Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec19e9feea8736f79d2650b1b52c9f408f080d1f3f4703432126a44bddc2217
+oid sha256:de7e824aac2dfa8f9376f6a450e1d72ed0aa98fd70beae78e4806ff10921e1fd
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaa19755e590e7c4d5099cfeb5e53f473818cce9d3cc2c549379501b08b74baa
+oid sha256:4eb0038e156fa1f9d70baf1b70e10055675e0bdeaf4a9dc97aaf509b9176a951
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14ecaf10f867d641510ce53dbd9769d9f0621e33faaf8ef0ef592d94d206124
+oid sha256:2166f1384d6b7000dadfa39914832766012037ccefa7ee367246ac2c5f6964eb
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4326bed15afbe95f7975c90fd86a88b02f65eb2b3a84aa0cf7b3dd837f7ac4b
+oid sha256:926fbc2e333a53a1af169ec3d357b84d68c7e5099b886dae14ca8ad907aefa5a
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5485714285714286,
+  "epoch": 0.7032967032967034,
   "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": 41.026,
       "eval_steps_per_second": 10.278,
       "step": 39
+    },
+    {
+      "epoch": 0.5626373626373626,
+      "grad_norm": 0.16583934426307678,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9045,
+      "step": 40
+    },
+    {
+      "epoch": 0.5767032967032967,
+      "grad_norm": 0.16519413888454437,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9248,
+      "step": 41
+    },
+    {
+      "epoch": 0.5907692307692308,
+      "grad_norm": 0.16163888573646545,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8944,
+      "step": 42
+    },
+    {
+      "epoch": 0.6048351648351649,
+      "grad_norm": 0.17038829624652863,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9563,
+      "step": 43
+    },
+    {
+      "epoch": 0.6189010989010989,
+      "grad_norm": 0.16273872554302216,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9048,
+      "step": 44
+    },
+    {
+      "epoch": 0.6329670329670329,
+      "grad_norm": 0.1728469431400299,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9209,
+      "step": 45
+    },
+    {
+      "epoch": 0.6470329670329671,
+      "grad_norm": 0.16880929470062256,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.9191,
+      "step": 46
+    },
+    {
+      "epoch": 0.6610989010989011,
+      "grad_norm": 0.16875362396240234,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9281,
+      "step": 47
+    },
+    {
+      "epoch": 0.6751648351648352,
+      "grad_norm": 0.16660304367542267,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9525,
+      "step": 48
+    },
+    {
+      "epoch": 0.6892307692307692,
+      "grad_norm": 0.16343393921852112,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9133,
+      "step": 49
+    },
+    {
+      "epoch": 0.7032967032967034,
+      "grad_norm": 0.1650265008211136,
+      "learning_rate": 0.0,
+      "loss": 0.9154,
+      "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": 4.498754837151744e+16,
+  "total_flos": 5.7676344066048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null