Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a255cc5ce734bbe23f23c79f2b4078f279af75615ab2654732ef205ac08c7d6
+oid sha256:f0f9167aba74f472cd8fa12f577020020cc65dab8f14382a75f6f51abb8d8b61
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2e8ea15401435695a1a6d7c6fa2077b7252bf3b3dc816e830f3582c7ce4bad
+oid sha256:ea83fc27cd80e0169edcc07037c207909276d3e4b09c14554b255b177a088545
 size 132798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be0d95b349f4a5439b800db674fec71503f77dc49f4d60d939a137cc4996bad
+oid sha256:39bfb25b5023e469e66f505c1a20bd42737ec2cae916299b37dc6dd5ce6d0cb4
 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": 0.021477882894400408,
+  "epoch": 0.02454615187931475,
   "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": 486.817,
       "eval_steps_per_second": 60.889,
       "step": 63
+    },
+    {
+      "epoch": 0.02250063922270519,
+      "grad_norm": 0.5121042728424072,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 44.3014,
+      "step": 66
+    },
+    {
+      "epoch": 0.023523395551009973,
+      "grad_norm": 0.47857794165611267,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 44.3116,
+      "step": 69
+    },
+    {
+      "epoch": 0.02454615187931475,
+      "grad_norm": 0.5120978951454163,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 44.3001,
+      "step": 72
+    },
+    {
+      "epoch": 0.02454615187931475,
+      "eval_loss": 11.07617473602295,
+      "eval_runtime": 10.1688,
+      "eval_samples_per_second": 485.897,
+      "eval_steps_per_second": 60.774,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 471670456320.0,
+  "total_flos": 539051950080.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null