Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6191878491f43ea990ba7de6c7003a7797ace82c07957c1b99f9238153115c46
+oid sha256:97bd4163198baf497e7b4a8abf3c917c56e9716628f424827646fc2b82ad66c2
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e143f5bdcad29f387c29b97e78ef0f60d0c79ec4c58b91771a92b82e941dcd
+oid sha256:5cbfc2ea55f5c437cdf9ee644d95ff2e6022b4072a7a97cf4682c55fe467d231
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3142ee6aaa193c1c9391b604988921bcafd1308f2f439db9ebf61ffce370b67f
+oid sha256:6ac30eb90771ad572928492a9b294c2a00ae840bf4dd4ced4785e131650bb6d2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.27835051546391754,
+  "epoch": 0.30927835051546393,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 6.84,
       "eval_steps_per_second": 0.865,
       "step": 81
+    },
+    {
+      "epoch": 0.28865979381443296,
+      "grad_norm": 1.94657301902771,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.6903,
+      "step": 84
+    },
+    {
+      "epoch": 0.29896907216494845,
+      "grad_norm": 1.8003250360488892,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.9591,
+      "step": 87
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "grad_norm": 1.829463005065918,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 3.063,
+      "step": 90
+    },
+    {
+      "epoch": 0.30927835051546393,
+      "eval_loss": 0.7055235505104065,
+      "eval_runtime": 71.6799,
+      "eval_samples_per_second": 6.836,
+      "eval_steps_per_second": 0.865,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8648187904393216e+17,
+  "total_flos": 3.1964744587935744e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null