Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660c6c5e67778f682cc5383ee8378cd5ba9a597f047a6d261866ad2bd853bdf6
+oid sha256:b3f6cfbacb332dc04c84be0336fe27175c99f69d333912a4ab2ded0446d76914
 size 767856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23eff95c0d4a651a755f8a3da6b2293079ef8dcfff7673a29436ca22ff25862d
+oid sha256:b03df755550792f9c3a437287c7026accb901cd78bb0721231d5b981f8d51979
 size 1003002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb98ef5303ec81ed369a5e6d1fe97c66c7de85c1a6cadb74ab2fa30d5017f2f4
+oid sha256:eb9cdf9545744c222bbf4ce56517460021ff9793bd6d0c961288d836aff47084
 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": 0.025130890052356022,
+  "epoch": 0.03221908981071285,
   "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": 110.44,
       "eval_steps_per_second": 55.22,
       "step": 39
+    },
+    {
+      "epoch": 0.02577527184857028,
+      "grad_norm": 2.051464796066284,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.3642,
+      "step": 40
+    },
+    {
+      "epoch": 0.026419653644784536,
+      "grad_norm": 1.3412200212478638,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 7.4789,
+      "step": 41
+    },
+    {
+      "epoch": 0.027064035440998793,
+      "grad_norm": 1.0841667652130127,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 7.6536,
+      "step": 42
+    },
+    {
+      "epoch": 0.02770841723721305,
+      "grad_norm": 1.1670408248901367,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 7.7881,
+      "step": 43
+    },
+    {
+      "epoch": 0.028352799033427304,
+      "grad_norm": 2.0704867839813232,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 7.6421,
+      "step": 44
+    },
+    {
+      "epoch": 0.02899718082964156,
+      "grad_norm": 1.0424221754074097,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.3945,
+      "step": 45
+    },
+    {
+      "epoch": 0.02964156262585582,
+      "grad_norm": 1.2187137603759766,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 7.8543,
+      "step": 46
+    },
+    {
+      "epoch": 0.030285944422070075,
+      "grad_norm": 1.103108286857605,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 7.4402,
+      "step": 47
+    },
+    {
+      "epoch": 0.030930326218284333,
+      "grad_norm": 1.0252392292022705,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 7.3845,
+      "step": 48
+    },
+    {
+      "epoch": 0.03157470801449859,
+      "grad_norm": 1.0439541339874268,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 7.4411,
+      "step": 49
+    },
+    {
+      "epoch": 0.03221908981071285,
+      "grad_norm": 1.1140565872192383,
+      "learning_rate": 0.0,
+      "loss": 7.2666,
+      "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": 85113745440768.0,
+  "total_flos": 109141070708736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null