Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c340ff2853e6cbd77bbc372d1d52dcab2d71c7964468686cb142634e6f79f04
+oid sha256:6780c8cadf9b9bbe8ce9a3d528c5c91a11c57499678dbc1221b6707c7c45d80c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:817ead807f26785b01ad970366a67276c20d3c3ed19c58a0111d586f1d03f2e9
+oid sha256:e59f65cb32590d23a19a5f0a3bc23e3ed29b78e9017bd3d768881eb066d5db68
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f9cf4d9a5473116427c25cd8c190945fbd751a93f90a6fee9c1aad7ed726a0
+oid sha256:93a4a3475bbbd37ecdd810d8257811f1364a7006e49ca0ea2393e9b025bf14bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02866593164277839,
+  "epoch": 0.04299889746416759,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 17.291,
       "eval_steps_per_second": 8.645,
       "step": 26
+    },
+    {
+      "epoch": 0.03307607497243661,
+      "grad_norm": 4.080863952636719,
+      "learning_rate": 0.0001,
+      "loss": 3.3461,
+      "step": 30
+    },
+    {
+      "epoch": 0.04299889746416759,
+      "eval_loss": 0.7252407670021057,
+      "eval_runtime": 22.0948,
+      "eval_samples_per_second": 17.289,
+      "eval_steps_per_second": 8.645,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9113888121421824.0,
+  "total_flos": 1.3670832182132736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null