Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691b843257f66e6dce930a3ceaf93df118881a2af93d5ef854679d2c9abdcdc8
+oid sha256:c3259410213f71972c5e084cfb4b3533792e0d83aec4fd313939eef10673ed4a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4890974348f52d8c9eb44f99a68dbe8026aea0524933d3349be5b8099720dbcc
+oid sha256:012aa51818c4458bc844cdc7cd8dd1e8655a6a70f8c4d71986db5bcd5c1bdc9c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bf193375456cd21ea5a24fd57cdba48349bd4edb788a35a7f0b46bef9f06eb5
+oid sha256:c3b054ae045b714f7e85cf547e62356e2e1fe97d70e4f0c74b5d95786c4a60c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4b36faeb98dcba92fa1213b5be4990581f9deb5a2fb8d1e425563b55ede5df9
+oid sha256:8634170e919c9d99c690b0056337094258fdb77569d2feaf905b96c380dc695e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0025303643724696357,
+  "epoch": 0.003036437246963563,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -83,6 +83,21 @@
       "eval_samples_per_second": 13.01,
       "eval_steps_per_second": 6.505,
       "step": 45
+    },
+    {
+      "epoch": 0.0028115159694107063,
+      "grad_norm": 4.259403705596924,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 3.1686,
+      "step": 50
+    },
+    {
+      "epoch": 0.003036437246963563,
+      "eval_loss": 0.7657517790794373,
+      "eval_runtime": 287.3701,
+      "eval_samples_per_second": 26.057,
+      "eval_steps_per_second": 13.028,
+      "step": 54
     }
   ],
   "logging_steps": 10,
@@ -102,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8569390765178880.0,
+  "total_flos": 1.0195377730879488e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null