Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c4fce5cfe32519a28388f7d1348427cace9a5bbc7fdcb42cd3a610f5a09b5c3
+oid sha256:27ea994bf14041147957e9710f066bfea9b71ae038d561ae5103f8fbbbb3b3b3
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b76806b0f6ab024d80b19c54695c7ae0422c719d15d5cd3bdfd8fba7688986c
+oid sha256:89b880315bfcdbcd43b1fb921b310af312f6062c3c8620eb2368afab044b0093
 size 63350356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3fbea5d1a6eda079b7b558d4de40c6d205a4bfa942ab3704e24899a9f2ac99
+oid sha256:3fa0224b8fb2b0426a129f41a0666ecf84d9b716217e39a5d1bf97eabc1d4486
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f331dc26bc0f831c123579d0f1016dd0c68b1e6dd20d45f153e5ad72322ffd
+oid sha256:5d9670b20a9cb1941b45346abad5eae0ba745f1dbd9ea876438710fe005ce5c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028,
+  "epoch": 0.034,
   "eval_steps": 1000,
-  "global_step": 70,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,103 @@
       "learning_rate": 6.185567010309279e-05,
       "loss": 1.593,
       "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.979381443298969e-05,
+      "loss": 2.1242,
+      "step": 71
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.7731958762886594e-05,
+      "loss": 1.8834,
+      "step": 72
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.567010309278351e-05,
+      "loss": 1.3748,
+      "step": 73
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.360824742268041e-05,
+      "loss": 1.3684,
+      "step": 74
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 5.1546391752577315e-05,
+      "loss": 1.392,
+      "step": 75
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.948453608247423e-05,
+      "loss": 1.8425,
+      "step": 76
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.7422680412371134e-05,
+      "loss": 1.6621,
+      "step": 77
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.536082474226804e-05,
+      "loss": 1.5169,
+      "step": 78
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.329896907216495e-05,
+      "loss": 1.4549,
+      "step": 79
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.1237113402061855e-05,
+      "loss": 1.6084,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.9175257731958764e-05,
+      "loss": 1.3467,
+      "step": 81
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.7113402061855674e-05,
+      "loss": 1.6058,
+      "step": 82
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.5051546391752576e-05,
+      "loss": 1.3481,
+      "step": 83
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.2989690721649485e-05,
+      "loss": 1.9237,
+      "step": 84
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 3.0927835051546395e-05,
+      "loss": 1.5566,
+      "step": 85
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 7958034868224000.0,
+  "total_flos": 9498160042721280.0,
   "trial_name": null,
   "trial_params": null
 }