Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b05b517de513c6779c8a19034a68f842f09784089d4df2fe1201c64995083d3d
+oid sha256:86e094428b014b10d14296bc96c79f343649fab50ee7757345d4ad890641dfb8
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346f5ae41ea0e9571fea16e8eb259c6a1f14901e23032287060cb42b4ae0c07c
+oid sha256:025e9c1a87c6b20c4124a8c37258471dfbfd1d35fd46a6532e0e6044a829dd60
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85446ac734307ad4c1e230db7d5d6a8d6dac6e2bec648ba2b41d25022bee9cdf
+oid sha256:f05e2a7fe5f9efc4996d13bce479f8f30cf4261d161f444cb216569e0ff49c89
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03541315345699832,
+  "epoch": 0.04047217537942664,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 18.186,
       "eval_steps_per_second": 2.276,
       "step": 63
+    },
+    {
+      "epoch": 0.03709949409780776,
+      "grad_norm": 0.16439783573150635,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.7293,
+      "step": 66
+    },
+    {
+      "epoch": 0.0387858347386172,
+      "grad_norm": 0.16857261955738068,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.7634,
+      "step": 69
+    },
+    {
+      "epoch": 0.04047217537942664,
+      "grad_norm": 0.15915103256702423,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.7338,
+      "step": 72
+    },
+    {
+      "epoch": 0.04047217537942664,
+      "eval_loss": 0.7342514991760254,
+      "eval_runtime": 164.7816,
+      "eval_samples_per_second": 18.188,
+      "eval_steps_per_second": 2.276,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.291797468794061e+16,
+  "total_flos": 3.762054250050355e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null