Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c75d66675c792f5e23fea6eac9fd9953ced2235105d92cc138b9edd1dd3105f
+oid sha256:1d9a1fc6f51087893687fcfc07f90ac5ddca4596c22687593af440f4d6a45507
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:647f172ae0a02e5ada7d5050144702c3cb1162b2f8f244342bdfbbcd53fb5c2e
+oid sha256:36c2286ec040c048795eb1542740f29f7dde68491269afb5151b4b5ca514e243
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a6fd2b248741a11823537d56957d1fe80916ef1a6eda0f48feeb67a1eed2e2
+oid sha256:f1f76708d5bde16be37e04a9e08236c745f9eacd944c01fc293b9f67a259d262
 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": 0.0037222619899785255,
+  "epoch": 0.005583392984967788,
   "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": 11.506,
       "eval_steps_per_second": 5.753,
       "step": 26
+    },
+    {
+      "epoch": 0.004294917680744453,
+      "grad_norm": 0.9274352192878723,
+      "learning_rate": 0.0001,
+      "loss": 3.4613,
+      "step": 30
+    },
+    {
+      "epoch": 0.005583392984967788,
+      "eval_loss": 0.8650556802749634,
+      "eval_runtime": 255.7824,
+      "eval_samples_per_second": 11.502,
+      "eval_steps_per_second": 5.751,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.598943274205184e+16,
+  "total_flos": 2.3746682290176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null