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:d7278c1135863e5ccf9bfc8361af8662c2414ecbca387270930625bdcb71fb52
+oid sha256:f06f2f40fe820d4f604ed1daffafae1b46c9e95c855d49cdded50cb40c4aa700
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d0d7bcd4284cbccabf3cdf59a92b4a51750ac0b5f64cd56634ec886272d3e2
+oid sha256:8829651f2fbd7e8352551568275ac3d148b153db81543c9dd871212833e4b04c
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41636bb657737ef6da26351e995f4b584d16764bcfbd07db766cbbf0dfddbdbf
+oid sha256:37213a494e3fd6178911cb03fec2c9e30f5cff9cbbc28b6dcb42357a9fc84265
 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": 0.00882994472524681,
+  "epoch": 0.010091365400282068,
   "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": 8.989,
       "eval_steps_per_second": 4.494,
       "step": 63
+    },
+    {
+      "epoch": 0.009250418283591895,
+      "grad_norm": 0.8267295360565186,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 1.2522,
+      "step": 66
+    },
+    {
+      "epoch": 0.009670891841936981,
+      "grad_norm": 0.8061164021492004,
+      "learning_rate": 6.538829429225069e-05,
+      "loss": 1.2313,
+      "step": 69
+    },
+    {
+      "epoch": 0.010091365400282068,
+      "grad_norm": 0.8370426893234253,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 1.2828,
+      "step": 72
+    },
+    {
+      "epoch": 0.010091365400282068,
+      "eval_loss": 1.3291566371917725,
+      "eval_runtime": 2673.7837,
+      "eval_samples_per_second": 8.989,
+      "eval_steps_per_second": 4.494,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.759892678909624e+17,
+  "total_flos": 4.297020204468142e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null