Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e762ba4f21d8ac501b65f4e5f30841019f510e0dd47273fe6a9332dc755d18ae
+oid sha256:2464edad70545451ea3b4ca9c1d406b39d4cbc16357f54f4dc2d19842b27ad69
 size 93608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00e47e864cf0bde982771776408c956ef9c7f70b233e450d8cb028509264b7b9
+oid sha256:840eeae8357e4a24d95d263ad555543c909277b1a01536634f05bf0b12c17c48
 size 197158

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bc9d59fade5c32432d168a1733323120abe43da9328cb3b9ed170adf092d2bd
+oid sha256:b8f44828df8830151d896be841876dc9cee379b27bb94793e2085a5033e38e02
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
+oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7191011235955056,
+  "epoch": 0.8089887640449438,
   "eval_steps": 5,
-  "global_step": 40,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -170,6 +170,28 @@
       "eval_samples_per_second": 96.312,
       "eval_steps_per_second": 24.59,
       "step": 40
+    },
+    {
+      "epoch": 0.755056179775281,
+      "grad_norm": 0.3940165936946869,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 11.8986,
+      "step": 42
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 0.35280826687812805,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.899,
+      "step": 45
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "eval_loss": 11.898167610168457,
+      "eval_runtime": 0.9809,
+      "eval_samples_per_second": 95.827,
+      "eval_steps_per_second": 24.466,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 377832407040.0,
+  "total_flos": 425438085120.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null