Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:303d3808899ee31f18d353a81aee545e536a2dcd4cbf6b967519fa2c85e216cf
+oid sha256:6a71f452e39be42f226077fc02ef1d9cd35fb105385d0893e5923d2ba4da0414
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf82ca0d1c2a8b78b728f10513331085b2fa3972fe291e89f4a5f25e18d40d82
+oid sha256:603fc44dc0dcc7e55622ab39fe350be7bf496843a61f644202a9539169eb455c
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85797b6736a862291678baca072e183198938fa2e531b073954ae497386d1e69
+oid sha256:4c8920f2a4268bc4fce4895714a93f0d42f4b23ede61ecccf586bc2a1a8d9321
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbdbed6f103600bb101032f12d2fcf21f68d620e7d74db4f36c50456df69b7e
+oid sha256:7ad7fafc1af8d86c13379f526e0cfbac632a863b9b0610d9ebb41405c99da8a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3817534778388871,
+  "epoch": 0.38822387576835976,
   "eval_steps": 386,
-  "global_step": 295,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2080,6 +2080,41 @@
       "learning_rate": 9.898317912544536e-05,
       "loss": 0.8985,
       "step": 295
+    },
+    {
+      "epoch": 0.38304755742478164,
+      "grad_norm": 0.8654418587684631,
+      "learning_rate": 9.897489014490553e-05,
+      "loss": 0.8752,
+      "step": 296
+    },
+    {
+      "epoch": 0.38434163701067614,
+      "grad_norm": 0.7863161563873291,
+      "learning_rate": 9.896656786597535e-05,
+      "loss": 1.0138,
+      "step": 297
+    },
+    {
+      "epoch": 0.3856357165965707,
+      "grad_norm": 0.8346667885780334,
+      "learning_rate": 9.895821229431323e-05,
+      "loss": 0.94,
+      "step": 298
+    },
+    {
+      "epoch": 0.3869297961824652,
+      "grad_norm": 0.9577547907829285,
+      "learning_rate": 9.894982343560016e-05,
+      "loss": 0.9967,
+      "step": 299
+    },
+    {
+      "epoch": 0.38822387576835976,
+      "grad_norm": 0.7633039951324463,
+      "learning_rate": 9.894140129553981e-05,
+      "loss": 0.8469,
+      "step": 300
     }
   ],
   "logging_steps": 1,
@@ -2099,7 +2134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2979146564960256e+17,
+  "total_flos": 3.353811515080704e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null