Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336fa09b07144084bf0b85cc9992216745b93e4fff84d6ff92594ae5648125ce
+oid sha256:bd55083b4091559ebf65192c407ebceaf4d21bf739682d6114ccc3dbf70a00a3
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2f46bb2321fe42ff8423ef5392039f5c6eecc1bae74ba0e7e2ce0f9f41bc014
+oid sha256:271672373ed49cdd7feb8ecbcc127f67a549a72a4528028c2ad80ee8ed1352d0
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ad7439565a5462d968f8d3364199f027aa6f68d9890049e5a20a8e24781131
+oid sha256:cea0571e03c42072c2619a6841806791c3454e943bf747e8a4e1158abf717848
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
+oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004329694185280844,
+  "epoch": 0.005195633022337012,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 3.051,
       "eval_steps_per_second": 1.526,
       "step": 45
+    },
+    {
+      "epoch": 0.004618340464299567,
+      "grad_norm": 21.155969619750977,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 8.103,
+      "step": 48
+    },
+    {
+      "epoch": 0.00490698674331829,
+      "grad_norm": 25.17514419555664,
+      "learning_rate": 0.0001346117057077493,
+      "loss": 7.4075,
+      "step": 51
+    },
+    {
+      "epoch": 0.005195633022337012,
+      "grad_norm": 21.17397117614746,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 6.9151,
+      "step": 54
+    },
+    {
+      "epoch": 0.005195633022337012,
+      "eval_loss": 0.21289654076099396,
+      "eval_runtime": 12548.5942,
+      "eval_samples_per_second": 2.79,
+      "eval_steps_per_second": 1.395,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3666203419475968e+17,
+  "total_flos": 2.839944410337116e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null