Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9989edd6d39aaf8961b5a34753ec6791eebf90f118027c4d2afd725ea07813e3
+oid sha256:befa92f02bbdfac750e4f599ad8c7b1e4140bed9bf6845394ddd8ed9b92edb7a
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d0105998f86b85fc7372df3cd1e994bb06439ed64679f8a0d6d8141ace9aa9
+oid sha256:adca7e98548af5bc34a7efa8e9c78f29f4e1917f94c8546f264190d6c7815cd9
 size 23159290

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340592f5e69d9225e347295e4162c62abff7816a6b4972749339e4dadb7c1304
+oid sha256:d3dedf9126e77dde77e0ce9a1e7c64a308e4038dabaca3d26aa526a1473a4967
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cac6703db676f115b44e685f7aab5cd5b2de97d46fa9573dfe9f79f5e9ff058
+oid sha256:e07fcffb67adf47923fe9808d65157169dd9ec2fb8da58d4f5235ab405a8112e
 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": 0.009277499832737382,
+  "epoch": 0.011894230554791517,
   "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": 39.819,
       "eval_steps_per_second": 9.955,
       "step": 39
+    },
+    {
+      "epoch": 0.009515384443833213,
+      "grad_norm": 0.6363677382469177,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0181,
+      "step": 40
+    },
+    {
+      "epoch": 0.009753269054929044,
+      "grad_norm": 0.5468412637710571,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0182,
+      "step": 41
+    },
+    {
+      "epoch": 0.009991153666024873,
+      "grad_norm": 0.6606681942939758,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0205,
+      "step": 42
+    },
+    {
+      "epoch": 0.010229038277120704,
+      "grad_norm": 0.5074648261070251,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0163,
+      "step": 43
+    },
+    {
+      "epoch": 0.010466922888216535,
+      "grad_norm": 0.27615487575531006,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0218,
+      "step": 44
+    },
+    {
+      "epoch": 0.010704807499312364,
+      "grad_norm": 0.4286714196205139,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0221,
+      "step": 45
+    },
+    {
+      "epoch": 0.010942692110408195,
+      "grad_norm": 0.49691057205200195,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0504,
+      "step": 46
+    },
+    {
+      "epoch": 0.011180576721504026,
+      "grad_norm": 0.4235456585884094,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0221,
+      "step": 47
+    },
+    {
+      "epoch": 0.011418461332599855,
+      "grad_norm": 0.6265489459037781,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0074,
+      "step": 48
+    },
+    {
+      "epoch": 0.011656345943695686,
+      "grad_norm": 0.4294980466365814,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0147,
+      "step": 49
+    },
+    {
+      "epoch": 0.011894230554791517,
+      "grad_norm": 0.5574062466621399,
+      "learning_rate": 0.0,
+      "loss": 0.0383,
+      "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": 1.2077177668160717e+17,
+  "total_flos": 1.548356111302656e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null