Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a288529085e85aa2a2b58c37011dd16b7750557b7f069f97f1bcb476e9141825
+oid sha256:2e1f5c84173ea5e9b2e4fb08e10124d39b1a491b402f0de28caf8de4b760db49
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89d5536243cdc3bdfd284d91f65637bbf5ab03984fe38ebed05dcf439569ea11
+oid sha256:515b3e1ecb36e1cb5fbebf47abf80241dff7b621accc66dc2a10405eb064652a
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630b121fadd21d13ee17a86473b928204282dffbb81941a61c173dd06a7af5f0
+oid sha256:c0f247327caf964bf7fa15c173ae9e435da78e83dfcb744db194cf8eca0374dd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e76ff8614026ec7c5c2d9793615ca4e2f707e550ce0b5a4376af475431afe3f1
+oid sha256:c9a138d58efee4722b14f409e14731dcd0935c0eaa8a6078a4918744b9529bab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.22525879917184266,
+  "epoch": 0.2502875546353807,
   "eval_steps": 50,
-  "global_step": 153,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1110,6 +1110,125 @@
       "learning_rate": 2.385012299531262e-05,
       "loss": 0.0515,
       "step": 153
+    },
+    {
+      "epoch": 0.22673107890499195,
+      "grad_norm": 0.10095140337944031,
+      "learning_rate": 2.2900622215575197e-05,
+      "loss": 0.0577,
+      "step": 154
+    },
+    {
+      "epoch": 0.22820335863814126,
+      "grad_norm": 0.09335016459226608,
+      "learning_rate": 2.1966991411008938e-05,
+      "loss": 0.0334,
+      "step": 155
+    },
+    {
+      "epoch": 0.22967563837129054,
+      "grad_norm": 0.14227519929409027,
+      "learning_rate": 2.1049514974601175e-05,
+      "loss": 0.078,
+      "step": 156
+    },
+    {
+      "epoch": 0.23114791810443985,
+      "grad_norm": 0.09830557554960251,
+      "learning_rate": 2.0148472378562215e-05,
+      "loss": 0.0481,
+      "step": 157
+    },
+    {
+      "epoch": 0.23262019783758914,
+      "grad_norm": 0.10622940212488174,
+      "learning_rate": 1.926413808919542e-05,
+      "loss": 0.0451,
+      "step": 158
+    },
+    {
+      "epoch": 0.23409247757073845,
+      "grad_norm": 0.12101616710424423,
+      "learning_rate": 1.8396781483292098e-05,
+      "loss": 0.0713,
+      "step": 159
+    },
+    {
+      "epoch": 0.23556475730388773,
+      "grad_norm": 0.08884954452514648,
+      "learning_rate": 1.7546666766076655e-05,
+      "loss": 0.0447,
+      "step": 160
+    },
+    {
+      "epoch": 0.23703703703703705,
+      "grad_norm": 0.08267998695373535,
+      "learning_rate": 1.671405289072718e-05,
+      "loss": 0.0157,
+      "step": 161
+    },
+    {
+      "epoch": 0.23850931677018633,
+      "grad_norm": 0.13504156470298767,
+      "learning_rate": 1.5899193479495857e-05,
+      "loss": 0.1002,
+      "step": 162
+    },
+    {
+      "epoch": 0.23998159650333564,
+      "grad_norm": 0.09033524990081787,
+      "learning_rate": 1.5102336746453053e-05,
+      "loss": 0.0555,
+      "step": 163
+    },
+    {
+      "epoch": 0.24145387623648493,
+      "grad_norm": 0.11912113428115845,
+      "learning_rate": 1.4323725421878949e-05,
+      "loss": 0.0801,
+      "step": 164
+    },
+    {
+      "epoch": 0.24292615596963424,
+      "grad_norm": 0.10221156477928162,
+      "learning_rate": 1.3563596678325606e-05,
+      "loss": 0.0453,
+      "step": 165
+    },
+    {
+      "epoch": 0.24439843570278352,
+      "grad_norm": 0.10165137052536011,
+      "learning_rate": 1.2822182058371878e-05,
+      "loss": 0.0465,
+      "step": 166
+    },
+    {
+      "epoch": 0.24587071543593284,
+      "grad_norm": 0.07042307406663895,
+      "learning_rate": 1.2099707404093203e-05,
+      "loss": 0.0156,
+      "step": 167
+    },
+    {
+      "epoch": 0.24734299516908212,
+      "grad_norm": 0.13063064217567444,
+      "learning_rate": 1.1396392788268052e-05,
+      "loss": 0.0635,
+      "step": 168
+    },
+    {
+      "epoch": 0.24881527490223143,
+      "grad_norm": 0.12741073966026306,
+      "learning_rate": 1.0712452447341582e-05,
+      "loss": 0.0275,
+      "step": 169
+    },
+    {
+      "epoch": 0.2502875546353807,
+      "grad_norm": 0.05055376887321472,
+      "learning_rate": 1.0048094716167095e-05,
+      "loss": 0.0101,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1129,7 +1248,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6162316446146232e+18,
+  "total_flos": 1.796206666199335e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null