Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81aa585871023ed118436bbe1f86b78109808e3fa693f9ef35345e0f4414f3f0
+oid sha256:d32022e027de0916d01dc718dda77327f706af43b8546cc3f3587e21f4a01bab
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2aa0ca9ef890d5d7060ee9ba9a60c83169e2dd854e7049cd3a386c1c71e95f8b
+oid sha256:920b642cfaeac219c10bdc8e03223db8ae187e5fb1ead4088a0e73e5e9766c0d
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025557011795543906,
+  "epoch": 0.0327653997378768,
   "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": 205.298,
       "eval_steps_per_second": 102.689,
       "step": 39
+    },
+    {
+      "epoch": 0.02621231979030144,
+      "grad_norm": 0.013880622573196888,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9314,
+      "step": 40
+    },
+    {
+      "epoch": 0.026867627785058978,
+      "grad_norm": 0.019777296110987663,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 11.9305,
+      "step": 41
+    },
+    {
+      "epoch": 0.027522935779816515,
+      "grad_norm": 0.013822672888636589,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.9314,
+      "step": 42
+    },
+    {
+      "epoch": 0.02817824377457405,
+      "grad_norm": 0.016023075208067894,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 11.9313,
+      "step": 43
+    },
+    {
+      "epoch": 0.028833551769331587,
+      "grad_norm": 0.01633632369339466,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 11.931,
+      "step": 44
+    },
+    {
+      "epoch": 0.02948885976408912,
+      "grad_norm": 0.014971333555877209,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9318,
+      "step": 45
+    },
+    {
+      "epoch": 0.03014416775884666,
+      "grad_norm": 0.01602235995233059,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 11.9318,
+      "step": 46
+    },
+    {
+      "epoch": 0.030799475753604193,
+      "grad_norm": 0.013982513919472694,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 11.9317,
+      "step": 47
+    },
+    {
+      "epoch": 0.03145478374836173,
+      "grad_norm": 0.01966976933181286,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 11.9299,
+      "step": 48
+    },
+    {
+      "epoch": 0.03211009174311927,
+      "grad_norm": 0.018536817282438278,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 11.9314,
+      "step": 49
+    },
+    {
+      "epoch": 0.0327653997378768,
+      "grad_norm": 0.01766209863126278,
+      "learning_rate": 0.0,
+      "loss": 11.9292,
+      "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": 233834545152.0,
+  "total_flos": 299787878400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null