Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c4e9ad06bda0f1051506cc5e549dcf5fc9c7571b4e20abef164bf2e570e5ab8
+oid sha256:20ec424f951f290c8bc554e2925bd9a8d579978c28dcdb93518b2c7a5e320116
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e02d7389a9d974a9cc11d77b77f48bce8b2f039e0675ef37766472d16c3963
+oid sha256:114a4d3ba6007e9bef0218db0fba723b12067c0bf8b2e1f7b11ab7addef8e22f
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89aa540b8c3fabbcd74d788f9d4a71f3d52d803910db8076339022610c2b0f1f
+oid sha256:ae21b9c450d7f49fec15852599f737b62bdf51a383326ec84ee14cbc3c8398db
 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": 0.09923664122137404,
+  "epoch": 0.1272264631043257,
   "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": 40.293,
       "eval_steps_per_second": 20.147,
       "step": 39
+    },
+    {
+      "epoch": 0.10178117048346055,
+      "grad_norm": 1.3084092140197754,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.1543,
+      "step": 40
+    },
+    {
+      "epoch": 0.10432569974554708,
+      "grad_norm": 2.607229232788086,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.2427,
+      "step": 41
+    },
+    {
+      "epoch": 0.10687022900763359,
+      "grad_norm": 2.31429123878479,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.1742,
+      "step": 42
+    },
+    {
+      "epoch": 0.10941475826972011,
+      "grad_norm": 2.2048234939575195,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.1644,
+      "step": 43
+    },
+    {
+      "epoch": 0.11195928753180662,
+      "grad_norm": 0.9953597784042358,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.0656,
+      "step": 44
+    },
+    {
+      "epoch": 0.11450381679389313,
+      "grad_norm": 1.6188597679138184,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.155,
+      "step": 45
+    },
+    {
+      "epoch": 0.11704834605597965,
+      "grad_norm": 1.3625197410583496,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.1116,
+      "step": 46
+    },
+    {
+      "epoch": 0.11959287531806616,
+      "grad_norm": 0.8615650534629822,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.038,
+      "step": 47
+    },
+    {
+      "epoch": 0.12213740458015267,
+      "grad_norm": 1.747086763381958,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.3618,
+      "step": 48
+    },
+    {
+      "epoch": 0.12468193384223919,
+      "grad_norm": 1.5428842306137085,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.1127,
+      "step": 49
+    },
+    {
+      "epoch": 0.1272264631043257,
+      "grad_norm": 1.6774532794952393,
+      "learning_rate": 0.0,
+      "loss": 0.1539,
+      "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": 1950379589763072.0,
+  "total_flos": 2500486653542400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null