Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12084b9e970fe080f2b521cb46a7939d514a0b63ce915757e65c7c135430c9da
+oid sha256:e29e85525a670405b5d249a19f01f5dce0122bbf4960af5aaa8cfcc5e267e463
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8953e314fc29b22217a35e980bf194a9d4ce906850332e607c4a04eb69ef257a
+oid sha256:a840fd1a65a2caa09655874ab3ff22460a990605d275212b30747d06186ceea4
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f32f4edb35882f03fe65e55b40b36ec39527db0c22bc57a50e108342587c75c
+oid sha256:b2790ca2ae94922a641bb14385a0cd060f1f701099a96a3bb2e73b3e356b1b67
 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": 0.006310679611650485,
+  "epoch": 0.008090614886731391,
   "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": 25.417,
       "eval_steps_per_second": 12.714,
       "step": 39
+    },
+    {
+      "epoch": 0.006472491909385114,
+      "grad_norm": 0.993474006652832,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.4233,
+      "step": 40
+    },
+    {
+      "epoch": 0.006634304207119741,
+      "grad_norm": 1.5529276132583618,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.5534,
+      "step": 41
+    },
+    {
+      "epoch": 0.006796116504854369,
+      "grad_norm": 1.223961591720581,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.3423,
+      "step": 42
+    },
+    {
+      "epoch": 0.0069579288025889965,
+      "grad_norm": 1.7816985845565796,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.6016,
+      "step": 43
+    },
+    {
+      "epoch": 0.007119741100323625,
+      "grad_norm": 1.4194049835205078,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.4413,
+      "step": 44
+    },
+    {
+      "epoch": 0.007281553398058253,
+      "grad_norm": 0.9579328894615173,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.3402,
+      "step": 45
+    },
+    {
+      "epoch": 0.00744336569579288,
+      "grad_norm": 1.146324872970581,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.3544,
+      "step": 46
+    },
+    {
+      "epoch": 0.007605177993527508,
+      "grad_norm": 1.090683102607727,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.4601,
+      "step": 47
+    },
+    {
+      "epoch": 0.007766990291262136,
+      "grad_norm": 1.0887632369995117,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.3667,
+      "step": 48
+    },
+    {
+      "epoch": 0.007928802588996763,
+      "grad_norm": 1.3140113353729248,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.3909,
+      "step": 49
+    },
+    {
+      "epoch": 0.008090614886731391,
+      "grad_norm": 0.9621336460113525,
+      "learning_rate": 0.0,
+      "loss": 0.3202,
+      "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": 8599911373209600.0,
+  "total_flos": 1.09887756435456e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null