Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f0a2fc6267937deecd4e28f6482a0100df3ba2d6024141559399cff3e234c9
+oid sha256:329378dcd8863dd1132524df42b47395224d3c024bbd7d960f87477002dd1384
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56c48ea34e8e1f7978b2fa1bbc1d3e19e17cbee609e6497b1fc38447a256ae46
+oid sha256:9d9a92d713109b69525d50f8ecef5a8130d6d56c448562836aa2a24e6c42f907
 size 18810036

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215560264689880257fdb7c8617f72affe41ba766add2cacbdb9ef5c31af674a
+oid sha256:b9dd667825d0dab5caa2e65e22da469d0963de92aa758a9dce7b8ab454668856
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94b39e8c3c264c7a29205e1143cc420054d6c2a4ccd0b8144d83abbcc8b6f6ba
+oid sha256:5119473e947f7d1bba2eca7c2f753f981bf55675729e7d3fb450b4cf6e4da76a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68bbed80b67563400d0c339f2aeac8b6acb4d6f9bf8cac433d81746ac01dad0d
+oid sha256:f2cd64c80eb5332f5dcb367d48de4f86cd002cd9fef0dc3e77fb79b0e90bb8e7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177ef792e0ddb06784c822410339968bdadccad87bb5f2ee4a2bcbf704576a5a
+oid sha256:cd68af42e19bdaf4b38b7c7e24fff809eafaccf27727e5157b9ae95302a22e07
 size 15024

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": 0.09614791987673343,
+  "epoch": 0.12326656394453005,
   "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": 140.527,
       "eval_steps_per_second": 17.585,
       "step": 39
+    },
+    {
+      "epoch": 0.09861325115562404,
+      "grad_norm": 0.2994353771209717,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0195,
+      "step": 40
+    },
+    {
+      "epoch": 0.10107858243451463,
+      "grad_norm": 0.19609463214874268,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0397,
+      "step": 41
+    },
+    {
+      "epoch": 0.10354391371340524,
+      "grad_norm": 0.8093880414962769,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0186,
+      "step": 42
+    },
+    {
+      "epoch": 0.10600924499229585,
+      "grad_norm": 0.6355484127998352,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.024,
+      "step": 43
+    },
+    {
+      "epoch": 0.10847457627118644,
+      "grad_norm": 0.41448116302490234,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0117,
+      "step": 44
+    },
+    {
+      "epoch": 0.11093990755007704,
+      "grad_norm": 0.775438129901886,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0383,
+      "step": 45
+    },
+    {
+      "epoch": 0.11340523882896764,
+      "grad_norm": 0.8112552165985107,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0306,
+      "step": 46
+    },
+    {
+      "epoch": 0.11587057010785824,
+      "grad_norm": 0.46484261751174927,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0129,
+      "step": 47
+    },
+    {
+      "epoch": 0.11833590138674885,
+      "grad_norm": 0.7908012866973877,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0282,
+      "step": 48
+    },
+    {
+      "epoch": 0.12080123266563944,
+      "grad_norm": 0.3184359073638916,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0163,
+      "step": 49
+    },
+    {
+      "epoch": 0.12326656394453005,
+      "grad_norm": 0.32925423979759216,
+      "learning_rate": 0.0,
+      "loss": 0.0087,
+      "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