Training in progress, step 55, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb3562d2376c7e44e807e75a251bfe4e20a8bbb1d2473548015437b6b53b8be3
+oid sha256:3e0b256324c77b74ce7cf35a934a1dea4cf2f1c4e901640287d88f57a3f16226
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a568b5ae0096ae42229e78a73ab2eb0dffab5c441bf57831500fe90f81243a04
+oid sha256:54788bd57376a0ecc9872c34fed24cc6327e9699d90ddaa7ba48b2e34adcbf9a
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e6a3dd563025f97e8d76541a82675dcf5abbc55aa6acc033ab4e92d8fbe7d5d
+oid sha256:501917edc59cb38fa8ba673663fd0069ec90987aba1d4647ea54c9fb6fe18e47
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c6ef871b14e9c2b6e6517244b08d50c3b172209dbf2c7f2f35e5b70f657975
+oid sha256:61487aeef4449a4dec50f3ae9ec76bca52908878863009a40746a21c237f51ad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.024451372333272204,
+  "epoch": 0.026896509566599426,
   "eval_steps": 34,
-  "global_step": 50,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,41 @@
       "learning_rate": 0.00019324722294043558,
       "loss": 1.0124,
       "step": 50
+    },
+    {
+      "epoch": 0.024940399779937648,
+      "grad_norm": 0.2487930953502655,
+      "learning_rate": 0.00019256376597815564,
+      "loss": 0.9894,
+      "step": 51
+    },
+    {
+      "epoch": 0.02542942722660309,
+      "grad_norm": 0.39657795429229736,
+      "learning_rate": 0.00019184869857459232,
+      "loss": 1.138,
+      "step": 52
+    },
+    {
+      "epoch": 0.02591845467326854,
+      "grad_norm": 0.5362446308135986,
+      "learning_rate": 0.00019110226492460885,
+      "loss": 1.0342,
+      "step": 53
+    },
+    {
+      "epoch": 0.026407482119933982,
+      "grad_norm": 0.5089200139045715,
+      "learning_rate": 0.0001903247199346129,
+      "loss": 1.1193,
+      "step": 54
+    },
+    {
+      "epoch": 0.026896509566599426,
+      "grad_norm": 0.28259485960006714,
+      "learning_rate": 0.00018951632913550626,
+      "loss": 0.9054,
+      "step": 55
     }
   ],
   "logging_steps": 1,
@@ -392,7 +427,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.219477097775104e+17,
+  "total_flos": 2.4414248075526144e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null