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:d06192d758f599c81e887b2a13e19ff974602cb65fdc40c23689ba90f5a0cc51
+oid sha256:4cc759cf13661b4c5b335690bc8b11943275e9a8dd062881721370264ed868f6
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef7a8706f17569c6dea0871a2304a6f7d337bb45555726571afc0a2d7edb4eb
+oid sha256:4638d466f282e677c317e35edb73d3ec79883b19369b6efef3161077916f349e
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59a28cc54d01a2cacfb06a120854babf31065aeadae401292bfd08b1b5f75518
+oid sha256:780a66f050a6446e42e4531bfc89697709babbf1afa47eb4223703c667289080
 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": 0.3564356435643564,
+  "epoch": 0.4752475247524752,
   "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": 88.1,
       "eval_steps_per_second": 11.086,
       "step": 126
+    },
+    {
+      "epoch": 0.3649222065063649,
+      "grad_norm": 0.17696824669837952,
+      "learning_rate": 8.613974319136958e-05,
+      "loss": 11.8171,
+      "step": 129
+    },
+    {
+      "epoch": 0.3734087694483734,
+      "grad_norm": 0.11144156008958817,
+      "learning_rate": 8.54684960502629e-05,
+      "loss": 11.815,
+      "step": 132
+    },
+    {
+      "epoch": 0.38189533239038187,
+      "grad_norm": 0.16119325160980225,
+      "learning_rate": 8.478412753017433e-05,
+      "loss": 11.8134,
+      "step": 135
+    },
+    {
+      "epoch": 0.39038189533239037,
+      "grad_norm": 0.10234789550304413,
+      "learning_rate": 8.408689080954998e-05,
+      "loss": 11.8138,
+      "step": 138
+    },
+    {
+      "epoch": 0.3988684582743989,
+      "grad_norm": 0.12111084908246994,
+      "learning_rate": 8.33770438273574e-05,
+      "loss": 11.8152,
+      "step": 141
+    },
+    {
+      "epoch": 0.4073550212164074,
+      "grad_norm": 0.07516127824783325,
+      "learning_rate": 8.265484918766243e-05,
+      "loss": 11.8128,
+      "step": 144
+    },
+    {
+      "epoch": 0.4158415841584158,
+      "grad_norm": 0.23707596957683563,
+      "learning_rate": 8.192057406248028e-05,
+      "loss": 11.8202,
+      "step": 147
+    },
+    {
+      "epoch": 0.4243281471004243,
+      "grad_norm": 0.1228451356291771,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 11.8201,
+      "step": 150
+    },
+    {
+      "epoch": 0.4328147100424328,
+      "grad_norm": 0.16358840465545654,
+      "learning_rate": 8.041687328877567e-05,
+      "loss": 11.8141,
+      "step": 153
+    },
+    {
+      "epoch": 0.44130127298444133,
+      "grad_norm": 0.10192089527845383,
+      "learning_rate": 7.964800392625129e-05,
+      "loss": 11.8128,
+      "step": 156
+    },
+    {
+      "epoch": 0.4497878359264498,
+      "grad_norm": 0.07679455727338791,
+      "learning_rate": 7.886816644444098e-05,
+      "loss": 11.8124,
+      "step": 159
+    },
+    {
+      "epoch": 0.4582743988684583,
+      "grad_norm": 0.10075189918279648,
+      "learning_rate": 7.807764934001874e-05,
+      "loss": 11.8119,
+      "step": 162
+    },
+    {
+      "epoch": 0.4667609618104668,
+      "grad_norm": 0.1872919499874115,
+      "learning_rate": 7.727674506052743e-05,
+      "loss": 11.8203,
+      "step": 165
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "grad_norm": 0.12166598439216614,
+      "learning_rate": 7.646574989618938e-05,
+      "loss": 11.8202,
+      "step": 168
+    },
+    {
+      "epoch": 0.4752475247524752,
+      "eval_loss": 11.818514823913574,
+      "eval_runtime": 6.4158,
+      "eval_samples_per_second": 92.895,
+      "eval_steps_per_second": 11.69,
+      "step": 168
     }
   ],
   "logging_steps": 3,
@@ -352,7 +458,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 765306470400.0,
+  "total_flos": 1025631191040.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null