Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc34d20f3ae89b41e519670ff3d2bd32701a5cb52ecbca627e240c056791307c
+oid sha256:54704e75e186295848b5ffeaee39f49f8360084c27cb5e2326310f5b85e8ab4c
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229abbd6d7e0b56184eba73701e0bc99a5564568aa9288de9efac99d4ccea504
+oid sha256:a290f8f24c33504874145f5b8f99bdd752ba22de05bf1ad8a4192b1d458c1804
 size 111142

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234ac728586f036a39f9f4804abaee8b944bd797ebadc60e7a93d7766d8cd54c
+oid sha256:cc2d4deabe8b7c7717f723f27c97b00e45c34e9312e4247b5ff09fbccbefbde4
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd3accccfd3b9734ccbf6755dad7f2ebf98df44282c87e04d3861251b80f3ea7
+oid sha256:18ea355a406408a61da03a07c153dcb802215d8a6d59cd936d916621115787e8
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfc869a7dff5e0685198915e801aa83c611704cec20b5c87ed3be65c80fb1390
+oid sha256:1a45ee1f874820d041513433d0211cbea1d98acaa5be4e13067438e3596b3da5
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cebb7780be2cb875de63977938b32f6277640431270beff7b5b6f29f321dff2
+oid sha256:1e5c0a21cbfe1aef9846a3bf19c31cc8c2ead43bd7d7711804dd072612f144ea
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cc614e18d28f43848b8c3c5d96e4cde50f9290acc197be6c202ee899b5aa3d
+oid sha256:8c71537086ab561ad76a11b267345c90f7b0ef1f39b21a66cc2acc83c668b0ed
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09f0f7e57c0b76d83ea8d8ebc0629e76ac24dd1e35ef7e7e00e39d9d8e09a98
+oid sha256:04bf5b3dd7ebc249c08b7d644ffde954f4f4038578564beaf567643f194198a5
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cba3c0b19620b980cb6cc9dfe04f656785982cc6092c1177384bd803074cd44
+oid sha256:a7fd45a007165b2bf758e0c7ebca3f6e73c2b03fa49115fa874f92fc38428018
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b93350a056d1f3d53846902376e9aabd7d93a8bfeedc0a59b7e301162605cd3
+oid sha256:65c92b3e511dd1adc5dfe5f1cff31aab675f96214af710d971afe11949c5991b
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.26519337016574585,
+  "epoch": 0.5303867403314917,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 689.891,
       "eval_steps_per_second": 90.775,
       "step": 3
+    },
+    {
+      "epoch": 0.35359116022099446,
+      "grad_norm": 0.21081098914146423,
+      "learning_rate": 4e-05,
+      "loss": 11.76,
+      "step": 4
+    },
+    {
+      "epoch": 0.4419889502762431,
+      "grad_norm": 0.21257060766220093,
+      "learning_rate": 5e-05,
+      "loss": 11.7497,
+      "step": 5
+    },
+    {
+      "epoch": 0.5303867403314917,
+      "grad_norm": 0.213060200214386,
+      "learning_rate": 6e-05,
+      "loss": 11.7588,
+      "step": 6
+    },
+    {
+      "epoch": 0.5303867403314917,
+      "eval_loss": 11.777400970458984,
+      "eval_runtime": 0.1098,
+      "eval_samples_per_second": 691.988,
+      "eval_steps_per_second": 91.051,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 19555204202496.0,
+  "total_flos": 39110408404992.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null