Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9babeed7df8e49dbdecfe9eb0a98e41a5c6e42c882fd790274ee0593b470145
+oid sha256:c158013999a0e7d4ba52ad22e28bf36f549f33c2f05866da198b3f4e70231d01
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41fb66820fa9fab122be6cec6c92425cca2195995b8b7de83046bfdde85be09
+oid sha256:518af2edfed8f5eeaca73f2afa0ee80745cffc281c7562db218e9ea84fd00f10
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d1175ac8d48e809b0c50fbee4d6d763ed8630f1e3a0081e245205549015047
+oid sha256:eb5345a289d4a53f402f15e634a8c996066a0cc15acecb088281e8a0d6bebe14
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99fc9c0ec571f76cf9b6d1229601c5173899cd18104e487c5627f5f4c56c6e8a
+oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02868617326448652,
+  "epoch": 0.05737234652897304,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 13.449,
       "eval_steps_per_second": 6.725,
       "step": 25
+    },
+    {
+      "epoch": 0.02983362019506598,
+      "grad_norm": 0.43531009554862976,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.0243,
+      "step": 26
+    },
+    {
+      "epoch": 0.03098106712564544,
+      "grad_norm": 0.48705872893333435,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0254,
+      "step": 27
+    },
+    {
+      "epoch": 0.0321285140562249,
+      "grad_norm": 0.42778128385543823,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.0228,
+      "step": 28
+    },
+    {
+      "epoch": 0.03327596098680436,
+      "grad_norm": 0.5449861884117126,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.0421,
+      "step": 29
+    },
+    {
+      "epoch": 0.03442340791738382,
+      "grad_norm": 0.3300516903400421,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0217,
+      "step": 30
+    },
+    {
+      "epoch": 0.03557085484796328,
+      "grad_norm": 0.36909106373786926,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0211,
+      "step": 31
+    },
+    {
+      "epoch": 0.03671830177854274,
+      "grad_norm": 0.32208243012428284,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.0221,
+      "step": 32
+    },
+    {
+      "epoch": 0.0378657487091222,
+      "grad_norm": 0.5139682292938232,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0351,
+      "step": 33
+    },
+    {
+      "epoch": 0.03901319563970167,
+      "grad_norm": 0.4424279034137726,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0402,
+      "step": 34
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 0.406888872385025,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.0256,
+      "step": 35
+    },
+    {
+      "epoch": 0.04130808950086059,
+      "grad_norm": 0.3193250298500061,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0306,
+      "step": 36
+    },
+    {
+      "epoch": 0.042455536431440045,
+      "grad_norm": 0.5056396126747131,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0446,
+      "step": 37
+    },
+    {
+      "epoch": 0.04360298336201951,
+      "grad_norm": 0.4755103886127472,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0345,
+      "step": 38
+    },
+    {
+      "epoch": 0.04475043029259897,
+      "grad_norm": 0.41109639406204224,
+      "learning_rate": 5e-05,
+      "loss": 0.0402,
+      "step": 39
+    },
+    {
+      "epoch": 0.04589787722317843,
+      "grad_norm": 0.48927897214889526,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0431,
+      "step": 40
+    },
+    {
+      "epoch": 0.04704532415375789,
+      "grad_norm": 0.4970654249191284,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.0468,
+      "step": 41
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 0.3974848687648773,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0347,
+      "step": 42
+    },
+    {
+      "epoch": 0.04934021801491681,
+      "grad_norm": 0.5659162402153015,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0475,
+      "step": 43
+    },
+    {
+      "epoch": 0.05048766494549627,
+      "grad_norm": 0.4630831778049469,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0555,
+      "step": 44
+    },
+    {
+      "epoch": 0.05163511187607573,
+      "grad_norm": 0.6687282919883728,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0602,
+      "step": 45
+    },
+    {
+      "epoch": 0.052782558806655194,
+      "grad_norm": 0.5463370680809021,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0574,
+      "step": 46
+    },
+    {
+      "epoch": 0.05393000573723465,
+      "grad_norm": 0.6840320825576782,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.074,
+      "step": 47
+    },
+    {
+      "epoch": 0.055077452667814115,
+      "grad_norm": 0.7155039310455322,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0904,
+      "step": 48
+    },
+    {
+      "epoch": 0.05622489959839357,
+      "grad_norm": 2.343247652053833,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.1657,
+      "step": 49
+    },
+    {
+      "epoch": 0.05737234652897304,
+      "grad_norm": 5.246421813964844,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.3323,
+      "step": 50
+    },
+    {
+      "epoch": 0.05737234652897304,
+      "eval_loss": 0.03461047261953354,
+      "eval_runtime": 54.72,
+      "eval_samples_per_second": 13.414,
+      "eval_steps_per_second": 6.707,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5579180435570688.0,
+  "total_flos": 1.0473198361509888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null