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:a54f9f423ae0a8098a29de3da3bd0e9c38bd4b551225bb78cc3b792f97b718a8
+oid sha256:98ac73fb18a717426f2d677a555ecd63e01072e96c43b7ad4e189cf99b17591a
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e540daaaa28f49d36eceaa194cd87cc0d2c5411861b6df9e9af623d86abed252
+oid sha256:817a9e783c17b568df71f9fb9a7ade93ccfcad0d547e2ad0a6e3242f048c8f93
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df5b0601170dedc7fb3816869722e4a1064c4d6d09140d08bf1f5e006e2abd3
+oid sha256:d37f984e459ac29119d1e223e683833fa82191d86820ac8eb951dd3f4fbd981f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
+oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15145368492224476,
+  "epoch": 0.17308992562542258,
   "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": 8.956,
       "eval_steps_per_second": 4.478,
       "step": 63
+    },
+    {
+      "epoch": 0.15866576515663736,
+      "grad_norm": 1.004503607749939,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 1.1231,
+      "step": 66
+    },
+    {
+      "epoch": 0.16587784539102998,
+      "grad_norm": 0.8763646483421326,
+      "learning_rate": 6.538829429225069e-05,
+      "loss": 1.1959,
+      "step": 69
+    },
+    {
+      "epoch": 0.17308992562542258,
+      "grad_norm": 1.0786497592926025,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.2195,
+      "step": 72
+    },
+    {
+      "epoch": 0.17308992562542258,
+      "eval_loss": 1.0894047021865845,
+      "eval_runtime": 156.5655,
+      "eval_samples_per_second": 8.955,
+      "eval_steps_per_second": 4.477,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.761757705040036e+17,
+  "total_flos": 4.2988852305985536e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null