Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06fa68d78d89a854827883ee55215383e1c1c0760a1ad33c93f2228f78986fd2
+oid sha256:9392dfab3d55e54ea39ae535f1f81a34b93b857d22a4f10c329993c296ccf616
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a8ce6d55957a4220034cdaf2960db4f9f9bb3123247090414c373d1298a53bf
+oid sha256:46d3cf151841a29458afd940f20d3704dadaddb2839c5d166123ccbe83bc2b8a
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:748c00c41dcc9767a3a919d998beb10fbad73a8dec5e63ea35c1f405977a910e
+oid sha256:aaa306a615f19cdf4bbc036ac17f0d0affdd165e969573fa03d457dc23dc7e21
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
+oid sha256:4f9bc32841f0c3d8bc8ea90b0bc3413eece3c955acd985fe2913112493248454
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.1272727272727274,
+  "epoch": 2.3636363636363638,
   "eval_steps": 13,
-  "global_step": 117,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -360,6 +360,42 @@
       "eval_samples_per_second": 9.958,
       "eval_steps_per_second": 1.285,
       "step": 117
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.3988870680332184,
+      "learning_rate": 1.090842587659851e-05,
+      "loss": 0.0385,
+      "step": 120
+    },
+    {
+      "epoch": 2.2363636363636363,
+      "grad_norm": 0.3185819983482361,
+      "learning_rate": 8.899896227604509e-06,
+      "loss": 0.0351,
+      "step": 123
+    },
+    {
+      "epoch": 2.290909090909091,
+      "grad_norm": 0.3625490665435791,
+      "learning_rate": 7.077560319906695e-06,
+      "loss": 0.0318,
+      "step": 126
+    },
+    {
+      "epoch": 2.3454545454545457,
+      "grad_norm": 0.31989988684654236,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0339,
+      "step": 129
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "eval_loss": 0.13768097758293152,
+      "eval_runtime": 9.3375,
+      "eval_samples_per_second": 9.96,
+      "eval_steps_per_second": 1.285,
+      "step": 130
     }
   ],
   "logging_steps": 3,
@@ -379,7 +415,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.6351846578716672e+17,
+  "total_flos": 2.9142596699396506e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null