Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97fc86cc0bd2632c4869f12c663ce373edc7b1ce4b4b3a184cd0fd3bfc81dbb4
+oid sha256:f6ba54415592535b5deb4d426438a9c2d3fda44dd59cc053b65b3d50072d6931
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ff5d443fddb5fb6fa25d441fee784e8e33020e086f39257a766017ebc08ddc
+oid sha256:3a7a35b2bab9539cc55cf97a00eb49ce0480bebbd5aae9cb3bdfdaee31e4b1fa
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7309e56b1f2626dc32ea9dd6f24616aa7f30e53f0b70fee6bf07a99e087242c9
+oid sha256:66b738e61e29b3536eb6d5c0f3f4d525d915958f2cf65da2df3e0128bb584b89
 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": 0.07328691828508611,
+  "epoch": 0.14657383657017223,
   "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": 13.787,
       "eval_steps_per_second": 6.893,
       "step": 25
+    },
+    {
+      "epoch": 0.07621839501648955,
+      "grad_norm": 0.8068152666091919,
+      "learning_rate": 7.68649804173412e-05,
+      "loss": 0.1082,
+      "step": 26
+    },
+    {
+      "epoch": 0.079149871747893,
+      "grad_norm": 0.3823889493942261,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.0364,
+      "step": 27
+    },
+    {
+      "epoch": 0.08208134847929645,
+      "grad_norm": 0.9048523306846619,
+      "learning_rate": 7.308743066175172e-05,
+      "loss": 0.1366,
+      "step": 28
+    },
+    {
+      "epoch": 0.08501282521069989,
+      "grad_norm": 0.8256965279579163,
+      "learning_rate": 7.113091308703498e-05,
+      "loss": 0.107,
+      "step": 29
+    },
+    {
+      "epoch": 0.08794430194210333,
+      "grad_norm": 0.5980184078216553,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.0635,
+      "step": 30
+    },
+    {
+      "epoch": 0.09087577867350678,
+      "grad_norm": 0.5219781398773193,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 0.0253,
+      "step": 31
+    },
+    {
+      "epoch": 0.09380725540491022,
+      "grad_norm": 0.6775377988815308,
+      "learning_rate": 6.503528997521366e-05,
+      "loss": 0.1005,
+      "step": 32
+    },
+    {
+      "epoch": 0.09673873213631366,
+      "grad_norm": 0.5344719886779785,
+      "learning_rate": 6.294095225512603e-05,
+      "loss": 0.0726,
+      "step": 33
+    },
+    {
+      "epoch": 0.09967020886771712,
+      "grad_norm": 0.684424877166748,
+      "learning_rate": 6.0821980696905146e-05,
+      "loss": 0.0762,
+      "step": 34
+    },
+    {
+      "epoch": 0.10260168559912056,
+      "grad_norm": 0.47931015491485596,
+      "learning_rate": 5.868240888334653e-05,
+      "loss": 0.053,
+      "step": 35
+    },
+    {
+      "epoch": 0.105533162330524,
+      "grad_norm": 0.48746219277381897,
+      "learning_rate": 5.6526309611002594e-05,
+      "loss": 0.0769,
+      "step": 36
+    },
+    {
+      "epoch": 0.10846463906192745,
+      "grad_norm": 0.41026896238327026,
+      "learning_rate": 5.435778713738292e-05,
+      "loss": 0.0623,
+      "step": 37
+    },
+    {
+      "epoch": 0.11139611579333089,
+      "grad_norm": 0.6301044821739197,
+      "learning_rate": 5.218096936826681e-05,
+      "loss": 0.0854,
+      "step": 38
+    },
+    {
+      "epoch": 0.11432759252473433,
+      "grad_norm": 0.43072110414505005,
+      "learning_rate": 5e-05,
+      "loss": 0.0488,
+      "step": 39
+    },
+    {
+      "epoch": 0.11725906925613779,
+      "grad_norm": 0.49057018756866455,
+      "learning_rate": 4.781903063173321e-05,
+      "loss": 0.0468,
+      "step": 40
+    },
+    {
+      "epoch": 0.12019054598754123,
+      "grad_norm": 0.541214108467102,
+      "learning_rate": 4.564221286261709e-05,
+      "loss": 0.1181,
+      "step": 41
+    },
+    {
+      "epoch": 0.12312202271894467,
+      "grad_norm": 0.4960033893585205,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0367,
+      "step": 42
+    },
+    {
+      "epoch": 0.1260534994503481,
+      "grad_norm": 0.46519333124160767,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.0634,
+      "step": 43
+    },
+    {
+      "epoch": 0.12898497618175156,
+      "grad_norm": 0.5953696966171265,
+      "learning_rate": 3.917801930309486e-05,
+      "loss": 0.0357,
+      "step": 44
+    },
+    {
+      "epoch": 0.131916452913155,
+      "grad_norm": 0.4260966181755066,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0504,
+      "step": 45
+    },
+    {
+      "epoch": 0.13484792964455844,
+      "grad_norm": 0.35495659708976746,
+      "learning_rate": 3.4964710024786354e-05,
+      "loss": 0.0461,
+      "step": 46
+    },
+    {
+      "epoch": 0.1377794063759619,
+      "grad_norm": 0.492147296667099,
+      "learning_rate": 3.289899283371657e-05,
+      "loss": 0.0833,
+      "step": 47
+    },
+    {
+      "epoch": 0.14071088310736535,
+      "grad_norm": 0.47650235891342163,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0771,
+      "step": 48
+    },
+    {
+      "epoch": 0.14364235983876877,
+      "grad_norm": 0.8814830780029297,
+      "learning_rate": 2.886908691296504e-05,
+      "loss": 0.1376,
+      "step": 49
+    },
+    {
+      "epoch": 0.14657383657017223,
+      "grad_norm": 0.7530894875526428,
+      "learning_rate": 2.6912569338248315e-05,
+      "loss": 0.0946,
+      "step": 50
+    },
+    {
+      "epoch": 0.14657383657017223,
+      "eval_loss": 0.06695578992366791,
+      "eval_runtime": 20.9098,
+      "eval_samples_per_second": 13.773,
+      "eval_steps_per_second": 6.887,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -217,7 +400,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5365118024024064.0,
+  "total_flos": 1.0573970474532864e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null