Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8104b17e2d41c7004275453f5491806e86ea64d3495084f3eab7905d62483c
+oid sha256:952c9588ca8aab9a3be93cbf5f2390f8fc788735e21cc497a1d52b1de2e9556e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:612291f4d43f224763c794097af0e32f1b9d1fee0ffbf7bb934dd6ce88c4ba2b
+oid sha256:19fc9eff172015d6eb14d20311692a4aaec89528931721e73b51b6692e7b1230
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2e18a6927c524267965181ffb51a4f3e6fc30ed6581fd48fe0ef4a1ccdeb3b
+oid sha256:370731f4eccf431eaed7fd7c80966de8cf9c9e7f5b12ce8e3b2169241d34df78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f9ab26294f369ba5d99cf6e2514a5d05f3df1a90b36a045191f6b23077ba365
+oid sha256:2188426f4adaa3a6124c181a61860e824dc2136981845a9e9c4162d0d3700af6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2529697738321708,
+  "epoch": 0.2705559078418939,
   "eval_steps": 50,
-  "global_step": 187,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1348,6 +1348,105 @@
       "learning_rate": 1.9222451411073645e-06,
       "loss": 0.8576,
       "step": 187
+    },
+    {
+      "epoch": 0.25432255337138027,
+      "grad_norm": 0.17826685309410095,
+      "learning_rate": 1.6389299449645733e-06,
+      "loss": 0.8168,
+      "step": 188
+    },
+    {
+      "epoch": 0.25567533291058975,
+      "grad_norm": 0.17930451035499573,
+      "learning_rate": 1.3779612414252017e-06,
+      "loss": 0.8579,
+      "step": 189
+    },
+    {
+      "epoch": 0.2570281124497992,
+      "grad_norm": 0.1737329512834549,
+      "learning_rate": 1.1394185240843983e-06,
+      "loss": 0.8247,
+      "step": 190
+    },
+    {
+      "epoch": 0.25838089198900865,
+      "grad_norm": 0.17530955374240875,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 0.8438,
+      "step": 191
+    },
+    {
+      "epoch": 0.25973367152821814,
+      "grad_norm": 0.18335498869419098,
+      "learning_rate": 7.298948443822228e-07,
+      "loss": 0.8925,
+      "step": 192
+    },
+    {
+      "epoch": 0.2610864510674276,
+      "grad_norm": 0.17108893394470215,
+      "learning_rate": 5.590386269008512e-07,
+      "loss": 0.8095,
+      "step": 193
+    },
+    {
+      "epoch": 0.2624392306066371,
+      "grad_norm": 0.18680942058563232,
+      "learning_rate": 4.108578473795032e-07,
+      "loss": 0.8519,
+      "step": 194
+    },
+    {
+      "epoch": 0.2637920101458465,
+      "grad_norm": 0.17714115977287292,
+      "learning_rate": 2.8539764311908407e-07,
+      "loss": 0.8445,
+      "step": 195
+    },
+    {
+      "epoch": 0.265144789685056,
+      "grad_norm": 0.17967358231544495,
+      "learning_rate": 1.8269623051318515e-07,
+      "loss": 0.8631,
+      "step": 196
+    },
+    {
+      "epoch": 0.2664975692242655,
+      "grad_norm": 0.17863860726356506,
+      "learning_rate": 1.027848934069625e-07,
+      "loss": 0.8315,
+      "step": 197
+    },
+    {
+      "epoch": 0.26785034876347497,
+      "grad_norm": 0.1744745522737503,
+      "learning_rate": 4.568797356781784e-08,
+      "loss": 0.805,
+      "step": 198
+    },
+    {
+      "epoch": 0.26920312830268445,
+      "grad_norm": 0.1872616410255432,
+      "learning_rate": 1.142286327065478e-08,
+      "loss": 0.8821,
+      "step": 199
+    },
+    {
+      "epoch": 0.2705559078418939,
+      "grad_norm": 0.18084542453289032,
+      "learning_rate": 0.0,
+      "loss": 0.8613,
+      "step": 200
+    },
+    {
+      "epoch": 0.2705559078418939,
+      "eval_loss": 0.842223584651947,
+      "eval_runtime": 438.0922,
+      "eval_samples_per_second": 5.684,
+      "eval_steps_per_second": 2.842,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1362,12 +1461,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.122745730507735e+18,
+  "total_flos": 1.2008903253719777e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null