Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0d2d46cbdc4b9220d6a849a4a7e2897d04a26f4ceb3fc6d36cfb3722da27ed
+oid sha256:687f4bca35f0d9df993f6d5b62109940fe0e84817db534ae8363cc0735fba861
 size 338298

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb587af29e9bd567091c9edc1922888b73d8ca2d4cc143c1d03589f6356311c
+oid sha256:16377976c107a6c66a499279562140fcb8371bea43a081943d633f33b2e65a86
 size 418030

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f7d8e9abeff9f0f2aa7d16e8494b24e0a7eaac3cc565c4ef78e32d32a521d4a
+oid sha256:ba868925edaf5516534779d862378ff0c5b1a6e19d0ed88b5d7747286b450e1c
 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": 1.4678899082568808,
+  "epoch": 1.6513761467889907,
   "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": 772.357,
       "eval_steps_per_second": 100.742,
       "step": 40
+    },
+    {
+      "epoch": 1.5412844036697249,
+      "grad_norm": 0.3164646625518799,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 6.8576,
+      "step": 42
+    },
+    {
+      "epoch": 1.6513761467889907,
+      "grad_norm": 0.3245089054107666,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 6.8992,
+      "step": 45
+    },
+    {
+      "epoch": 1.6513761467889907,
+      "eval_loss": 6.84040641784668,
+      "eval_runtime": 0.0629,
+      "eval_samples_per_second": 731.69,
+      "eval_steps_per_second": 95.438,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 904061061120.0,
+  "total_flos": 1009785145344.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null