Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b93e5bd75b575e6e88f5e54747692cc658d8c0ffc173de276a183558eec11a8
+oid sha256:dd701c77ed33ad2c9d2a9005245fc7c4bf1f113e8fda45fc514315d2a65bc289
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caefd9faa605619008e57cbbd0df85b8f2e8b808d4168b750dab18e0851e3030
+oid sha256:2c7c25814e14d28ffdfe538f83854adad79338109d05fc8bfac1d2245ba2e55f
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aff36119180d11672e5f41239d75959a6cc53a2997d91aee1bbc1f32b00c958
+oid sha256:fc8cd07aac7537c464bf38a5760aed564a544cf74a9537eab637e6cc69579c7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0009804106412262675,
+  "epoch": 0.001960821282452535,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 6.184,
       "eval_steps_per_second": 3.092,
       "step": 10
+    },
+    {
+      "epoch": 0.0011312430475687702,
+      "grad_norm": 3.774066209793091,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.1968,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015083240634250269,
+      "grad_norm": 4.928558349609375,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.2653,
+      "step": 20
+    },
+    {
+      "epoch": 0.0015083240634250269,
+      "eval_loss": 0.7486514449119568,
+      "eval_runtime": 903.8279,
+      "eval_samples_per_second": 6.178,
+      "eval_steps_per_second": 3.089,
+      "step": 20
+    },
+    {
+      "epoch": 0.0018854050792812835,
+      "grad_norm": 4.04644250869751,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.8283,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7345973797847040.0,
+  "total_flos": 1.476326772965376e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null