Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e80d73d7ea8287d4d49111ae154fa10ab8ecb04101598ec9f712a0f99a038cc
+oid sha256:79694a08f27a7db0d74d836062a867fe6cf7d2d679d4fe6fbfac1f593077df2f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf4ed8d399c02026277e1b7092eccc3798624bd81c61244ae566d3927df0228
+oid sha256:d067b6a0996f030f162989d63e242664e4a29bf1874ecbfe8ff38e1429495143
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666db1a3036f75fb6b26726210e41c4460dd644b6401981dc1b87a82ead0d8c6
+oid sha256:3599a3f132ff4c2767b47f547ee0465ae1ef48e7ce5bed9baf9910032e4a63fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.175054704595186,
+  "epoch": 0.26258205689277897,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 38.794,
       "eval_steps_per_second": 19.477,
       "step": 100
+    },
+    {
+      "epoch": 0.1925601750547046,
+      "grad_norm": 0.8636429905891418,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.1199,
+      "step": 110
+    },
+    {
+      "epoch": 0.2100656455142232,
+      "grad_norm": 1.805497646331787,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.0979,
+      "step": 120
+    },
+    {
+      "epoch": 0.2275711159737418,
+      "grad_norm": 0.6997489333152771,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.0705,
+      "step": 130
+    },
+    {
+      "epoch": 0.24507658643326038,
+      "grad_norm": 0.6966172456741333,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.066,
+      "step": 140
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "grad_norm": 1.7771542072296143,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.0989,
+      "step": 150
+    },
+    {
+      "epoch": 0.26258205689277897,
+      "eval_loss": 0.07951899617910385,
+      "eval_runtime": 6.1499,
+      "eval_samples_per_second": 39.188,
+      "eval_steps_per_second": 19.675,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5000973307084800.0,
+  "total_flos": 7501459960627200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null