Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93e02cdd1adcfe71a506fa5bc7635a71a137ea736debdec16ce3088c2f4288b7
+oid sha256:d5f46cdbcddbd110909abba05976b088ca0a215268860607fa465f10ca9912a1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bcd7ac9e515130617391943b3d9f5a46923b1b1cd7abb4951103e1e52bf91e
+oid sha256:666644d5d3a68687287a0c66a70b9e5eaf88924d5e93ea735cf48152d89870b9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c53416f50af32d04b9099560de94b7eda2ac7de98df5f4387b71785667ea642a
+oid sha256:05e8b11cd8d83539c6a1db5f797527713c44262128b9b6a0754da46492005fea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff360a84775339d0d3e752ae059cb60f5332814e8f938b32d8d690f5d4087fc5
+oid sha256:52408658f8afed2d0ac64c41a3c3f93b4c8a8478fa6362941012d17f634f7dad
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03423192126658109,
+  "epoch": 0.03667705849990831,
   "eval_steps": 34,
-  "global_step": 70,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -521,6 +521,41 @@
       "learning_rate": 0.00017390089172206592,
       "loss": 0.9441,
       "step": 70
+    },
+    {
+      "epoch": 0.03472094871324653,
+      "grad_norm": 0.3507513999938965,
+      "learning_rate": 0.00017264335740162242,
+      "loss": 0.9604,
+      "step": 71
+    },
+    {
+      "epoch": 0.035209976159911976,
+      "grad_norm": 0.39182308316230774,
+      "learning_rate": 0.00017136101544117525,
+      "loss": 1.0598,
+      "step": 72
+    },
+    {
+      "epoch": 0.03569900360657742,
+      "grad_norm": 0.3877043128013611,
+      "learning_rate": 0.0001700543037593291,
+      "loss": 0.8719,
+      "step": 73
+    },
+    {
+      "epoch": 0.036188031053242864,
+      "grad_norm": 0.6628935933113098,
+      "learning_rate": 0.00016872366859692627,
+      "loss": 0.9241,
+      "step": 74
+    },
+    {
+      "epoch": 0.03667705849990831,
+      "grad_norm": 0.45674100518226624,
+      "learning_rate": 0.00016736956436465573,
+      "loss": 1.2833,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -540,7 +575,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1072679368851456e+17,
+  "total_flos": 3.329215646662656e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null