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:bfb8dfc4674949b6332d4118c674bae37025476acba7ef73c72801bc9613b95d
+oid sha256:e558c584b1ab69f81f18d064d18a1350b80e85cd5c8df719812a5c4778283a61
 size 402688040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2786d73fc7a01d27c8f883351c93274064d7f8b83d74e2ed95290ef8300c5e1d
+oid sha256:b14303ba15a33151cfb02c99ed03db5aae81b8b8b30bd91c12001b9beeada540
 size 204773716

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0d7bfb9e1905012663e4954280d50ba1cfda12f6dada658e3ee115125d30c95
+oid sha256:3dac5e06e2dfa31136d8bb374837c95dbb4ca404c2fc8aa0a6c8502696ee35d3
 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": 0.10197578075207138,
+  "epoch": 0.1147227533460803,
   "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": 14.487,
       "eval_steps_per_second": 1.819,
       "step": 40
+    },
+    {
+      "epoch": 0.10707456978967496,
+      "grad_norm": 7.441665172576904,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.8598,
+      "step": 42
+    },
+    {
+      "epoch": 0.1147227533460803,
+      "grad_norm": 8.042488098144531,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.4286,
+      "step": 45
+    },
+    {
+      "epoch": 0.1147227533460803,
+      "eval_loss": 1.1251012086868286,
+      "eval_runtime": 45.6063,
+      "eval_samples_per_second": 14.494,
+      "eval_steps_per_second": 1.82,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.025512041545728e+16,
+  "total_flos": 3.401352046706688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null