Training in progress, step 238, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13acbad963ec40074c567d0d1784741f6961767387ad3467d2cb553791d2e54e
+oid sha256:1f9fbcddc5470d728295fa3156e8cc8e85bdb3e075c721f1a6f3de138e6afd3f
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57a427fb02e64b2e9c07be952273516c0846d810883556edaa06d8b17464ff05
+oid sha256:6828c635537ff06d969e1f45a0902d6456cd737e4146dcf425fbba25e04bed82
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb6833ca1600bf131a99c9282df1f52267ed44a81a8c0477f031f940e545f8af
+oid sha256:872fb8e64e364c7f25bf0433e726bc19c70aafc58093b42c433869870b0988fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f9839d107756d9c8815de9164f2ebf92c05b3536704a349ca5892084df7663e
+oid sha256:bbcef9424696e41c7961bd91f0570d39d59ef33af28ed19a0eb9e4f50ed1b09a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013745704467353952,
+  "epoch": 0.016036655211912942,
   "eval_steps": 34,
-  "global_step": 204,
+  "global_step": 238,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -539,6 +539,91 @@
       "eval_samples_per_second": 14.025,
       "eval_steps_per_second": 1.754,
       "step": 204
+    },
+    {
+      "epoch": 0.013947847180109158,
+      "grad_norm": 0.7248020768165588,
+      "learning_rate": 2.459724913431772e-05,
+      "loss": 0.814,
+      "step": 207
+    },
+    {
+      "epoch": 0.014149989892864362,
+      "grad_norm": 0.7375376224517822,
+      "learning_rate": 2.399335149726463e-05,
+      "loss": 0.8381,
+      "step": 210
+    },
+    {
+      "epoch": 0.014352132605619567,
+      "grad_norm": 0.75850510597229,
+      "learning_rate": 2.3390041714589514e-05,
+      "loss": 0.7851,
+      "step": 213
+    },
+    {
+      "epoch": 0.014554275318374773,
+      "grad_norm": 0.711068332195282,
+      "learning_rate": 2.2787672102216042e-05,
+      "loss": 0.7992,
+      "step": 216
+    },
+    {
+      "epoch": 0.014756418031129977,
+      "grad_norm": 0.7301695346832275,
+      "learning_rate": 2.2186594427034864e-05,
+      "loss": 0.8506,
+      "step": 219
+    },
+    {
+      "epoch": 0.014958560743885184,
+      "grad_norm": 0.720683753490448,
+      "learning_rate": 2.1587159701481716e-05,
+      "loss": 0.8061,
+      "step": 222
+    },
+    {
+      "epoch": 0.015160703456640388,
+      "grad_norm": 0.665138304233551,
+      "learning_rate": 2.098971797855599e-05,
+      "loss": 0.7454,
+      "step": 225
+    },
+    {
+      "epoch": 0.015362846169395592,
+      "grad_norm": 0.6854159235954285,
+      "learning_rate": 2.0394618147399713e-05,
+      "loss": 0.828,
+      "step": 228
+    },
+    {
+      "epoch": 0.015564988882150799,
+      "grad_norm": 0.7191194891929626,
+      "learning_rate": 1.980220772955602e-05,
+      "loss": 0.7885,
+      "step": 231
+    },
+    {
+      "epoch": 0.015767131594906003,
+      "grad_norm": 0.7301977276802063,
+      "learning_rate": 1.921283267602643e-05,
+      "loss": 0.81,
+      "step": 234
+    },
+    {
+      "epoch": 0.015969274307661208,
+      "grad_norm": 0.7239346504211426,
+      "learning_rate": 1.8626837165245165e-05,
+      "loss": 0.787,
+      "step": 237
+    },
+    {
+      "epoch": 0.016036655211912942,
+      "eval_loss": 0.8127490878105164,
+      "eval_runtime": 1781.9808,
+      "eval_samples_per_second": 14.027,
+      "eval_steps_per_second": 1.754,
+      "step": 238
     }
   ],
   "logging_steps": 3,
@@ -558,7 +643,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8687699974448742e+17,
+  "total_flos": 3.346898330352353e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null