Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6db843601c8b1f36da11f0e7fe2b8f9dd32d6d8780c6b20a7935c67779133113
+oid sha256:a71a0f14e812e4cb2b11535d9222681bfb9816e20d014e8d468fd684c8e3480f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1e03cb2af7689d6980c28c86947c56699ef9cc10a29968797df9bf324b7a62b
+oid sha256:0d511321ac7ccd8573223b6c0b735064da1b320284e819949d31a9e12042002e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f4f595e53a11daeaa16927192c84c01423620ce6e9c68ca46e9640ea3c6d56d
+oid sha256:122925ea11d91bdcb7b69e82ee3fe1f3f2a6d738e78b0c49ca7bfad403daebc1
 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": 0.006972690296339338,
+  "epoch": 0.008939346533768381,
   "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": 2.8036,
       "step": 35
+    },
+    {
+      "epoch": 0.0071514772270147055,
+      "grad_norm": 0.514265775680542,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6892,
+      "step": 40
+    },
+    {
+      "epoch": 0.0071514772270147055,
+      "eval_loss": 2.772698402404785,
+      "eval_runtime": 241.7888,
+      "eval_samples_per_second": 9.744,
+      "eval_steps_per_second": 4.872,
+      "step": 40
+    },
+    {
+      "epoch": 0.008045411880391543,
+      "grad_norm": 0.6126759648323059,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.7549,
+      "step": 45
+    },
+    {
+      "epoch": 0.008939346533768381,
+      "grad_norm": 0.5537281632423401,
+      "learning_rate": 0.0,
+      "loss": 2.7579,
+      "step": 50
+    },
+    {
+      "epoch": 0.008939346533768381,
+      "eval_loss": 2.7696890830993652,
+      "eval_runtime": 241.7278,
+      "eval_samples_per_second": 9.747,
+      "eval_steps_per_second": 4.873,
+      "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": 8503374869692416.0,
+  "total_flos": 1.088596299743232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null