Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4df0e1b70cbc406462f50fa47053966a4aadd598f7b2c7c03b8bbf79a922d6
+oid sha256:7650cf86409af55838ac1dc25ddd084b8b18061cd0f67c032a49709923e4beb6
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:783a7745cd06bb68071405a6418bb0e1f0483a532e9b3faf8066fe9dfc3687d3
+oid sha256:0937ad86bd0b7c28b02ff312b3ab2a66768aac76e05413cda95e40b59973310c
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49644ad8f5452e53758ca52013eb3650a3941bcec6083d72c46c935a677f7d88
+oid sha256:455977057132821379da92f1a77f9b1f540991d9dd7c684ba956aca72c970f71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.20947630922693267,
+  "epoch": 0.23940149625935161,
   "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": 14.226,
       "eval_steps_per_second": 1.796,
       "step": 63
+    },
+    {
+      "epoch": 0.2194513715710723,
+      "grad_norm": 1.280704379081726,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 1.2475,
+      "step": 66
+    },
+    {
+      "epoch": 0.22942643391521197,
+      "grad_norm": 1.503631591796875,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 1.3387,
+      "step": 69
+    },
+    {
+      "epoch": 0.23940149625935161,
+      "grad_norm": 1.318060278892517,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 1.2855,
+      "step": 72
+    },
+    {
+      "epoch": 0.23940149625935161,
+      "eval_loss": 1.346817970275879,
+      "eval_runtime": 35.6,
+      "eval_samples_per_second": 14.242,
+      "eval_steps_per_second": 1.798,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.347779772861645e+16,
+  "total_flos": 1.0683176883270451e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null