Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f46cdbcddbd110909abba05976b088ca0a215268860607fa465f10ca9912a1
+oid sha256:7fac2a188ca757124ed37df4c4e3cd760af896f06cb1852013bed461e07edd15
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666644d5d3a68687287a0c66a70b9e5eaf88924d5e93ea735cf48152d89870b9
+oid sha256:94d7315c5918a3d91c3ff30c4f7cbbc0252e41f75551ad8b77f74d0ebc7a4e14
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05e8b11cd8d83539c6a1db5f797527713c44262128b9b6a0754da46492005fea
+oid sha256:01c1ee15529a526a9fe4c19508572c414c6ef23f4c5c37a9bdfac25ac8b91945
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52408658f8afed2d0ac64c41a3c3f93b4c8a8478fa6362941012d17f634f7dad
+oid sha256:4bc75fc1c14b28d29d31fa9d4252536c919fc25a390fac3a1e8c09d6575b4029
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03667705849990831,
+  "epoch": 0.039122195733235526,
   "eval_steps": 34,
-  "global_step": 75,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -556,6 +556,41 @@
       "learning_rate": 0.00016736956436465573,
       "loss": 1.2833,
       "step": 75
+    },
+    {
+      "epoch": 0.03716608594657375,
+      "grad_norm": 0.5053292512893677,
+      "learning_rate": 0.0001659924534878723,
+      "loss": 0.9678,
+      "step": 76
+    },
+    {
+      "epoch": 0.037655113393239195,
+      "grad_norm": 0.31924471259117126,
+      "learning_rate": 0.00016459280624867874,
+      "loss": 0.9702,
+      "step": 77
+    },
+    {
+      "epoch": 0.03814414083990464,
+      "grad_norm": 0.37664365768432617,
+      "learning_rate": 0.0001631711006253251,
+      "loss": 0.8382,
+      "step": 78
+    },
+    {
+      "epoch": 0.03863316828657008,
+      "grad_norm": 0.3583241403102875,
+      "learning_rate": 0.0001617278221289793,
+      "loss": 1.0149,
+      "step": 79
+    },
+    {
+      "epoch": 0.039122195733235526,
+      "grad_norm": 0.3891322910785675,
+      "learning_rate": 0.00016026346363792567,
+      "loss": 1.2247,
+      "step": 80
     }
   ],
   "logging_steps": 1,
@@ -575,7 +610,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.329215646662656e+17,
+  "total_flos": 3.5511633564401664e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null