Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10dbc3e447ef456106185cb387ad618d2b649564c22eea0609cb0023a5e13ec
+oid sha256:c036fa34aa3d38dd51d36d7dccae034c0b2ce7416c44fc7c492a3179e0e40956
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f12eab731e75cd22c441af90d9fb0784724eb0291790d1377106cd2f31f71dd2
+oid sha256:8d71205d99ec41f148fa142badcaa4f1918d416228d3431d866a0aab2932039c
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe2ebf6c6ce4da6faf3c75eec68c00b65479f71477f851e6c8647d90c8b9bf0a
+oid sha256:59fe8c4484114c245f7cb3e862ff95188def5914a8d47654168396cdd28d7d6f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22a6e6a0b2784c7e2a9fa2d84da5a62a9f8cb07ce793f7ae78e83f3f18f8cb85
+oid sha256:ac599fff4b26ed2f8aaa3f64038b795f8035d5e4d74e62f4a3c0c4e718607220
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5688888888888889,
+  "epoch": 0.8533333333333334,
   "eval_steps": 6,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,29 @@
       "eval_samples_per_second": 201.589,
       "eval_steps_per_second": 25.464,
       "step": 12
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 11.580877304077148,
+      "eval_runtime": 0.9468,
+      "eval_samples_per_second": 200.668,
+      "eval_steps_per_second": 25.348,
+      "step": 18
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 7.129571437835693,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 11.7256,
+      "step": 20
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_loss": 11.461081504821777,
+      "eval_runtime": 0.93,
+      "eval_samples_per_second": 204.306,
+      "eval_steps_per_second": 25.807,
+      "step": 24
     }
   ],
   "logging_steps": 10,
@@ -57,7 +80,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 33565974724608.0,
+  "total_flos": 50348962086912.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null