Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7d9f0de45a89fc5cb3bc7796e758edbb6489c836e34f11f012f7531086c814
+oid sha256:327e1fce2e63dae8a2d4099dffd9997a28c2000c73b4387b9c65f61f9cee75dd
 size 130583912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33ab7ba1a39100b39a35ec3bd85348527552b5b2a900cf38cfb9a854b4f4e3b
+oid sha256:256737b5651fa28d430bb2189d3606e1eeb73c220b5e6e809a4ef88ed8594f97
 size 66578772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd81add2bd1b4b406fdf4dff35cd233ccbed55bc850d068f5a65ffc03162b1c1
+oid sha256:a109e0c9f38066f0989282257dd7eb9449c1052dcada1f7051f628fab81dd162
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb0a9ae08a837d696210720a364c40061c9c8b036f36570a99f11fe3b8d70f51
+oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.000561470188092513,
+  "epoch": 0.001122940376185026,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 21.239,
       "eval_steps_per_second": 10.622,
       "step": 13
+    },
+    {
+      "epoch": 0.000863800289373097,
+      "grad_norm": 1.3639366626739502,
+      "learning_rate": 0.0002,
+      "loss": 4.5318,
+      "step": 20
+    },
+    {
+      "epoch": 0.001122940376185026,
+      "eval_loss": 2.1809253692626953,
+      "eval_runtime": 229.5626,
+      "eval_samples_per_second": 21.236,
+      "eval_steps_per_second": 10.62,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2086522781958144.0,
+  "total_flos": 4213957775327232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null