Training in progress, step 204, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7273ba923906b04b87992eae4005ab0c8dc4da4808ad7e8a3b8ab902f05d901
+oid sha256:13acbad963ec40074c567d0d1784741f6961767387ad3467d2cb553791d2e54e
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b08f6a6bee912a14eac6fe7863008999f3647480e4a08bce79f58c1b92e19e
+oid sha256:57a427fb02e64b2e9c07be952273516c0846d810883556edaa06d8b17464ff05
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34186b94f008aa4de4418533e839ad95cc0707e02f4933eee512f4e8d5d15989
+oid sha256:fb6833ca1600bf131a99c9282df1f52267ed44a81a8c0477f031f940e545f8af
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21ce5519aba36efeb75a8dad39ab6bd85bd42d0ae24cbc1f5cfa5d96741b8bc
+oid sha256:5f9839d107756d9c8815de9164f2ebf92c05b3536704a349ca5892084df7663e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011454753722794959,
+  "epoch": 0.013745704467353952,
   "eval_steps": 34,
-  "global_step": 170,
+  "global_step": 204,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -447,6 +447,98 @@
       "eval_samples_per_second": 14.035,
       "eval_steps_per_second": 1.755,
       "step": 170
+    },
+    {
+      "epoch": 0.011522134627046696,
+      "grad_norm": 0.7096220850944519,
+      "learning_rate": 3.17617799075421e-05,
+      "loss": 0.7807,
+      "step": 171
+    },
+    {
+      "epoch": 0.0117242773398019,
+      "grad_norm": 0.7657400369644165,
+      "learning_rate": 3.1178227669141744e-05,
+      "loss": 0.7858,
+      "step": 174
+    },
+    {
+      "epoch": 0.011926420052557105,
+      "grad_norm": 0.8024412393569946,
+      "learning_rate": 3.0591067519763895e-05,
+      "loss": 0.8122,
+      "step": 177
+    },
+    {
+      "epoch": 0.01212856276531231,
+      "grad_norm": 0.6976025700569153,
+      "learning_rate": 3.0000642344401113e-05,
+      "loss": 0.8288,
+      "step": 180
+    },
+    {
+      "epoch": 0.012330705478067515,
+      "grad_norm": 0.6966779828071594,
+      "learning_rate": 2.9407296934729227e-05,
+      "loss": 0.793,
+      "step": 183
+    },
+    {
+      "epoch": 0.012532848190822721,
+      "grad_norm": 0.7219818830490112,
+      "learning_rate": 2.8811377787758636e-05,
+      "loss": 0.7883,
+      "step": 186
+    },
+    {
+      "epoch": 0.012734990903577926,
+      "grad_norm": 0.8189945816993713,
+      "learning_rate": 2.8213232903489865e-05,
+      "loss": 0.885,
+      "step": 189
+    },
+    {
+      "epoch": 0.01293713361633313,
+      "grad_norm": 0.902603805065155,
+      "learning_rate": 2.761321158169134e-05,
+      "loss": 0.8383,
+      "step": 192
+    },
+    {
+      "epoch": 0.013139276329088337,
+      "grad_norm": 0.8128630518913269,
+      "learning_rate": 2.7011664217918154e-05,
+      "loss": 0.852,
+      "step": 195
+    },
+    {
+      "epoch": 0.013341419041843541,
+      "grad_norm": 0.7031587958335876,
+      "learning_rate": 2.6408942098890936e-05,
+      "loss": 0.8622,
+      "step": 198
+    },
+    {
+      "epoch": 0.013543561754598747,
+      "grad_norm": 0.7614731788635254,
+      "learning_rate": 2.580539719735433e-05,
+      "loss": 0.8162,
+      "step": 201
+    },
+    {
+      "epoch": 0.013745704467353952,
+      "grad_norm": 0.6810929179191589,
+      "learning_rate": 2.5201381966534748e-05,
+      "loss": 0.8271,
+      "step": 204
+    },
+    {
+      "epoch": 0.013745704467353952,
+      "eval_loss": 0.8147265315055847,
+      "eval_runtime": 1782.1355,
+      "eval_samples_per_second": 14.025,
+      "eval_steps_per_second": 1.754,
+      "step": 204
     }
   ],
   "logging_steps": 3,
@@ -466,7 +558,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3906416645373952e+17,
+  "total_flos": 2.8687699974448742e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null