Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42416108f97a3819b4bd2240a04742941a54982500e06041d6740b0f086f1b05
+oid sha256:19d7fdcfff32c8f095ac2af29c718011e887bf296db4c2af109a252eb93150e1
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764d30744a2d196fe5e3d3a693ba10ea4bc34dcfa41dc180226eee6119960791
+oid sha256:f4e94a234e360e56bd72c46903b57b5f1b9d501d6737ff7ebc6275cdf82d264f
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6777854a7d16d2ed048ffceaeb822cfc907d9b86c3ff3213c5abc2910706824f
+oid sha256:43dec0ab383c50457cbeccc820e1117b654d7225bac20e2acad0f1d3d85b2995
 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": 0.0016964819748790168,
+  "epoch": 0.0021749768908705344,
   "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": 0.6469,
       "step": 35
+    },
+    {
+      "epoch": 0.0017399815126964277,
+      "grad_norm": 0.42244553565979004,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.629,
+      "step": 40
+    },
+    {
+      "epoch": 0.0017399815126964277,
+      "eval_loss": 0.6393447518348694,
+      "eval_runtime": 334.8479,
+      "eval_samples_per_second": 28.909,
+      "eval_steps_per_second": 14.454,
+      "step": 40
+    },
+    {
+      "epoch": 0.0019574792017834812,
+      "grad_norm": 0.43721675872802734,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6313,
+      "step": 45
+    },
+    {
+      "epoch": 0.0021749768908705344,
+      "grad_norm": 0.4112253189086914,
+      "learning_rate": 0.0,
+      "loss": 0.6377,
+      "step": 50
+    },
+    {
+      "epoch": 0.0021749768908705344,
+      "eval_loss": 0.6375181078910828,
+      "eval_runtime": 334.4333,
+      "eval_samples_per_second": 28.944,
+      "eval_steps_per_second": 14.472,
+      "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": 1963203433070592.0,
+  "total_flos": 2506761386852352.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null