Training in progress, step 32, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f905c1cff345416341d46b46f91271dbe323fa59c6c4da2192495f4403e5c0f
+oid sha256:30ded4bce8f3aeb46976eaf0b5329b44ad473a2a4305ab8d2f19270798882d91
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e931c2a97cd0f7da55dc51d4070cd4be734a7fd9a9dd370fc0288b463769e2e
+oid sha256:a65835a5d88bd1313380b80afe6d10fa69949be4f94bd0e3624d1a7b2e009716
 size 60837186

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489aec5b0e96507c051eebbfc7b3dbb164d74248f9e9c5f2325ef812ff316a23
+oid sha256:e3d62c754a4618e6e2045bed18fcd110ce3e033eadacd83db11e3e65d6fdb46b
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6141f065eba1ae0b8d7809735d4d4fbb7fbfda9eb5f9c7b1690edd5a6c2c5b
+oid sha256:ed4d68a8cd0d7c336eae5ec9326f4344f8484e56ac5abb9db3c35753732b9e85
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7f7b5cf9c6458b2c233922c4300feef134fea79461a679e60cba05607af01c
+oid sha256:814cb1a0cec135cba6a03f6f7a188e85ada15f60bf1b79a649c42e89652b64a2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25296442687747034,
+  "epoch": 0.5059288537549407,
   "eval_steps": 16,
-  "global_step": 16,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -135,6 +135,126 @@
       "eval_samples_per_second": 13.305,
       "eval_steps_per_second": 3.357,
       "step": 16
+    },
+    {
+      "epoch": 0.26877470355731226,
+      "grad_norm": 0.4768655002117157,
+      "learning_rate": 3.4000000000000007e-05,
+      "loss": 0.2191,
+      "step": 17
+    },
+    {
+      "epoch": 0.2845849802371542,
+      "grad_norm": 0.9923710823059082,
+      "learning_rate": 3.6e-05,
+      "loss": 0.384,
+      "step": 18
+    },
+    {
+      "epoch": 0.30039525691699603,
+      "grad_norm": 0.5063422322273254,
+      "learning_rate": 3.8e-05,
+      "loss": 0.1493,
+      "step": 19
+    },
+    {
+      "epoch": 0.31620553359683795,
+      "grad_norm": 0.5010712742805481,
+      "learning_rate": 4e-05,
+      "loss": 0.0675,
+      "step": 20
+    },
+    {
+      "epoch": 0.33201581027667987,
+      "grad_norm": 0.48852574825286865,
+      "learning_rate": 4.2e-05,
+      "loss": 0.0739,
+      "step": 21
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.4387320578098297,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 0.0751,
+      "step": 22
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.3455885648727417,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 0.0516,
+      "step": 23
+    },
+    {
+      "epoch": 0.3794466403162055,
+      "grad_norm": 0.29778942465782166,
+      "learning_rate": 4.8e-05,
+      "loss": 0.0421,
+      "step": 24
+    },
+    {
+      "epoch": 0.3952569169960474,
+      "grad_norm": 0.3956562578678131,
+      "learning_rate": 5e-05,
+      "loss": 0.057,
+      "step": 25
+    },
+    {
+      "epoch": 0.41106719367588934,
+      "grad_norm": 0.8842503428459167,
+      "learning_rate": 5.2000000000000004e-05,
+      "loss": 0.1188,
+      "step": 26
+    },
+    {
+      "epoch": 0.4268774703557312,
+      "grad_norm": 0.9197725653648376,
+      "learning_rate": 5.4000000000000005e-05,
+      "loss": 0.1128,
+      "step": 27
+    },
+    {
+      "epoch": 0.4426877470355731,
+      "grad_norm": 0.9175456762313843,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 0.0628,
+      "step": 28
+    },
+    {
+      "epoch": 0.45849802371541504,
+      "grad_norm": 0.5987579822540283,
+      "learning_rate": 5.8e-05,
+      "loss": 0.0499,
+      "step": 29
+    },
+    {
+      "epoch": 0.4743083003952569,
+      "grad_norm": 0.8026472330093384,
+      "learning_rate": 6e-05,
+      "loss": 0.0619,
+      "step": 30
+    },
+    {
+      "epoch": 0.4901185770750988,
+      "grad_norm": 0.5789671540260315,
+      "learning_rate": 6.2e-05,
+      "loss": 0.0394,
+      "step": 31
+    },
+    {
+      "epoch": 0.5059288537549407,
+      "grad_norm": 0.7335872054100037,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.2007,
+      "step": 32
+    },
+    {
+      "epoch": 0.5059288537549407,
+      "eval_loss": 0.050875596702098846,
+      "eval_runtime": 8.2485,
+      "eval_samples_per_second": 12.972,
+      "eval_steps_per_second": 3.273,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -154,7 +274,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2383975687389184.0,
+  "total_flos": 4791247562604544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null