Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba9d0a4a5c09811c8ff389b7ceaa0e836a98b549ef0e0b95e50909e506bf064
+oid sha256:1d0d0c03c0a620e93cfed795a3e332866d538b99c997dd4d5087833b58dddc45
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:835b6dbbbad154007db3eb6a580b768a9ac33d9b0dd5309b306c7d27de0756b2
+oid sha256:0ea719924057030a0fddf7d19d4791498a42890580e5f1761223042c323c4739
 size 3633466

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6011dbc1beaf916a24aa0692a7ad3787fe62f4d3127d9859b27643438838594d
+oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009914487544925021,
+  "epoch": 0.014871731317387532,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 231.054,
       "eval_steps_per_second": 115.595,
       "step": 10
+    },
+    {
+      "epoch": 0.010905936299417524,
+      "grad_norm": 0.6500622630119324,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.1351,
+      "step": 11
+    },
+    {
+      "epoch": 0.011897385053910026,
+      "grad_norm": 0.5976778864860535,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.1733,
+      "step": 12
+    },
+    {
+      "epoch": 0.012888833808402528,
+      "grad_norm": 0.6121130585670471,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.215,
+      "step": 13
+    },
+    {
+      "epoch": 0.01388028256289503,
+      "grad_norm": 0.640393078327179,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.0551,
+      "step": 14
+    },
+    {
+      "epoch": 0.014871731317387532,
+      "grad_norm": 0.5806251764297485,
+      "learning_rate": 5e-05,
+      "loss": 3.0478,
+      "step": 15
+    },
+    {
+      "epoch": 0.014871731317387532,
+      "eval_loss": 3.0984115600585938,
+      "eval_runtime": 7.2089,
+      "eval_samples_per_second": 235.68,
+      "eval_steps_per_second": 117.909,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 145743764520960.0,
+  "total_flos": 219472963043328.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null