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:e6160a9688e5518a6a9c93f5ed67c94ecddf4fc974117e29e79f6a05fa9c5f1c
+oid sha256:1898e011f12bcefa675ba9dd2aa404cfdc46d20feaaf0d789ca42d931ad6a095
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e02b4e4538ebcbb52c0f8a295f4ba67d04229a33ac992e0d7592c3b3a3302057
+oid sha256:2e709864c6185009a503b1ed2538e4d2a14bf99cbd23473f93b39cde7e0deea4
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41545c83c667446944388978812bb06593d44bfffd5dfc346f997e48601eff99
+oid sha256:6beb92e82d89b74efdd456fb9bf2b41610797ca90b007f020dc4fb8145708801
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08176100628930817,
+  "epoch": 0.10482180293501048,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.4054,
       "step": 35
+    },
+    {
+      "epoch": 0.08385744234800839,
+      "grad_norm": 0.40710872411727905,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4665,
+      "step": 40
+    },
+    {
+      "epoch": 0.08385744234800839,
+      "eval_loss": 1.3742934465408325,
+      "eval_runtime": 35.7187,
+      "eval_samples_per_second": 5.627,
+      "eval_steps_per_second": 2.828,
+      "step": 40
+    },
+    {
+      "epoch": 0.09433962264150944,
+      "grad_norm": 0.3978058397769928,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3321,
+      "step": 45
+    },
+    {
+      "epoch": 0.10482180293501048,
+      "grad_norm": 0.4136011302471161,
+      "learning_rate": 0.0,
+      "loss": 1.3557,
+      "step": 50
+    },
+    {
+      "epoch": 0.10482180293501048,
+      "eval_loss": 1.3728853464126587,
+      "eval_runtime": 35.784,
+      "eval_samples_per_second": 5.617,
+      "eval_steps_per_second": 2.822,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.38717318610944e+16,
+  "total_flos": 1.780205588840448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null