Training in progress, step 168, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5849698230477377bc43d99927ea0b750ff86b3da0cd6f06982ce816ba6dbcd
+oid sha256:8ac95b09d8525db8031f8dbc1d8e3ed07d7e85a7df4228ef043cdaf3ee203236
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c427c14ecb51f7b09cfad05ca6b48fae3ca8b3a89561d714f3b547288cbe22e
+oid sha256:aa4029985d53a5443c979e69946d3dbe088ec242f46eb7a6202b94cf53f44199
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4c2513b077ee0a9d0d20b1ed96188cfd8d5c30d65f28f3d6dee11f2dc6d8ca8
+oid sha256:eb35f7933787785ef92acdac24ff917ef72043d42461a8f1e3ee05f375cdf20a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00328545513b592b6bf311a002e087bb048e374276594cf37ee8782d28887fc
+oid sha256:2f516a6e4e8a8eba956b80cb2ea416b9fd98f0dec12d7d9d9a36274d0eef4a63
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.41042345276872966,
+  "epoch": 0.5472312703583062,
   "eval_steps": 42,
-  "global_step": 126,
+  "global_step": 168,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -333,6 +333,112 @@
       "eval_samples_per_second": 23.321,
       "eval_steps_per_second": 5.864,
       "step": 126
+    },
+    {
+      "epoch": 0.4201954397394137,
+      "grad_norm": 2.6070010662078857,
+      "learning_rate": 8.613974319136958e-05,
+      "loss": 1.313,
+      "step": 129
+    },
+    {
+      "epoch": 0.42996742671009774,
+      "grad_norm": 2.7287192344665527,
+      "learning_rate": 8.54684960502629e-05,
+      "loss": 1.4142,
+      "step": 132
+    },
+    {
+      "epoch": 0.43973941368078173,
+      "grad_norm": 2.9047019481658936,
+      "learning_rate": 8.478412753017433e-05,
+      "loss": 1.4128,
+      "step": 135
+    },
+    {
+      "epoch": 0.4495114006514658,
+      "grad_norm": 3.378373622894287,
+      "learning_rate": 8.408689080954998e-05,
+      "loss": 1.5116,
+      "step": 138
+    },
+    {
+      "epoch": 0.4592833876221498,
+      "grad_norm": 2.828160285949707,
+      "learning_rate": 8.33770438273574e-05,
+      "loss": 1.3085,
+      "step": 141
+    },
+    {
+      "epoch": 0.46905537459283386,
+      "grad_norm": 2.577202081680298,
+      "learning_rate": 8.265484918766243e-05,
+      "loss": 1.3892,
+      "step": 144
+    },
+    {
+      "epoch": 0.4788273615635179,
+      "grad_norm": 2.659550428390503,
+      "learning_rate": 8.192057406248028e-05,
+      "loss": 1.4546,
+      "step": 147
+    },
+    {
+      "epoch": 0.48859934853420195,
+      "grad_norm": 3.5885229110717773,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 1.2797,
+      "step": 150
+    },
+    {
+      "epoch": 0.498371335504886,
+      "grad_norm": 2.8732728958129883,
+      "learning_rate": 8.041687328877567e-05,
+      "loss": 1.405,
+      "step": 153
+    },
+    {
+      "epoch": 0.50814332247557,
+      "grad_norm": 2.7093594074249268,
+      "learning_rate": 7.964800392625129e-05,
+      "loss": 1.4728,
+      "step": 156
+    },
+    {
+      "epoch": 0.5179153094462541,
+      "grad_norm": 2.460803747177124,
+      "learning_rate": 7.886816644444098e-05,
+      "loss": 1.5428,
+      "step": 159
+    },
+    {
+      "epoch": 0.5276872964169381,
+      "grad_norm": 2.5754201412200928,
+      "learning_rate": 7.807764934001874e-05,
+      "loss": 1.332,
+      "step": 162
+    },
+    {
+      "epoch": 0.5374592833876222,
+      "grad_norm": 2.630692481994629,
+      "learning_rate": 7.727674506052743e-05,
+      "loss": 1.4519,
+      "step": 165
+    },
+    {
+      "epoch": 0.5472312703583062,
+      "grad_norm": 3.039989948272705,
+      "learning_rate": 7.646574989618938e-05,
+      "loss": 1.4669,
+      "step": 168
+    },
+    {
+      "epoch": 0.5472312703583062,
+      "eval_loss": 1.471885085105896,
+      "eval_runtime": 22.1606,
+      "eval_samples_per_second": 23.33,
+      "eval_steps_per_second": 5.866,
+      "step": 168
     }
   ],
   "logging_steps": 3,
@@ -352,7 +458,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.503635546098893e+16,
+  "total_flos": 1.267151406146519e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null