Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a96a12628b3e0170d420e6c480f3112fd0b4aa7e7e665c9447fb9a39a2fc8908
+oid sha256:d02005adff8f90f7b4220dc231f3eb98a1c4f6c5a04a0e49b184b3425e70f753
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8b052e5a8ff99b128943144629d0c75360af506a32296070193695b49a665a6
+oid sha256:74173cc1483f3ca831484d78893b0c82016835bffb1aafc86bcd04290ad3950b
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2790fbe4c7b99ec49d4b4c03b9ab968ac7530589725905d8485c8345302070f4
+oid sha256:970eb02fd02107946134f26fbe7431207b9e97bd6bce050f8f42ba4eba61c700
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3187250996015936,
+  "epoch": 0.47808764940239046,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 9.311,
       "eval_steps_per_second": 4.673,
       "step": 50
+    },
+    {
+      "epoch": 0.3250996015936255,
+      "grad_norm": 0.20304904878139496,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.025,
+      "step": 51
+    },
+    {
+      "epoch": 0.3314741035856574,
+      "grad_norm": 0.18800340592861176,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0323,
+      "step": 52
+    },
+    {
+      "epoch": 0.33784860557768925,
+      "grad_norm": 0.17694565653800964,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.0348,
+      "step": 53
+    },
+    {
+      "epoch": 0.34422310756972113,
+      "grad_norm": 0.2166670709848404,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0458,
+      "step": 54
+    },
+    {
+      "epoch": 0.350597609561753,
+      "grad_norm": 0.16114047169685364,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0334,
+      "step": 55
+    },
+    {
+      "epoch": 0.3569721115537849,
+      "grad_norm": 0.25571057200431824,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.04,
+      "step": 56
+    },
+    {
+      "epoch": 0.3633466135458167,
+      "grad_norm": 0.28820469975471497,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0357,
+      "step": 57
+    },
+    {
+      "epoch": 0.3697211155378486,
+      "grad_norm": 0.22852648794651031,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0419,
+      "step": 58
+    },
+    {
+      "epoch": 0.37609561752988047,
+      "grad_norm": 0.22057059407234192,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.0259,
+      "step": 59
+    },
+    {
+      "epoch": 0.38247011952191234,
+      "grad_norm": 0.251699835062027,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0323,
+      "step": 60
+    },
+    {
+      "epoch": 0.3888446215139442,
+      "grad_norm": 0.4483722150325775,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0478,
+      "step": 61
+    },
+    {
+      "epoch": 0.3952191235059761,
+      "grad_norm": 0.20875990390777588,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0316,
+      "step": 62
+    },
+    {
+      "epoch": 0.401593625498008,
+      "grad_norm": 0.27821633219718933,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0452,
+      "step": 63
+    },
+    {
+      "epoch": 0.40796812749003986,
+      "grad_norm": 0.2893379032611847,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0434,
+      "step": 64
+    },
+    {
+      "epoch": 0.41434262948207173,
+      "grad_norm": 0.2663540244102478,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0256,
+      "step": 65
+    },
+    {
+      "epoch": 0.4207171314741036,
+      "grad_norm": 0.16980110108852386,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0288,
+      "step": 66
+    },
+    {
+      "epoch": 0.42709163346613543,
+      "grad_norm": 0.36909863352775574,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0238,
+      "step": 67
+    },
+    {
+      "epoch": 0.4334661354581673,
+      "grad_norm": 0.7255321741104126,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0393,
+      "step": 68
+    },
+    {
+      "epoch": 0.4398406374501992,
+      "grad_norm": 0.5421790480613708,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0505,
+      "step": 69
+    },
+    {
+      "epoch": 0.44621513944223107,
+      "grad_norm": 0.4364238381385803,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0218,
+      "step": 70
+    },
+    {
+      "epoch": 0.45258964143426295,
+      "grad_norm": 0.37261253595352173,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0376,
+      "step": 71
+    },
+    {
+      "epoch": 0.4589641434262948,
+      "grad_norm": 0.3598557114601135,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0248,
+      "step": 72
+    },
+    {
+      "epoch": 0.4653386454183267,
+      "grad_norm": 0.32301172614097595,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0396,
+      "step": 73
+    },
+    {
+      "epoch": 0.4717131474103586,
+      "grad_norm": 0.21462203562259674,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0217,
+      "step": 74
+    },
+    {
+      "epoch": 0.47808764940239046,
+      "grad_norm": 0.8589568138122559,
+      "learning_rate": 0.0,
+      "loss": 0.0735,
+      "step": 75
+    },
+    {
+      "epoch": 0.47808764940239046,
+      "eval_loss": 0.040345437824726105,
+      "eval_runtime": 28.5358,
+      "eval_samples_per_second": 9.287,
+      "eval_steps_per_second": 4.661,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.33004802392064e+17,
+  "total_flos": 1.99507203588096e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null