Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a21340e794b45512c9e0796d6b59e7c91e399435994104d9006e79049e2d873
+oid sha256:24b3bad030e4dcdc32910a5169314fcd6132df73894d8dc92ea72a53798fe4f6
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e57157a4746f713241cf05e254ce32fbf18de92d6a3236ee6decbda69426122
+oid sha256:a63481767194808e20d873f2f5248c7285ab651835b7c71da940b6812f1e9140
 size 509176980

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f0a52bb46f51e660abcb041b0b835241189b691ea4109f2665f135f52d27aa2
+oid sha256:b52a51c3b4c01f9b630403ebb6928c43e1ecb011855669002547cf6d66e6c4a9
 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": 0.003277009728622632,
+  "epoch": 0.003686635944700461,
   "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": 6.618,
       "eval_steps_per_second": 0.827,
       "step": 40
+    },
+    {
+      "epoch": 0.0034408602150537634,
+      "grad_norm": 0.05236983299255371,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0026,
+      "step": 42
+    },
+    {
+      "epoch": 0.003686635944700461,
+      "grad_norm": 0.055042464286088943,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3431,
+      "step": 45
+    },
+    {
+      "epoch": 0.003686635944700461,
+      "eval_loss": 0.14288893342018127,
+      "eval_runtime": 3104.0602,
+      "eval_samples_per_second": 6.623,
+      "eval_steps_per_second": 0.828,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.030418891538432e+17,
+  "total_flos": 1.159221252980736e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null