Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9043660a1b4ccaacec49d9de3e54c375ab554d8bc09b519e049e1187a4e6d443
+oid sha256:02312c7c4a6a65dcedae55f92c45010543c6ab80a4d6626bc0561c429966206b
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6666386711c5d8f44decb6f7d96d5331da7db7a80dd5ed27f7be690ed958ca2e
+oid sha256:f6c1369d2f475d0808b362e7dfe69cc4de1f9d4ae752f779e574f4f4e1d017c9
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936a92cdb8cd619b5f2846f7c558ea4b3f948376f7dd89ce1c0fd506c8361f44
+oid sha256:abf19aa5dfffd213199bdf003cff4088827173c85322b83ce516c5aa848c12f2
 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": 0.0011235712279337093,
+  "epoch": 0.0014404759332483452,
   "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": 1.173,
       "step": 35
+    },
+    {
+      "epoch": 0.0011523807465986763,
+      "grad_norm": 0.7039690613746643,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0843,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011523807465986763,
+      "eval_loss": 1.1501621007919312,
+      "eval_runtime": 478.5524,
+      "eval_samples_per_second": 30.54,
+      "eval_steps_per_second": 15.271,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012964283399235106,
+      "grad_norm": 0.6280918121337891,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0935,
+      "step": 45
+    },
+    {
+      "epoch": 0.0014404759332483452,
+      "grad_norm": 0.6172332763671875,
+      "learning_rate": 0.0,
+      "loss": 1.0376,
+      "step": 50
+    },
+    {
+      "epoch": 0.0014404759332483452,
+      "eval_loss": 1.1479227542877197,
+      "eval_runtime": 480.5166,
+      "eval_samples_per_second": 30.415,
+      "eval_steps_per_second": 15.209,
+      "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": 1995177430351872.0,
+  "total_flos": 2557919782502400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null