Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:432eec1fba0080d963fdc6ae82a834cb1e734041f7aff1118b89ad7b18c207db
+oid sha256:410899590cb89182ad507b94c9715cb6c79c8f84fd690d8a965cfead128037bd
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05128a102a188bf1805db3f87861a8ec32a704f4a163c27ce580f009fdd12730
+oid sha256:b916308985c9b72399ed4db8197d12693083402880ad55b12fd007643fd47514
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5181f6310a2ee8021297af86cebbb89fed67729cda31b24d40e1d23f86a348a4
+oid sha256:2f161ce82ded6ccdd3cb237edfd4b9542d0d5479bd11aac60eed50ba70af1776
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb97b24f34ff3e53eec5be9cf35c1a7161c58dbc2fed7dda160fb3eb64e5f353
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21479713603818615,
+  "epoch": 0.2386634844868735,
   "eval_steps": 25,
-  "global_step": 90,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -669,6 +669,84 @@
       "learning_rate": 6.030737921409169e-06,
       "loss": 0.8122,
       "step": 90
+    },
+    {
+      "epoch": 0.2171837708830549,
+      "grad_norm": 0.512912929058075,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.9124,
+      "step": 91
+    },
+    {
+      "epoch": 0.21957040572792363,
+      "grad_norm": 0.4402737021446228,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 0.619,
+      "step": 92
+    },
+    {
+      "epoch": 0.22195704057279236,
+      "grad_norm": 0.5990650057792664,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 0.7048,
+      "step": 93
+    },
+    {
+      "epoch": 0.2243436754176611,
+      "grad_norm": 0.553033173084259,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.9326,
+      "step": 94
+    },
+    {
+      "epoch": 0.22673031026252982,
+      "grad_norm": 0.48306721448898315,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.7718,
+      "step": 95
+    },
+    {
+      "epoch": 0.22911694510739858,
+      "grad_norm": 0.5778696537017822,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 0.8295,
+      "step": 96
+    },
+    {
+      "epoch": 0.2315035799522673,
+      "grad_norm": 0.4547498822212219,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.6779,
+      "step": 97
+    },
+    {
+      "epoch": 0.23389021479713604,
+      "grad_norm": 0.5626754760742188,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 0.9394,
+      "step": 98
+    },
+    {
+      "epoch": 0.23627684964200477,
+      "grad_norm": 0.5053015351295471,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 0.8733,
+      "step": 99
+    },
+    {
+      "epoch": 0.2386634844868735,
+      "grad_norm": 0.5155021548271179,
+      "learning_rate": 0.0,
+      "loss": 0.912,
+      "step": 100
+    },
+    {
+      "epoch": 0.2386634844868735,
+      "eval_loss": 0.8268756866455078,
+      "eval_runtime": 34.9723,
+      "eval_samples_per_second": 5.061,
+      "eval_steps_per_second": 2.545,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -683,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.741900625215488e+16,
+  "total_flos": 1.93544513912832e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null