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:adac11fe9b13bf1b76ad183dcdd7e81553c07712d98750b3a009b0fde4a8f61b
+oid sha256:e1cd5aeb2351bf3f7f393d5da945d90195388ecf503901c6048484c28d16beed
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f08485c8ba652d542301fa3d085478be8bed85616b2bcb26abf83e95f4faea3
+oid sha256:32143bc13d61a27624fdfea7555a00420c4d16ddde6073b23f26708af84d89fc
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887c396fe906e451edd5dc1fa4bc857e822a44e9109e8deb2d1acfa642c3f206
+oid sha256:a595415dd381301168ca7a830d46eddf8b42b4c9fd8235b4b7e89468bc79b8d1
 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": 10.5181,
       "step": 50
+    },
+    {
+      "epoch": 0.024940399779937648,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019256376597815564,
+      "loss": 9.8439,
+      "step": 51
+    },
+    {
+      "epoch": 0.02542942722660309,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019184869857459232,
+      "loss": 9.1904,
+      "step": 52
+    },
+    {
+      "epoch": 0.02591845467326854,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00019110226492460885,
+      "loss": 8.9795,
+      "step": 53
+    },
+    {
+      "epoch": 0.026407482119933982,
+      "grad_norm": 1.3233301388714312e+18,
+      "learning_rate": 0.0001903247199346129,
+      "loss": 8.6349,
+      "step": 54
+    },
+    {
+      "epoch": 0.026896509566599426,
+      "grad_norm": Infinity,
+      "learning_rate": 0.00018951632913550626,
+      "loss": 9.4657,
+      "step": 55
     }
   ],
   "logging_steps": 1,
@@ -392,7 +427,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.102239837978624e+17,
+  "total_flos": 1.2124638217764864e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null