Training in progress, step 4, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c8b26291f003bcaf7618bdfe03016fa23d8a28690f562da186ca74eb245103
+oid sha256:a8cae26ec0ea9b8d8aef33be9f3910cf76cec4588f2cd8f1d19ee5a3e49f0556
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8317daeb7ac31e6bfcfda0a883145f909b974fe229b13d8448f31c6fee19e1d
+oid sha256:c441286cead4cc051e15c136fcf8badf856de665a6408a2a2f403dbd04818e64
 size 14714004

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2171e7b0ac834a8c916eb3c49a6743d2794cc931db7dd16fb3d556d8abf990e
+oid sha256:a70d38a1d9cebbea8036393a9b3d797a45881fdb89c1ef14ae4312bc6dae3141
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3a2eb038ed1471459b5c14771495b2b5d5df9ab5e9310238a3ebfb6da55a72
+oid sha256:c237a6ed32c2da6e4c48e32ba0037725e16c7d85eed174d3b3a02e3d6735c096
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccb90b25918d4f2c5d36d69e07b960e3069c1895bfb75fdabb4bf5446606885
+oid sha256:c286a144f47b2686fa63ff203b2c0e28b8d4edcbda01b8d4ac64a1aac8b73b36
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9553c875aa0c1e7d2a3638caa0cbe2b098306af2e7edbbe5b90fd604a0bcb68b
+oid sha256:20f883c54dee1916e8ac0b1483920fbd30f191d049387ff869103c28e4937771
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3368421052631579,
+  "epoch": 0.6736842105263158,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 409.043,
       "eval_steps_per_second": 51.13,
       "step": 2
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 2.549992561340332,
+      "learning_rate": 3e-05,
+      "loss": 12.1333,
+      "step": 3
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 2.6916556358337402,
+      "learning_rate": 4e-05,
+      "loss": 11.0508,
+      "step": 4
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "eval_loss": 0.70751953125,
+      "eval_runtime": 0.0968,
+      "eval_samples_per_second": 413.083,
+      "eval_steps_per_second": 51.635,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 955934092296192.0,
+  "total_flos": 1911868184592384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null