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:a14b4fb6ee528d58f0de1d58f043501b5e4275318c33ad7005c9d3ffdf345923
+oid sha256:7464abc8d084c6fc75061b9d32a63c2bf35d1b4069f98a55d58f46e73a71dafb
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85d3f296f1caccc97576f334d3c8ce445219341e5eba574da97417873583f70c
+oid sha256:ab7dbd2c70b1e013770dd724d8ea078f2d817909782821dce6ac969695937e58
 size 313998650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7759c9d37a3bfdf34170c5799fd274c55882b176c21c6560d16f0af9f841e5cf
+oid sha256:bdec9d1fdb78bc8b4577462e9b6785a7732743b19c615a410973e2069ccf0e5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09124087591240876,
+  "epoch": 0.18248175182481752,
   "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": 5.327015646150716e-05,
       "loss": 2.2555,
       "step": 25
+    },
+    {
+      "epoch": 0.0948905109489051,
+      "grad_norm": 17.39502716064453,
+      "learning_rate": 5e-05,
+      "loss": 3.1638,
+      "step": 26
+    },
+    {
+      "epoch": 0.09854014598540146,
+      "grad_norm": 11.822202682495117,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.7542,
+      "step": 27
+    },
+    {
+      "epoch": 0.10218978102189781,
+      "grad_norm": 15.457491874694824,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.0197,
+      "step": 28
+    },
+    {
+      "epoch": 0.10583941605839416,
+      "grad_norm": 12.597031593322754,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.9913,
+      "step": 29
+    },
+    {
+      "epoch": 0.10948905109489052,
+      "grad_norm": 11.128311157226562,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.3148,
+      "step": 30
+    },
+    {
+      "epoch": 0.11313868613138686,
+      "grad_norm": 9.338001251220703,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7951,
+      "step": 31
+    },
+    {
+      "epoch": 0.11678832116788321,
+      "grad_norm": 9.208539962768555,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.3319,
+      "step": 32
+    },
+    {
+      "epoch": 0.12043795620437957,
+      "grad_norm": 11.79247760772705,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.6863,
+      "step": 33
+    },
+    {
+      "epoch": 0.12408759124087591,
+      "grad_norm": 12.631509780883789,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.8203,
+      "step": 34
+    },
+    {
+      "epoch": 0.12773722627737227,
+      "grad_norm": 11.063702583312988,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.8893,
+      "step": 35
+    },
+    {
+      "epoch": 0.13138686131386862,
+      "grad_norm": 10.822319030761719,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.8956,
+      "step": 36
+    },
+    {
+      "epoch": 0.13503649635036497,
+      "grad_norm": 9.506606101989746,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.2636,
+      "step": 37
+    },
+    {
+      "epoch": 0.1386861313868613,
+      "grad_norm": 13.27221393585205,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.0448,
+      "step": 38
+    },
+    {
+      "epoch": 0.14233576642335766,
+      "grad_norm": 10.660257339477539,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1345,
+      "step": 39
+    },
+    {
+      "epoch": 0.145985401459854,
+      "grad_norm": 10.788248062133789,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.1946,
+      "step": 40
+    },
+    {
+      "epoch": 0.14963503649635038,
+      "grad_norm": 11.949002265930176,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.1181,
+      "step": 41
+    },
+    {
+      "epoch": 0.15328467153284672,
+      "grad_norm": 15.836535453796387,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.67,
+      "step": 42
+    },
+    {
+      "epoch": 0.15693430656934307,
+      "grad_norm": 9.54406452178955,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.8201,
+      "step": 43
+    },
+    {
+      "epoch": 0.16058394160583941,
+      "grad_norm": 12.462480545043945,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.7056,
+      "step": 44
+    },
+    {
+      "epoch": 0.16423357664233576,
+      "grad_norm": 14.278252601623535,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.8137,
+      "step": 45
+    },
+    {
+      "epoch": 0.1678832116788321,
+      "grad_norm": 12.841248512268066,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.7448,
+      "step": 46
+    },
+    {
+      "epoch": 0.17153284671532848,
+      "grad_norm": 11.82575511932373,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.6659,
+      "step": 47
+    },
+    {
+      "epoch": 0.17518248175182483,
+      "grad_norm": 11.361124038696289,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.5508,
+      "step": 48
+    },
+    {
+      "epoch": 0.17883211678832117,
+      "grad_norm": 9.747543334960938,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.3046,
+      "step": 49
+    },
+    {
+      "epoch": 0.18248175182481752,
+      "grad_norm": 11.088653564453125,
+      "learning_rate": 0.0,
+      "loss": 2.8381,
+      "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": 4967074313011200.0,
+  "total_flos": 9934148626022400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null