Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:640fb97455fc6057d1c7fc2b42a196c78995e9168f3a2a810db6839300c2762c
+oid sha256:df6596d1fae343b8c802e74d34a3967f9330ccf6f76e835ac7db0dd03cae7098
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baef85c1828d77eb506f5d52be066bcd1bd47c0105f1e78b89038a6652bda682
+oid sha256:30900fa383cfd975e2c21cf53cc8bd5e77743756747c586a07482bc28b24f006
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c72461d8b102f8348796119289aad1a7993b551f980fac40ec203302a5c72e0
+oid sha256:f8e9eae442f771da3806c99b5cd6522f74f754ffe88b669e7b10de01669cb969
 size 14244

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": 0.0026583734503472073,
+  "epoch": 0.0034081710901887274,
   "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": 6.822,
       "eval_steps_per_second": 3.411,
       "step": 39
+    },
+    {
+      "epoch": 0.002726536872150982,
+      "grad_norm": 3.731128454208374,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.7914,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027947002939547566,
+      "grad_norm": 2.8531653881073,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.7838,
+      "step": 41
+    },
+    {
+      "epoch": 0.0028628637157585312,
+      "grad_norm": 2.8280680179595947,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4223,
+      "step": 42
+    },
+    {
+      "epoch": 0.002931027137562306,
+      "grad_norm": 2.862281084060669,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.5895,
+      "step": 43
+    },
+    {
+      "epoch": 0.00299919055936608,
+      "grad_norm": 2.7972028255462646,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.6017,
+      "step": 44
+    },
+    {
+      "epoch": 0.0030673539811698547,
+      "grad_norm": 4.903096675872803,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5924,
+      "step": 45
+    },
+    {
+      "epoch": 0.0031355174029736293,
+      "grad_norm": 5.058813571929932,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.473,
+      "step": 46
+    },
+    {
+      "epoch": 0.003203680824777404,
+      "grad_norm": 3.77838134765625,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.6534,
+      "step": 47
+    },
+    {
+      "epoch": 0.0032718442465811785,
+      "grad_norm": 3.0591816902160645,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.6966,
+      "step": 48
+    },
+    {
+      "epoch": 0.0033400076683849527,
+      "grad_norm": 2.853864908218384,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.5413,
+      "step": 49
+    },
+    {
+      "epoch": 0.0034081710901887274,
+      "grad_norm": 2.967231035232544,
+      "learning_rate": 0.0,
+      "loss": 0.5969,
+      "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": 2.3146883247085978e+17,
+  "total_flos": 2.967549134241792e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null