Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d71b937e8a1599c663d332b51128ef293a0870c9aae1e6fa8b713ea534003a8
+oid sha256:6b561aa476f50acfc69110676633665331b852de55c45dd6524107482da6ce1d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7fec050739a173db66e6af212ef2cca07c5dadda9480f765373fdb5c86fd2e5
+oid sha256:2ea8e0005d6fc73b708b66a5128e5e94122532b4dd2d8a1b18abc5e5a55db996
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a72025a75dfde9f6316cf7e78853946a2bfc45ed559fba6d15f16c4440f7ee5
+oid sha256:3ac9e56eb478bb7f690364dd51912aceda670c4f7d68fb18770d429dcec15f3a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ef6f22d42e935fbf13f0628837cd5d2513a098109335b9474dbc5e57db0c7d
+oid sha256:b99c176154c32f3c6148d434b4181fc39da3594f48ce393bb9e59b1fd24bca4d
 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": 0.10717966334592924,
+  "epoch": 0.13740982480247338,
   "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": 11.003,
       "eval_steps_per_second": 2.751,
       "step": 39
+    },
+    {
+      "epoch": 0.1099278598419787,
+      "grad_norm": 0.22532352805137634,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5904,
+      "step": 40
+    },
+    {
+      "epoch": 0.11267605633802817,
+      "grad_norm": 0.23213639855384827,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6341,
+      "step": 41
+    },
+    {
+      "epoch": 0.11542425283407763,
+      "grad_norm": 0.25779661536216736,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6331,
+      "step": 42
+    },
+    {
+      "epoch": 0.1181724493301271,
+      "grad_norm": 0.23315420746803284,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5517,
+      "step": 43
+    },
+    {
+      "epoch": 0.12092064582617656,
+      "grad_norm": 0.20655833184719086,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.6658,
+      "step": 44
+    },
+    {
+      "epoch": 0.12366884232222604,
+      "grad_norm": 0.23243050277233124,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6034,
+      "step": 45
+    },
+    {
+      "epoch": 0.1264170388182755,
+      "grad_norm": 0.2170373648405075,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.6216,
+      "step": 46
+    },
+    {
+      "epoch": 0.12916523531432497,
+      "grad_norm": 0.22000928223133087,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5846,
+      "step": 47
+    },
+    {
+      "epoch": 0.13191343181037443,
+      "grad_norm": 0.2359149158000946,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6,
+      "step": 48
+    },
+    {
+      "epoch": 0.13466162830642392,
+      "grad_norm": 0.2346540242433548,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6019,
+      "step": 49
+    },
+    {
+      "epoch": 0.13740982480247338,
+      "grad_norm": 0.21734513342380524,
+      "learning_rate": 0.0,
+      "loss": 0.6008,
+      "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": 9.258753298834391e+17,
+  "total_flos": 1.1870196536967168e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null