Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5edf6d4e50770a4d47b33b41a138eefa144cf2441ad9ee1e793383458379f6b
+oid sha256:f685d1b73db37255c28b0937b165cf8eafb0099434ebb5026f9d5f086049f370
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e39541a1961b1b1776c8aa286511b75a4ea3559ceabc41a50d10266e34db0100
+oid sha256:85ccbe8f52b64656a2fae23bebc063ec4f55dfced1911be4f5675713b7a3b725
 size 79968772

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54e1f093d600b612b1e132dbc95de8f3a25e6b7bda5f75ddbe3a65564b445ca
+oid sha256:fb6cd3789a603cc9db1f0b416612fba074ab96fe35f4ad309fac449135e2f22d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
+oid sha256:02d97e2af7e51ba89efcffc7f2a661ca0885e61db7f78987db5df30514ab62df
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02819548872180451,
+  "epoch": 0.03759398496240601,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,21 @@
       "eval_samples_per_second": 27.933,
       "eval_steps_per_second": 6.983,
       "step": 15
+    },
+    {
+      "epoch": 0.03383458646616541,
+      "grad_norm": 1.463262677192688,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.7978,
+      "step": 18
+    },
+    {
+      "epoch": 0.03759398496240601,
+      "eval_loss": 1.7174512147903442,
+      "eval_runtime": 16.0423,
+      "eval_samples_per_second": 27.926,
+      "eval_steps_per_second": 6.982,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -93,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2980244587806720.0,
+  "total_flos": 3973659450408960.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null