Training in progress, step 9, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54704e75e186295848b5ffeaee39f49f8360084c27cb5e2326310f5b85e8ab4c
+oid sha256:c4f4c933cf70843c2602f40951e20266951c410fb8006e421ecf31ffec707c8f
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a290f8f24c33504874145f5b8f99bdd752ba22de05bf1ad8a4192b1d458c1804
+oid sha256:d4cb7ebce57bd11fca7520178266303ad5bc9150fd9a8c8ed0d60ec0b2224ee1
 size 111142

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2d4deabe8b7c7717f723f27c97b00e45c34e9312e4247b5ff09fbccbefbde4
+oid sha256:be8c7012d2315e9c325977cca320dc960d5e33864f79e79beb75ccda0bf536dd
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18ea355a406408a61da03a07c153dcb802215d8a6d59cd936d916621115787e8
+oid sha256:bbec86e3a68ec7635cef0df8e46613c1b102bfbbab6cbdf84634e5bcb9522113
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a45ee1f874820d041513433d0211cbea1d98acaa5be4e13067438e3596b3da5
+oid sha256:0cf15be6cbce8ddbc38b41dfb82f1b58e00f664697c263d5d0929f2dcd8f1462
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e5c0a21cbfe1aef9846a3bf19c31cc8c2ead43bd7d7711804dd072612f144ea
+oid sha256:795da922131b91fd13d24624df668203e22af6a44d5906e041405d7184e0cf30
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c71537086ab561ad76a11b267345c90f7b0ef1f39b21a66cc2acc83c668b0ed
+oid sha256:02637d0093b2828e98bb30d53efc5c0bc09bb9e506ca57ef491659dfa91cef7a
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04bf5b3dd7ebc249c08b7d644ffde954f4f4038578564beaf567643f194198a5
+oid sha256:a03b6181079382202edb3d585c4442a2bc2ad117f9c078ab35cec1cb4c4f0067
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7fd45a007165b2bf758e0c7ebca3f6e73c2b03fa49115fa874f92fc38428018
+oid sha256:2b5ac0c8e9d1e0146036a49d1c6ab4d9f015cbae51892d4cf812e9b636a69078
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c92b3e511dd1adc5dfe5f1cff31aab675f96214af710d971afe11949c5991b
+oid sha256:627a9c1d344afe11ab1c13ab2e46abfd20bf98c9c30ca638d7a1c07f5cdbfb9c
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5303867403314917,
+  "epoch": 0.7955801104972375,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 691.988,
       "eval_steps_per_second": 91.051,
       "step": 6
+    },
+    {
+      "epoch": 0.6187845303867403,
+      "grad_norm": 0.18384572863578796,
+      "learning_rate": 7e-05,
+      "loss": 11.7538,
+      "step": 7
+    },
+    {
+      "epoch": 0.7071823204419889,
+      "grad_norm": 0.2052992433309555,
+      "learning_rate": 8e-05,
+      "loss": 11.7604,
+      "step": 8
+    },
+    {
+      "epoch": 0.7955801104972375,
+      "grad_norm": 0.1799938976764679,
+      "learning_rate": 9e-05,
+      "loss": 11.7505,
+      "step": 9
+    },
+    {
+      "epoch": 0.7955801104972375,
+      "eval_loss": 11.764886856079102,
+      "eval_runtime": 0.11,
+      "eval_samples_per_second": 690.859,
+      "eval_steps_per_second": 90.902,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 39110408404992.0,
+  "total_flos": 58665612607488.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null