Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7310740e9f6b1d549dc7d593d1337e81ff1e08576dc2f2db72336a6a3d1ae2a6
+oid sha256:3d06848349b4385c85e7d1829294f59308b92604034e74581df400d281539d39
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda05f718db000f70ff7429aabf480d4ebeb732b521c632ed91f8d603235e34b
+oid sha256:c9fba810b8a39cdc33a88cae6f3e46986ca052ac6f46a53ce0761b0d6001f46b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b406b950e63c883a5e375e07824f589373180bc8cc6acce00919fc2ab3b022
+oid sha256:198b819774fd43bf907c99b4450f48a63938b3384330a474b96cdd27af2c009e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
+oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00464025160475368,
+  "epoch": 0.005568301925704416,
   "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": 14.03,
       "eval_steps_per_second": 1.754,
       "step": 45
+    },
+    {
+      "epoch": 0.004949601711737259,
+      "grad_norm": 4.873887538909912,
+      "learning_rate": 3.104804738999169e-05,
+      "loss": 5.3023,
+      "step": 48
+    },
+    {
+      "epoch": 0.005258951818720837,
+      "grad_norm": 7.830043792724609,
+      "learning_rate": 2.8479327524001636e-05,
+      "loss": 6.1552,
+      "step": 51
+    },
+    {
+      "epoch": 0.005568301925704416,
+      "grad_norm": 7.771931171417236,
+      "learning_rate": 2.587248741756253e-05,
+      "loss": 6.3556,
+      "step": 54
+    },
+    {
+      "epoch": 0.005568301925704416,
+      "eval_loss": 1.4463921785354614,
+      "eval_runtime": 1163.8809,
+      "eval_samples_per_second": 14.034,
+      "eval_steps_per_second": 1.754,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.644573762538701e+16,
+  "total_flos": 7.91020686016512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null