.021938714677477048,
+      "grad_norm": 5.496179580688477,
+      "learning_rate": 8.51854342773295e-07,
+      "loss": 1.1269,
+      "step": 46
+    },
+    {
+      "epoch": 0.0224156432574222,
+      "grad_norm": 5.928053379058838,
+      "learning_rate": 4.803679899192392e-07,
+      "loss": 1.4756,
+      "step": 47
+    },
+    {
+      "epoch": 0.022892571837367353,
+      "grad_norm": 5.825471878051758,
+      "learning_rate": 2.1387846565474045e-07,
+      "loss": 2.1599,
+      "step": 48
+    },
+    {
+      "epoch": 0.02336950041731251,
+      "grad_norm": 8.19292163848877,
+      "learning_rate": 5.352691903491303e-08,
+      "loss": 1.5091,
+      "step": 49
+    },
+    {
+      "epoch": 0.02384642899725766,
+      "grad_norm": 24.69010353088379,
+      "learning_rate": 0.0,
+      "loss": 2.3403,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.9023266530197504e+16,
+  "total_flos": 3.76735278343127e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null