Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3411e5658b009b621408a4d83e81e94f5004cb224cc956abfc4ef9e7ebdba124
+oid sha256:63707defcbc7b945442cb5097b9c4a1a382399ceb22128085b3184d574c26b23
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6194c87c3c8b88895fa059da50a78aed1ee2aafa20db246337921a2f276b035b
+oid sha256:7f620b7624b59c0e7d6f71b2042e2bc1ab892974fec5bee48cd674e278364e8f
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0e2bee1a521f4ebd0f27488d621d4beaa40703e66e4b6904b0a1458fb4f0d90
+oid sha256:5be61a5ae78fd26316299d1a58283ac9b251ff20875759cb974275078771f6e5
 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": 0.006358782048669139,
+  "epoch": 0.008152284677780949,
   "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": 1.0057,
       "step": 35
+    },
+    {
+      "epoch": 0.006521827742224758,
+      "grad_norm": 0.1731029897928238,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0015,
+      "step": 40
+    },
+    {
+      "epoch": 0.006521827742224758,
+      "eval_loss": 1.0348747968673706,
+      "eval_runtime": 137.9943,
+      "eval_samples_per_second": 18.718,
+      "eval_steps_per_second": 9.363,
+      "step": 40
+    },
+    {
+      "epoch": 0.0073370562100028534,
+      "grad_norm": 0.17811691761016846,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9535,
+      "step": 45
+    },
+    {
+      "epoch": 0.008152284677780949,
+      "grad_norm": 0.1666414737701416,
+      "learning_rate": 0.0,
+      "loss": 0.9758,
+      "step": 50
+    },
+    {
+      "epoch": 0.008152284677780949,
+      "eval_loss": 1.033933162689209,
+      "eval_runtime": 136.1083,
+      "eval_samples_per_second": 18.978,
+      "eval_steps_per_second": 9.492,
+      "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": 1758569850470400.0,
+  "total_flos": 2270153806970880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null