Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cc51fb6d2512cb36a3b23e155e7b3df71456eda31ed02c953ce7a24738b4dba
+oid sha256:6bbaec19efb64fdbff88b6d715adee9e2871c20fa86828befa335053f4ba3924
 size 684272496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a2aea5afb85a30fb8f24c02c2c3a736fd2ad3ac3b10391c3c6aeac430f24744
+oid sha256:e405cb3a57a3f99e1b936fb48e373e6363d394a0629ecb421d0f277e27918958
 size 81730196

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb38c8d79b6f38bb790b1913bfdbc32aaa50622962ddeebd7fe86be4a71c506
+oid sha256:a2569b8843c8005365c4198b2d30ca0a109afe93a67c8e9ae4255460f521ed82
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e92f89ad47b97f18bdec3c5ec118ea00d4a1eb5574a7b3527978d8e4990243d
+oid sha256:e0681b36578a1688994f6fd5decaf01633a0ce062d702bffa0ee6216dfc94b7e
 size 14512

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": 0.027273502088127503,
+  "epoch": 0.04091025313219126,
   "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": 11.054,
       "eval_steps_per_second": 2.766,
       "step": 10
+    },
+    {
+      "epoch": 0.030000852296940255,
+      "grad_norm": 5.722675800323486,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 0.2533,
+      "step": 11
+    },
+    {
+      "epoch": 0.03272820250575301,
+      "grad_norm": 2.8063879013061523,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.1486,
+      "step": 12
+    },
+    {
+      "epoch": 0.035455552714565755,
+      "grad_norm": 1.7891703844070435,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.1449,
+      "step": 13
+    },
+    {
+      "epoch": 0.0381829029233785,
+      "grad_norm": 2.760188579559326,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.1632,
+      "step": 14
+    },
+    {
+      "epoch": 0.04091025313219126,
+      "grad_norm": 0.9324430227279663,
+      "learning_rate": 5e-05,
+      "loss": 0.1375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04091025313219126,
+      "eval_loss": 0.21234437823295593,
+      "eval_runtime": 219.4952,
+      "eval_samples_per_second": 11.253,
+      "eval_steps_per_second": 2.816,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0910675345801216e+17,
+  "total_flos": 3.1366013018701824e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null