Training in progress, step 160, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2832e178fbfc4fe2fb481e79a8d919fe407032c53cea12f332a1381234b6f1c4
+oid sha256:4d364eb38a8be050b253d95fb9bb96a3cca85c934f5694fdf28af039b0f831af
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbcd49ec20bf55444feca0578bd6f0012b99c1072af990df00376b5d58929f87
+oid sha256:86177b2d4721c68d5e890ce7ce966763b55e655be1b7686c76b23550228c8c19
 size 281829907

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:994855e9f3bb291ce54dbed25621bf0ab9b11111a5f95765ed4ae5933e96cbd7
+oid sha256:c87752ccee056791ab2999ec7c3dec0f8bae82b1dfd073feafe2df524ed5926c
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cea2e56a8bde12e649a1d7cae49ed9d38ef81a2916cebf53379e47210c432c6
+oid sha256:4d8f1711fa5a9b936955c6d8224082844929d47bb03fce797eceac8f3a3a5313
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6,
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 120,
+  "global_step": 160,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -184,6 +184,62 @@
       "learning_rate": 0.0002694209618222516,
       "loss": 0.4828,
       "step": 120
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.09766612201929092,
+      "learning_rate": 0.00025,
+      "loss": 0.4853,
+      "step": 125
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 0.09704718738794327,
+      "learning_rate": 0.00023057903817774841,
+      "loss": 0.4392,
+      "step": 130
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.11206477135419846,
+      "learning_rate": 0.00021127545494647882,
+      "loss": 0.4489,
+      "step": 135
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 0.11189498007297516,
+      "learning_rate": 0.00019220591947125766,
+      "loss": 0.4856,
+      "step": 140
+    },
+    {
+      "epoch": 1.9333333333333333,
+      "grad_norm": 0.1053239181637764,
+      "learning_rate": 0.0001734856863530282,
+      "loss": 0.4406,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.10603803396224976,
+      "learning_rate": 0.0001552278990399052,
+      "loss": 0.4405,
+      "step": 150
+    },
+    {
+      "epoch": 2.066666666666667,
+      "grad_norm": 0.1078822985291481,
+      "learning_rate": 0.00013754290599809105,
+      "loss": 0.3784,
+      "step": 155
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.09372378885746002,
+      "learning_rate": 0.00012053759377541865,
+      "loss": 0.4102,
+      "step": 160
     }
   ],
   "logging_steps": 5,
@@ -203,7 +259,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3966885123194880.0,
+  "total_flos": 5289180164259840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null