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:b9aadf29a0eea20c068c61052867df6b7a81ff0bcfccbd0c85a49c275d7ae0e5
+oid sha256:a0c13189860da3bcd462596b8e7015c39fce23d62574100e92f6d55e9c745f71
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:146fc970ac2733a2a8fac4585bbf9236dbe1698d9e6acc07b4a1d43df0667e23
+oid sha256:7704f9c849864d0154c33d61767d679407c50c8f5f7e5c7e0114fbcfd2cc52d4
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa3a4caf35fd209d48f11310346c98ca5b35cff91643ace351650698faea638
+oid sha256:2c17ca34385562456afadba288e9aa425ed1218b489da5d7634961839d193b4a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03877703206562267,
+  "epoch": 0.049714143673875215,
   "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": 12.368,
       "eval_steps_per_second": 6.184,
       "step": 39
+    },
+    {
+      "epoch": 0.039771314939100175,
+      "grad_norm": 0.5207390785217285,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.85,
+      "step": 40
+    },
+    {
+      "epoch": 0.04076559781257768,
+      "grad_norm": 0.49141305685043335,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.8256,
+      "step": 41
+    },
+    {
+      "epoch": 0.041759880686055184,
+      "grad_norm": 0.49803686141967773,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 1.0561,
+      "step": 42
+    },
+    {
+      "epoch": 0.04275416355953269,
+      "grad_norm": 0.5928795337677002,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 1.0151,
+      "step": 43
+    },
+    {
+      "epoch": 0.043748446433010194,
+      "grad_norm": 0.4802905023097992,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.9441,
+      "step": 44
+    },
+    {
+      "epoch": 0.0447427293064877,
+      "grad_norm": 0.45927828550338745,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.9223,
+      "step": 45
+    },
+    {
+      "epoch": 0.0457370121799652,
+      "grad_norm": 0.5768618583679199,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 1.1136,
+      "step": 46
+    },
+    {
+      "epoch": 0.04673129505344271,
+      "grad_norm": 0.6009936332702637,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 1.1245,
+      "step": 47
+    },
+    {
+      "epoch": 0.047725577926920205,
+      "grad_norm": 0.9392962455749512,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 1.2505,
+      "step": 48
+    },
+    {
+      "epoch": 0.04871986080039771,
+      "grad_norm": 0.5324287414550781,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.8628,
+      "step": 49
+    },
+    {
+      "epoch": 0.049714143673875215,
+      "grad_norm": 0.4643092751502991,
+      "learning_rate": 0.0,
+      "loss": 0.9188,
+      "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": 1.3904966757384192e+16,
+  "total_flos": 1.7547965428137984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null