Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d8e9736efc006c9f6333bedd4f2cd6d31e4acfcc3e68bc75c6f33db5442d072
+oid sha256:f0ee9d038fdfb39e9bd9e55f4c8f788bb92151e68f72b9d6367ea82855ee2e2f
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99f71c66c523575cf877e9256f46e1da9413499eceb6265cf29c21811249692c
+oid sha256:c2f6f1b0a1f8f871f48a36f3d02a2520916fee6a6ee88edb89172de597c386e1
 size 148462004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6927877e6551a1f0698893e28b93742cc61a7a885e166664a8829bb2eadfce
+oid sha256:b32b2639b16b6624de4cc86c5b2874e9893bb8c25e458e5870ebfbb551ffdf86
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1df434ec5d39f570ded65a944db333de3cdd9df7c23996fdc6aaf5d06de18167
+oid sha256:ad5893d6157dd23b3c59b0fbd477b43e2b7bc277c23d1bb43b6558d4e0634ada
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015498948069442554,
+  "epoch": 0.001937368508680319,
   "eval_steps": 500,
-  "global_step": 16,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,34 @@
       "learning_rate": 3.0769230769230774e-05,
       "loss": 2.0042,
       "step": 16
+    },
+    {
+      "epoch": 0.0016467632323782712,
+      "grad_norm": 0.19615541398525238,
+      "learning_rate": 3.269230769230769e-05,
+      "loss": 1.9725,
+      "step": 17
+    },
+    {
+      "epoch": 0.001743631657812287,
+      "grad_norm": 0.18842636048793793,
+      "learning_rate": 3.461538461538462e-05,
+      "loss": 1.9555,
+      "step": 18
+    },
+    {
+      "epoch": 0.0018405000832463032,
+      "grad_norm": 0.23347383737564087,
+      "learning_rate": 3.653846153846154e-05,
+      "loss": 1.9779,
+      "step": 19
+    },
+    {
+      "epoch": 0.001937368508680319,
+      "grad_norm": 0.19372476637363434,
+      "learning_rate": 3.846153846153846e-05,
+      "loss": 1.9203,
+      "step": 20
     }
   ],
   "logging_steps": 1.0,
@@ -138,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5538570495590400.0,
+  "total_flos": 6822886326681600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null