Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d751c5b027e9bd168cf97bc8ac2e14ed984bdc5ea43713bf9ac7b00ce0d9734
+oid sha256:4e3000ef600ff4a03d166e31231d048d748f4c98cb873a10f1f9f20d196d78b7
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c98c9228780b5154dd4a1b891bcbd30fb9379b77dba5d7b5c8cf81d27cb539ab
+oid sha256:9e33249d272752445df8815fa686baa1f0489bac834a5e2388ee4a4b5debdfe0
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 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": 0.133475935828877,
+  "epoch": 0.1711229946524064,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 28.18,
       "eval_steps_per_second": 14.119,
       "step": 39
+    },
+    {
+      "epoch": 0.13689839572192514,
+      "grad_norm": 0.8070633411407471,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5244,
+      "step": 40
+    },
+    {
+      "epoch": 0.14032085561497326,
+      "grad_norm": 0.762014627456665,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.4261,
+      "step": 41
+    },
+    {
+      "epoch": 0.14374331550802139,
+      "grad_norm": 0.5508111715316772,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3714,
+      "step": 42
+    },
+    {
+      "epoch": 0.1471657754010695,
+      "grad_norm": 0.735578715801239,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.4624,
+      "step": 43
+    },
+    {
+      "epoch": 0.15058823529411763,
+      "grad_norm": 0.5103933811187744,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.244,
+      "step": 44
+    },
+    {
+      "epoch": 0.15401069518716579,
+      "grad_norm": 0.5898608565330505,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3896,
+      "step": 45
+    },
+    {
+      "epoch": 0.1574331550802139,
+      "grad_norm": 0.676190197467804,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3595,
+      "step": 46
+    },
+    {
+      "epoch": 0.16085561497326203,
+      "grad_norm": 0.5928998589515686,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.4371,
+      "step": 47
+    },
+    {
+      "epoch": 0.16427807486631016,
+      "grad_norm": 0.815858781337738,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.413,
+      "step": 48
+    },
+    {
+      "epoch": 0.16770053475935828,
+      "grad_norm": 0.5120140910148621,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.1915,
+      "step": 49
+    },
+    {
+      "epoch": 0.1711229946524064,
+      "grad_norm": 0.5748466849327087,
+      "learning_rate": 0.0,
+      "loss": 0.3791,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.124688709287936e+16,
+  "total_flos": 1.4419086016512e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null