Training in progress, step 168, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0020ebc06166cd6fbb21fea648ebd8e089cf08d59f8a369d5ccc62994306af35
+oid sha256:5e056a6c824bd2b82bcfb4b22fd4c452b5e6e252f473644e6707d9e7aa905426
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f1b4d8adfadaaf59c2e6e469ab5468b025cbbff070f473a59804411605a3047
+oid sha256:382ca0bf57a11f5a5578b3cf7085b8d51e0355e4bc3b3550cdc1bd3403ebd59c
 size 197158

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5504ef09e4cfb51812fd7a9abcfb2f28e7b4cf5622051aa506c80b1903c2ce18
+oid sha256:bfcaaae51171e7f2154bf7987e0cee9b37d43cdaad7e0a601e845794e2d16a7a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6628ebff94c3a6b8fdb16ed899453e0564fb950e7ae1d3e33c819c9bdd72e3c4
+oid sha256:980f3048c9e624e61f36d02f7920ce9a18fb66e5656e6f4264f835f0c860998f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4477dcc6fa149a821c6a1471f47125572228d5c13a485cbcd42df776c95bcb70
+oid sha256:18364ede1da3fcfa616bf4b04a3b725bd669a65c375cfdd782448d68f791d203
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b25e19ffd8a56430878e7874bc350fc05f2b592464eeaef1dac5822dbb0979
+oid sha256:184c568fce2131695bfc392333c69a45c01f3b8659492da73b71968597bb3421
 size 15024

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": 0.32919660352710645,
+  "epoch": 0.4389288047028086,
   "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": 775.442,
       "eval_steps_per_second": 24.364,
       "step": 126
+    },
+    {
+      "epoch": 0.3370346178967995,
+      "grad_norm": 0.015373232774436474,
+      "learning_rate": 8.613974319136958e-05,
+      "loss": 11.9189,
+      "step": 129
+    },
+    {
+      "epoch": 0.3448726322664925,
+      "grad_norm": 0.018870707601308823,
+      "learning_rate": 8.54684960502629e-05,
+      "loss": 11.9199,
+      "step": 132
+    },
+    {
+      "epoch": 0.3527106466361855,
+      "grad_norm": 0.019645841792225838,
+      "learning_rate": 8.478412753017433e-05,
+      "loss": 11.9192,
+      "step": 135
+    },
+    {
+      "epoch": 0.3605486610058785,
+      "grad_norm": 0.012606288306415081,
+      "learning_rate": 8.408689080954998e-05,
+      "loss": 11.9192,
+      "step": 138
+    },
+    {
+      "epoch": 0.3683866753755715,
+      "grad_norm": 0.02213534526526928,
+      "learning_rate": 8.33770438273574e-05,
+      "loss": 11.9192,
+      "step": 141
+    },
+    {
+      "epoch": 0.3762246897452645,
+      "grad_norm": 0.025056803598999977,
+      "learning_rate": 8.265484918766243e-05,
+      "loss": 11.9194,
+      "step": 144
+    },
+    {
+      "epoch": 0.3840627041149575,
+      "grad_norm": 0.017324019223451614,
+      "learning_rate": 8.192057406248028e-05,
+      "loss": 11.919,
+      "step": 147
+    },
+    {
+      "epoch": 0.3919007184846506,
+      "grad_norm": 0.016662944108247757,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 11.9196,
+      "step": 150
+    },
+    {
+      "epoch": 0.3997387328543436,
+      "grad_norm": 0.01738261617720127,
+      "learning_rate": 8.041687328877567e-05,
+      "loss": 11.9183,
+      "step": 153
+    },
+    {
+      "epoch": 0.4075767472240366,
+      "grad_norm": 0.014731982722878456,
+      "learning_rate": 7.964800392625129e-05,
+      "loss": 11.9195,
+      "step": 156
+    },
+    {
+      "epoch": 0.4154147615937296,
+      "grad_norm": 0.019330400973558426,
+      "learning_rate": 7.886816644444098e-05,
+      "loss": 11.9189,
+      "step": 159
+    },
+    {
+      "epoch": 0.4232527759634226,
+      "grad_norm": 0.01512803602963686,
+      "learning_rate": 7.807764934001874e-05,
+      "loss": 11.9189,
+      "step": 162
+    },
+    {
+      "epoch": 0.4310907903331156,
+      "grad_norm": 0.017275972291827202,
+      "learning_rate": 7.727674506052743e-05,
+      "loss": 11.9183,
+      "step": 165
+    },
+    {
+      "epoch": 0.4389288047028086,
+      "grad_norm": 0.016290944069623947,
+      "learning_rate": 7.646574989618938e-05,
+      "loss": 11.919,
+      "step": 168
+    },
+    {
+      "epoch": 0.4389288047028086,
+      "eval_loss": 11.918442726135254,
+      "eval_runtime": 3.3195,
+      "eval_samples_per_second": 776.625,
+      "eval_steps_per_second": 24.401,
+      "step": 168
     }
   ],
   "logging_steps": 3,
@@ -352,7 +458,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2430902599680.0,
+  "total_flos": 3240801730560.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null