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:b745462f26110d8f5e6c0bcef91055e14492965f4fda21faf63549fad0fcc448
+oid sha256:63d64bb4252a56462612ce8ea325bbb4f7eb1e476a12210a5f3bc4adabecffe5
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aedeeacab12f5e39f365b4749f7ef795c5b68cd1bab0b91369367d075cadfc66
+oid sha256:4beda4b81812c494724c944ce42a1384386d898438a92682ca41d1363ea7cd53
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb210574debeca01beef086494f1b0da6d8ee8853b3831ec7094b554157981c
+oid sha256:2d2cc8b4da1c1e828f3ecd6fdcd0ddcc7555dae3d2812a0ace74e33cfe7a8a86
 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": 0.7090514120202752,
+  "epoch": 0.7878349022447502,
   "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": 0.3123,
       "step": 153
+    },
+    {
+      "epoch": 0.713685734974656,
+      "grad_norm": 1.3699779510498047,
+      "learning_rate": 2.2900622215575197e-05,
+      "loss": 0.2744,
+      "step": 154
+    },
+    {
+      "epoch": 0.718320057929037,
+      "grad_norm": 1.4394081830978394,
+      "learning_rate": 2.1966991411008938e-05,
+      "loss": 0.2854,
+      "step": 155
+    },
+    {
+      "epoch": 0.7229543808834178,
+      "grad_norm": 1.1516926288604736,
+      "learning_rate": 2.1049514974601175e-05,
+      "loss": 0.232,
+      "step": 156
+    },
+    {
+      "epoch": 0.7275887038377987,
+      "grad_norm": 1.226991891860962,
+      "learning_rate": 2.0148472378562215e-05,
+      "loss": 0.2174,
+      "step": 157
+    },
+    {
+      "epoch": 0.7322230267921795,
+      "grad_norm": 1.3236987590789795,
+      "learning_rate": 1.926413808919542e-05,
+      "loss": 0.2859,
+      "step": 158
+    },
+    {
+      "epoch": 0.7368573497465605,
+      "grad_norm": 1.3909859657287598,
+      "learning_rate": 1.8396781483292098e-05,
+      "loss": 0.1741,
+      "step": 159
+    },
+    {
+      "epoch": 0.7414916727009413,
+      "grad_norm": 1.3062829971313477,
+      "learning_rate": 1.7546666766076655e-05,
+      "loss": 0.2003,
+      "step": 160
+    },
+    {
+      "epoch": 0.7461259956553222,
+      "grad_norm": 1.4208601713180542,
+      "learning_rate": 1.671405289072718e-05,
+      "loss": 0.2306,
+      "step": 161
+    },
+    {
+      "epoch": 0.7507603186097032,
+      "grad_norm": 1.130900502204895,
+      "learning_rate": 1.5899193479495857e-05,
+      "loss": 0.1712,
+      "step": 162
+    },
+    {
+      "epoch": 0.755394641564084,
+      "grad_norm": 1.3274939060211182,
+      "learning_rate": 1.5102336746453053e-05,
+      "loss": 0.2057,
+      "step": 163
+    },
+    {
+      "epoch": 0.7600289645184649,
+      "grad_norm": 1.5153155326843262,
+      "learning_rate": 1.4323725421878949e-05,
+      "loss": 0.2792,
+      "step": 164
+    },
+    {
+      "epoch": 0.7646632874728457,
+      "grad_norm": 1.2106071710586548,
+      "learning_rate": 1.3563596678325606e-05,
+      "loss": 0.213,
+      "step": 165
+    },
+    {
+      "epoch": 0.7692976104272267,
+      "grad_norm": 1.3996082544326782,
+      "learning_rate": 1.2822182058371878e-05,
+      "loss": 0.2113,
+      "step": 166
+    },
+    {
+      "epoch": 0.7739319333816075,
+      "grad_norm": 1.1402256488800049,
+      "learning_rate": 1.2099707404093203e-05,
+      "loss": 0.1599,
+      "step": 167
+    },
+    {
+      "epoch": 0.7785662563359884,
+      "grad_norm": 1.6671884059906006,
+      "learning_rate": 1.1396392788268052e-05,
+      "loss": 0.301,
+      "step": 168
+    },
+    {
+      "epoch": 0.7832005792903693,
+      "grad_norm": 1.1182959079742432,
+      "learning_rate": 1.0712452447341582e-05,
+      "loss": 0.1367,
+      "step": 169
+    },
+    {
+      "epoch": 0.7878349022447502,
+      "grad_norm": 1.0370293855667114,
+      "learning_rate": 1.0048094716167095e-05,
+      "loss": 0.1441,
+      "step": 170
     }
   ],
   "logging_steps": 1,
@@ -1129,7 +1248,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.131167934494802e+17,
+  "total_flos": 1.0145742149438669e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null