Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:685557d6c7f0acd63fc143db4dd74a3f2188486f8b8bc96de5530b270a92e239
+oid sha256:f1f985b2de0be9c55d45c71723bd8aea6b04cbb3d676df4db5bac7f76ba3f0bc
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4cd701ffb567d640f9a3b0d0d970467943ee7745b13bc1bf0f0995236a5cb5
+oid sha256:59c99d53fa636b9ef80c5541e87e913e7bca2f3b6e0f847d74f5e68a49b45a3a
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a115517abb6d8b87ea28a19292f9a3bef4c09cf7bb3e28560963cea766ee1e1
+oid sha256:c63b277f9063baabe3cab581c91fc76d2ee8635847283051aab19b4b4f8b94a4
 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": 0.004118997847823625,
+  "epoch": 0.006178496771735437,
   "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": 37.301,
       "eval_steps_per_second": 18.652,
       "step": 100
+    },
+    {
+      "epoch": 0.004530897632605987,
+      "grad_norm": 0.8922375440597534,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 0.9168,
+      "step": 110
+    },
+    {
+      "epoch": 0.004942797417388349,
+      "grad_norm": 0.8508503437042236,
+      "learning_rate": 7.217825360835473e-05,
+      "loss": 0.9419,
+      "step": 120
+    },
+    {
+      "epoch": 0.005354697202170712,
+      "grad_norm": 0.7896482348442078,
+      "learning_rate": 5.713074385969457e-05,
+      "loss": 0.9312,
+      "step": 130
+    },
+    {
+      "epoch": 0.0057665969869530745,
+      "grad_norm": 0.8143855929374695,
+      "learning_rate": 4.3193525326884435e-05,
+      "loss": 0.9023,
+      "step": 140
+    },
+    {
+      "epoch": 0.006178496771735437,
+      "grad_norm": 0.7980097532272339,
+      "learning_rate": 3.072756464904006e-05,
+      "loss": 0.8894,
+      "step": 150
+    },
+    {
+      "epoch": 0.006178496771735437,
+      "eval_loss": 0.9244847893714905,
+      "eval_runtime": 273.882,
+      "eval_samples_per_second": 37.326,
+      "eval_steps_per_second": 18.665,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8200486649856000.0,
+  "total_flos": 1.2300729974784e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null