Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28995b8e6c2eaa29a86bdadd079fa6a5a8e1e5f9857d6a2a21ea3fa9fa343416
+oid sha256:092b09f233adea6d9b0fed8b771f37bfb8e2131bc5fed5e43bc9571f51f6eeec
 size 239906848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ea4b09d3520616d58cf13712ace22e9e0e14382b0b21de39a6a4936683cd12
+oid sha256:69c52b15e31989412dc21731d73eb1374b8eae7c512eeeb012dd616d672aff72
 size 122200212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fa9dbafe28db2ab616e0d533532c08ed5e3949338846c939ea2d4b0b931791d
+oid sha256:22a3b64d9fdc384450ed7f441ee4d32abde219d0d02739ebfcea0baf60e3c55e
 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": 0.022256224787870357,
+  "epoch": 0.025038252886354154,
   "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": 18.174,
       "eval_steps_per_second": 2.275,
       "step": 40
+    },
+    {
+      "epoch": 0.023369036027263874,
+      "grad_norm": 0.3020647466182709,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0034,
+      "step": 42
+    },
+    {
+      "epoch": 0.025038252886354154,
+      "grad_norm": 0.29544344544410706,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0153,
+      "step": 45
+    },
+    {
+      "epoch": 0.025038252886354154,
+      "eval_loss": 1.043650507926941,
+      "eval_runtime": 166.7168,
+      "eval_samples_per_second": 18.157,
+      "eval_steps_per_second": 2.273,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -189,7 +211,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.493979060862976e+16,
+  "total_flos": 2.805726443470848e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null