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:e85ad51a8f7791129aaf97fb561ce631105d810e38029b60c5e10b3ba81c6da6
+oid sha256:e7091e879d4f5189b4bb1535ec5e68f51ed1a63bd63d8046d25b0cca5d755423
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd5d1b79a35eeded8b6e9f489d2495c066c10b984eb7cb6d30a625c505a0da0
+oid sha256:69a7cf4df3867e14f4373fd685aeb216ef39643cc3ab5010c4260a93e93c8227
 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": 0.2342606149341142,
+  "epoch": 0.2635431918008785,
   "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": 15.568,
       "eval_steps_per_second": 1.946,
       "step": 40
+    },
+    {
+      "epoch": 0.24597364568081992,
+      "grad_norm": 10.164499282836914,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.5064,
+      "step": 42
+    },
+    {
+      "epoch": 0.2635431918008785,
+      "grad_norm": 5.043495178222656,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0295,
+      "step": 45
+    },
+    {
+      "epoch": 0.2635431918008785,
+      "eval_loss": 0.33903414011001587,
+      "eval_runtime": 18.4737,
+      "eval_samples_per_second": 15.59,
+      "eval_steps_per_second": 1.949,
+      "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