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:deef8309f7775dfae22cd187b5a740c4952a019695ef3a0705bd8f6f20bf2d21
+oid sha256:adf4d81665c463139b62940be68da8a0149ed478eee21eb621ffc41a12bf39c9
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfd21b7ba44e39b389af26651f74cdf3733e798a1199dbe053135232ec20429a
+oid sha256:2ed2d1e3a6f1e5bf167533312c46c6163dfd85392d23f6fd02194800059054ae
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408a06755b519bb846de2707ae71844004b4b1bde9426470048a53e0c32a92b3
+oid sha256:71b07cdafd3b5e2145088a8972b9442b008f1502e71d5096045be99cb1c123be
 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": 0.28622540250447226,
+  "epoch": 0.3220035778175313,
   "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": 11.062,
       "eval_steps_per_second": 1.406,
       "step": 40
+    },
+    {
+      "epoch": 0.3005366726296959,
+      "grad_norm": 13.742753982543945,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.3929,
+      "step": 42
+    },
+    {
+      "epoch": 0.3220035778175313,
+      "grad_norm": 3.5590667724609375,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0585,
+      "step": 45
+    },
+    {
+      "epoch": 0.3220035778175313,
+      "eval_loss": 0.015118077397346497,
+      "eval_runtime": 21.333,
+      "eval_samples_per_second": 11.063,
+      "eval_steps_per_second": 1.406,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.322034636652544e+16,
+  "total_flos": 5.987288966234112e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null