Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2019092eaab1c98d8ffa6cf5daa900efe89c20c779c04a0660fe242aa83dc4a2
+oid sha256:d2963c2a4f2a7eaa61f07ba73a60b329e7c773fb31384455fc331945f47e37cd
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0825add271cb1928713806d119b0318708f8a4bddc391a2ecb983e76aec8a81c
+oid sha256:18f04fd04382aa5d4dafd98fd6464a92640abcf8c83cb319f966fc0cc49f52ad
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22ccfd88f620eb832cdc95b7c73f631ee104fb7843f178a425bf2208b904d28d
+oid sha256:9f03fbef729f64ddf68b55e06f01e7bb1d8bf0494ed9ac87477f34ab984a1d9b
 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": 0.03444034440344403,
+  "epoch": 0.03936039360393604,
   "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": 7.286,
       "eval_steps_per_second": 0.913,
       "step": 63
+    },
+    {
+      "epoch": 0.03608036080360803,
+      "grad_norm": 0.1749543398618698,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.5603,
+      "step": 66
+    },
+    {
+      "epoch": 0.03772037720377204,
+      "grad_norm": 0.19363927841186523,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 0.5691,
+      "step": 69
+    },
+    {
+      "epoch": 0.03936039360393604,
+      "grad_norm": 0.22506117820739746,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.5878,
+      "step": 72
+    },
+    {
+      "epoch": 0.03936039360393604,
+      "eval_loss": 0.6035451292991638,
+      "eval_runtime": 422.7242,
+      "eval_samples_per_second": 7.288,
+      "eval_steps_per_second": 0.913,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6527352922112e+17,
+  "total_flos": 1.8808127625363456e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null