Training in progress, step 233, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:473f4b3ff0b219aa3d4708c39fab335413427789124d1cc01e586e727315cff4
+oid sha256:afd25c170355ea632cfa5da978f90f702ff16dbc4d51afcebf4989ad9d0f333b
 size 100198584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ec22a1dfeb40ec71635f49ced12c4198b8107b4b216dad54278bd643cdb721c
+oid sha256:73e0747b869366afbdebd37788920b02982df01eccc71e682aec61e6a7645b33
 size 50675156

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7650503afdff505462325f6f430e903bb44a778f9119236884da4fcf462c9e5
+oid sha256:d1c9368a0cddac000b7996e7cc550ed94e1405683912f0e0601527c458e30db8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.306821294858917,
+  "epoch": 0.3404255319148936,
   "eval_steps": 500,
-  "global_step": 210,
+  "global_step": 233,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1477,6 +1477,167 @@
       "learning_rate": 1.623287671232877e-05,
       "loss": 1.2169,
       "step": 210
+    },
+    {
+      "epoch": 0.3082823486439595,
+      "grad_norm": 0.11075271666049957,
+      "learning_rate": 1.61986301369863e-05,
+      "loss": 1.2867,
+      "step": 211
+    },
+    {
+      "epoch": 0.3097434024290019,
+      "grad_norm": 0.10098811239004135,
+      "learning_rate": 1.6164383561643838e-05,
+      "loss": 1.2625,
+      "step": 212
+    },
+    {
+      "epoch": 0.31120445621404436,
+      "grad_norm": 0.10328993201255798,
+      "learning_rate": 1.613013698630137e-05,
+      "loss": 1.2121,
+      "step": 213
+    },
+    {
+      "epoch": 0.3126655099990868,
+      "grad_norm": 0.11792083084583282,
+      "learning_rate": 1.6095890410958904e-05,
+      "loss": 1.2316,
+      "step": 214
+    },
+    {
+      "epoch": 0.3141265637841293,
+      "grad_norm": 0.1143653616309166,
+      "learning_rate": 1.606164383561644e-05,
+      "loss": 1.2084,
+      "step": 215
+    },
+    {
+      "epoch": 0.31558761756917175,
+      "grad_norm": 0.10241192579269409,
+      "learning_rate": 1.6027397260273974e-05,
+      "loss": 1.2924,
+      "step": 216
+    },
+    {
+      "epoch": 0.3170486713542142,
+      "grad_norm": 0.09764024615287781,
+      "learning_rate": 1.599315068493151e-05,
+      "loss": 1.2387,
+      "step": 217
+    },
+    {
+      "epoch": 0.3185097251392567,
+      "grad_norm": 0.0964062437415123,
+      "learning_rate": 1.5958904109589043e-05,
+      "loss": 1.2143,
+      "step": 218
+    },
+    {
+      "epoch": 0.31997077892429915,
+      "grad_norm": 0.10618474334478378,
+      "learning_rate": 1.5924657534246576e-05,
+      "loss": 1.1912,
+      "step": 219
+    },
+    {
+      "epoch": 0.3214318327093416,
+      "grad_norm": 0.10085848718881607,
+      "learning_rate": 1.589041095890411e-05,
+      "loss": 1.1691,
+      "step": 220
+    },
+    {
+      "epoch": 0.3228928864943841,
+      "grad_norm": 0.10805616527795792,
+      "learning_rate": 1.5856164383561646e-05,
+      "loss": 1.2028,
+      "step": 221
+    },
+    {
+      "epoch": 0.32435394027942654,
+      "grad_norm": 0.10075750201940536,
+      "learning_rate": 1.5821917808219182e-05,
+      "loss": 1.2286,
+      "step": 222
+    },
+    {
+      "epoch": 0.325814994064469,
+      "grad_norm": 0.09440125524997711,
+      "learning_rate": 1.5787671232876715e-05,
+      "loss": 1.24,
+      "step": 223
+    },
+    {
+      "epoch": 0.3272760478495115,
+      "grad_norm": 0.09914068877696991,
+      "learning_rate": 1.5753424657534248e-05,
+      "loss": 1.2225,
+      "step": 224
+    },
+    {
+      "epoch": 0.32873710163455394,
+      "grad_norm": 0.10779386013746262,
+      "learning_rate": 1.571917808219178e-05,
+      "loss": 1.1821,
+      "step": 225
+    },
+    {
+      "epoch": 0.3301981554195964,
+      "grad_norm": 0.09676062315702438,
+      "learning_rate": 1.5684931506849318e-05,
+      "loss": 1.2975,
+      "step": 226
+    },
+    {
+      "epoch": 0.33165920920463887,
+      "grad_norm": 0.09622418135404587,
+      "learning_rate": 1.565068493150685e-05,
+      "loss": 1.2935,
+      "step": 227
+    },
+    {
+      "epoch": 0.3331202629896813,
+      "grad_norm": 0.10332711786031723,
+      "learning_rate": 1.5616438356164384e-05,
+      "loss": 1.2178,
+      "step": 228
+    },
+    {
+      "epoch": 0.33458131677472375,
+      "grad_norm": 0.10794605314731598,
+      "learning_rate": 1.5582191780821917e-05,
+      "loss": 1.1103,
+      "step": 229
+    },
+    {
+      "epoch": 0.3360423705597662,
+      "grad_norm": 0.10352062433958054,
+      "learning_rate": 1.5547945205479453e-05,
+      "loss": 1.2187,
+      "step": 230
+    },
+    {
+      "epoch": 0.3375034243448087,
+      "grad_norm": 0.10264533013105392,
+      "learning_rate": 1.551369863013699e-05,
+      "loss": 1.3449,
+      "step": 231
+    },
+    {
+      "epoch": 0.33896447812985114,
+      "grad_norm": 0.10094834864139557,
+      "learning_rate": 1.5479452054794523e-05,
+      "loss": 1.2042,
+      "step": 232
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.09931448101997375,
+      "learning_rate": 1.5445205479452056e-05,
+      "loss": 1.1876,
+      "step": 233
     }
   ],
   "logging_steps": 1,
@@ -1496,7 +1657,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3556959221775155e+17,
+  "total_flos": 2.619657311583191e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null