Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29791a025ced8d299076a79346377bd78aed9f80b92c62bc9f6fbd9253cf2852
+oid sha256:298516dbcdfb6f71f47cd7ef45620b1a7780cc860fe07420c135805c1714ff23
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d403de80d714eb7e810a40b639c6f9fecc4dff7279304deda2241c8dc2573da3
+oid sha256:65418715ce8a6fdccb45c3ad7a5db6512f82c50e94390bd38ab1df68795dc803
 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 sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 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": 7.217,
       "eval_steps_per_second": 0.904,
       "step": 27
+    },
+    {
+      "epoch": 0.016400164001640016,
+      "grad_norm": 0.2589839696884155,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.7209,
+      "step": 30
+    },
+    {
+      "epoch": 0.018040180401804017,
+      "grad_norm": 0.18874622881412506,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.6304,
+      "step": 33
+    },
+    {
+      "epoch": 0.01968019680196802,
+      "grad_norm": 0.2278064489364624,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.6688,
+      "step": 36
+    },
+    {
+      "epoch": 0.01968019680196802,
+      "eval_loss": 0.6574512720108032,
+      "eval_runtime": 426.6686,
+      "eval_samples_per_second": 7.221,
+      "eval_steps_per_second": 0.905,
+      "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