Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82feb456804e11aa1aac6b468165868ea3785731a1ee138e33aa75a210960b7b
+oid sha256:25d492a66140da25111f7b6590b48e1e2522eb272fca4cd2a544bb701950eeb2
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4507c96ac9bfa04398e062e48747aa5a56ab5b558ae2b7eeedbfe456725d8f
+oid sha256:11214110bee1549bf2fa904dd92d1a15f9528976746e014c11dd5a5e97d8fbac
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38cd886aae1e330a5a2703d9ebe2022b4cfb2765da717985c0e0f3c11bf70a76
+oid sha256:6edb796ecc8ec0d9b80850298ebb2d1091e83fce1522424d1f6bd231066a0bd2
 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": 0.23672230652503792,
+  "epoch": 0.30349013657056145,
   "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": 12.854,
       "eval_steps_per_second": 6.427,
       "step": 39
+    },
+    {
+      "epoch": 0.24279210925644917,
+      "grad_norm": 0.4682345688343048,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1725,
+      "step": 40
+    },
+    {
+      "epoch": 0.2488619119878604,
+      "grad_norm": 0.5020042657852173,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.2094,
+      "step": 41
+    },
+    {
+      "epoch": 0.2549317147192716,
+      "grad_norm": 0.4078826308250427,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.2058,
+      "step": 42
+    },
+    {
+      "epoch": 0.26100151745068284,
+      "grad_norm": 0.4525303244590759,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.194,
+      "step": 43
+    },
+    {
+      "epoch": 0.26707132018209406,
+      "grad_norm": 0.4362923800945282,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.2323,
+      "step": 44
+    },
+    {
+      "epoch": 0.2731411229135053,
+      "grad_norm": 0.4615617096424103,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1723,
+      "step": 45
+    },
+    {
+      "epoch": 0.27921092564491656,
+      "grad_norm": 0.4249371886253357,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2361,
+      "step": 46
+    },
+    {
+      "epoch": 0.2852807283763278,
+      "grad_norm": 0.9497168064117432,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 1.1992,
+      "step": 47
+    },
+    {
+      "epoch": 0.291350531107739,
+      "grad_norm": 0.4832310080528259,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.1603,
+      "step": 48
+    },
+    {
+      "epoch": 0.29742033383915023,
+      "grad_norm": 0.42413023114204407,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.2171,
+      "step": 49
+    },
+    {
+      "epoch": 0.30349013657056145,
+      "grad_norm": 0.3935677111148834,
+      "learning_rate": 0.0,
+      "loss": 1.1498,
+      "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": 6.273061332870758e+16,
+  "total_flos": 8.04238632419328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null