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:d4fa93565cff642ee223b46502df77abd126352a7d3b926d12b1fa8aaff201bd
+oid sha256:9b4e2da111a5727eb8f2fe2f7581c48eb61b56280dce31a7f4531cf047190392
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95add27b4bc4dd443bff40a096f0111bea14534d1319bc9ee3e974ccacaf3fb9
+oid sha256:c590495afffd018236089728e53f1ccfb02eff672e95a03391e66a3810d89da3
 size 41119636

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": 0.14146772767462423,
+  "epoch": 0.21220159151193635,
   "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": 20.554,
       "eval_steps_per_second": 10.277,
       "step": 10
+    },
+    {
+      "epoch": 0.15561450044208666,
+      "grad_norm": 7.615804195404053,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 4.8278,
+      "step": 11
+    },
+    {
+      "epoch": 0.16976127320954906,
+      "grad_norm": 7.701565742492676,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 3.9847,
+      "step": 12
+    },
+    {
+      "epoch": 0.1839080459770115,
+      "grad_norm": 6.278581619262695,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 3.133,
+      "step": 13
+    },
+    {
+      "epoch": 0.19805481874447392,
+      "grad_norm": 6.357863903045654,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.2536,
+      "step": 14
+    },
+    {
+      "epoch": 0.21220159151193635,
+      "grad_norm": 4.74558687210083,
+      "learning_rate": 5e-05,
+      "loss": 1.9522,
+      "step": 15
+    },
+    {
+      "epoch": 0.21220159151193635,
+      "eval_loss": 1.695694088935852,
+      "eval_runtime": 5.7854,
+      "eval_samples_per_second": 20.742,
+      "eval_steps_per_second": 10.371,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6714878412718080.0,
+  "total_flos": 1.001052425945088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null