Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d5d573d6db792ecf561d3d6aecf0526ad2e07672917c919dd995025e90165a
+oid sha256:f20e283777f2dc1adca2578b5177f9274bdeb429c4758dfe96f8052e393d5253
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b876382fdb7dcba79b993e4cb68aeb8f01d2f489d2c6cac654d3bdcbddea9d5
+oid sha256:a2f8884bce5fc446ab034c2f983faf6714b1df90b7f76001e3826729a5d6d85b
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a182a36b53b72fd58058a734a0954266d4a8bdcf891d2eec7f7c86b06a3160
+oid sha256:2fb35c45d8feb8c3bee5f12ca4d9d742b4a38831ae017bf30f22bb04e9bf8cee
 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": 0.0023129614802953474,
+  "epoch": 0.002965335231147881,
   "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": 1.1512,
       "step": 35
+    },
+    {
+      "epoch": 0.002372268184918305,
+      "grad_norm": 1.5854142904281616,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1031,
+      "step": 40
+    },
+    {
+      "epoch": 0.002372268184918305,
+      "eval_loss": 1.1262532472610474,
+      "eval_runtime": 280.072,
+      "eval_samples_per_second": 25.351,
+      "eval_steps_per_second": 12.675,
+      "step": 40
+    },
+    {
+      "epoch": 0.0026688017080330933,
+      "grad_norm": 1.6224738359451294,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1091,
+      "step": 45
+    },
+    {
+      "epoch": 0.002965335231147881,
+      "grad_norm": 1.5776338577270508,
+      "learning_rate": 0.0,
+      "loss": 1.074,
+      "step": 50
+    },
+    {
+      "epoch": 0.002965335231147881,
+      "eval_loss": 1.1203703880310059,
+      "eval_runtime": 279.615,
+      "eval_samples_per_second": 25.392,
+      "eval_steps_per_second": 12.696,
+      "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": 1876255020417024.0,
+  "total_flos": 2405455154380800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null