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:a2cae747609acd15f0bd5e47e06c03de7825e6f4725cb94d94cefc92b6d6ebe4
+oid sha256:39bbe041494d50246913d92ed7230473308905067bba8e83144fc997fa1b979b
 size 66103768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69cf053c015ba0e147ee95712645bc037946cf7f55a10a0eb4d36832a5c61dc5
+oid sha256:7edcde22eddcc6a57b4ee810a49399a57aa42cb1a4c47dfa90e87d1832083652
 size 33939412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a3438e5c4c05cc5f92b6bf2929bd85f16e204d826166c53f2e2fa2c198f18af
+oid sha256:5925b138a3c973f32047aaa4ca9ebc79eba128bf0b849859344e28993a39f8da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec74e92563bbe4b510ec939dc1c78d591826119d26043cc49e0a868b67121a2
+oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002251364889964541,
+  "epoch": 0.0004502729779929082,
   "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": 22.048,
       "eval_steps_per_second": 11.024,
       "step": 13
+    },
+    {
+      "epoch": 0.000346363829225314,
+      "grad_norm": 2.826448678970337,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 6.3914,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004502729779929082,
+      "eval_loss": 1.5376884937286377,
+      "eval_runtime": 1102.0089,
+      "eval_samples_per_second": 22.062,
+      "eval_steps_per_second": 11.032,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2664722245152768.0,
+  "total_flos": 5329444490305536.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null