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:ef12fc154f65e02202852589cfb64f0ddefa61cbec5cce250d02ea66479be516
+oid sha256:593dfda10a1e5a397dde3226f0337d236158ab4ed3f289ba757349e60e643a41
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e0c63f2c8720aeb33d96d1a53ee8279717548ed6211211cf27cf5e208d1cad
+oid sha256:6a695e5fdbfe74c0e077089926808e72737bd0bb657e1457d8d97969df80f2dc
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f059df7c18fbe96aebe483d58dfa306f9104df1fafc197ffe97cfff90eea1d
+oid sha256:b12a183087b8e7b8d82ac60053169790191d496904101efcb0b8553eac5c5267
 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": 0.019306930693069307,
+  "epoch": 0.024752475247524754,
   "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": 61.263,
       "eval_steps_per_second": 30.667,
       "step": 39
+    },
+    {
+      "epoch": 0.019801980198019802,
+      "grad_norm": 0.6241593956947327,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 2.3477,
+      "step": 40
+    },
+    {
+      "epoch": 0.020297029702970298,
+      "grad_norm": 0.7181453108787537,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 2.5936,
+      "step": 41
+    },
+    {
+      "epoch": 0.020792079207920793,
+      "grad_norm": 0.590019941329956,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 2.5446,
+      "step": 42
+    },
+    {
+      "epoch": 0.02128712871287129,
+      "grad_norm": 0.6002688407897949,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 2.5584,
+      "step": 43
+    },
+    {
+      "epoch": 0.02178217821782178,
+      "grad_norm": 0.6000116467475891,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 2.3596,
+      "step": 44
+    },
+    {
+      "epoch": 0.022277227722772276,
+      "grad_norm": 0.48489993810653687,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 2.4035,
+      "step": 45
+    },
+    {
+      "epoch": 0.02277227722772277,
+      "grad_norm": 0.590663492679596,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 2.5489,
+      "step": 46
+    },
+    {
+      "epoch": 0.023267326732673267,
+      "grad_norm": 0.7829977869987488,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 2.6551,
+      "step": 47
+    },
+    {
+      "epoch": 0.023762376237623763,
+      "grad_norm": 0.6934583783149719,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 2.5088,
+      "step": 48
+    },
+    {
+      "epoch": 0.024257425742574258,
+      "grad_norm": 0.5398517847061157,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 2.4165,
+      "step": 49
+    },
+    {
+      "epoch": 0.024752475247524754,
+      "grad_norm": 0.7464584112167358,
+      "learning_rate": 0.0,
+      "loss": 2.5148,
+      "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": 1227801495601152.0,
+  "total_flos": 1624279061889024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null