Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71790dcd5f442b4ca25df401bda9645cc7f92f030754a5dffc723ab22d3b0f8
+oid sha256:b5daf99fbc67f78f3732de61d507c0219ef5f2b4cdab752164cb288231963850
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c80b4b755c0a2728a5f67490c270862059eb2a2fa26bd35e82cc77b1ad0206ae
+oid sha256:caffc911962f8e0eccda3755e5ed515835658eca874399b9d5cc64ab9f43e332
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6782a17cd94b88584cdd39e48a03aa9ee53aa99ebb01a7ca50bd04caffebba8e
+oid sha256:ac2fbbcfec39a266c55920bef9e4f13dec185fbafadb2891cdbdeaddfff2bb90
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fd8212ec5ec3406d74a7f927b717dd30ea8a06115ee6582e14976f7b84b4b58
+oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14519056261343014,
+  "epoch": 0.2177858439201452,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 30.659,
       "eval_steps_per_second": 15.329,
       "step": 100
+    },
+    {
+      "epoch": 0.15970961887477314,
+      "grad_norm": 6.844799995422363,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 3.8731,
+      "step": 110
+    },
+    {
+      "epoch": 0.17422867513611615,
+      "grad_norm": 7.042694568634033,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 3.321,
+      "step": 120
+    },
+    {
+      "epoch": 0.18874773139745918,
+      "grad_norm": 5.778402805328369,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 2.6964,
+      "step": 130
+    },
+    {
+      "epoch": 0.20326678765880218,
+      "grad_norm": 6.522513389587402,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 2.7133,
+      "step": 140
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "grad_norm": 8.259108543395996,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 2.9013,
+      "step": 150
+    },
+    {
+      "epoch": 0.2177858439201452,
+      "eval_loss": 2.0801122188568115,
+      "eval_runtime": 9.4829,
+      "eval_samples_per_second": 30.582,
+      "eval_steps_per_second": 15.291,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.84956424814592e+16,
+  "total_flos": 2.77434637221888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null