Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f090a967c768682a5c33da5adf53c647384951be19662b908338cdb28a9d17ca
+oid sha256:b44225243062c88e47568ad7e33ae051863a9222451ceeb231123684c93addfe
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9345b9d1e697822621ea85e4941ac524a4dff70444e09d39085bce12b1ba34e8
+oid sha256:9cc9ae53dd8f8b0f56a026ac1a10a905b61a070fcbf30dc01a4d4e8a96cc729a
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926c539986362599115d4154ffc69906160c0ab960c9d9ae1b2884107080e0e2
+oid sha256:149ce6f9fed784895c9f3e27043159b254515601069bd04b971d74fdaafd4f26
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.014760147601476014,
+  "epoch": 0.01968019680196802,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 7.285,
       "eval_steps_per_second": 0.913,
       "step": 27
+    },
+    {
+      "epoch": 0.016400164001640016,
+      "grad_norm": 0.2171449512243271,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.686,
+      "step": 30
+    },
+    {
+      "epoch": 0.018040180401804017,
+      "grad_norm": 0.14807440340518951,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.5976,
+      "step": 33
+    },
+    {
+      "epoch": 0.01968019680196802,
+      "grad_norm": 0.19816875457763672,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.6343,
+      "step": 36
+    },
+    {
+      "epoch": 0.01968019680196802,
+      "eval_loss": 0.626940906047821,
+      "eval_runtime": 422.6652,
+      "eval_samples_per_second": 7.289,
+      "eval_steps_per_second": 0.913,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.073707050663936e+16,
+  "total_flos": 9.453645871448064e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null