Training in progress, step 130, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90d81106a66a46d33a8f9d9caaf45506fd89c41f919ddab7c8efc174c6169c96
+oid sha256:04219c720b69da395b407d47b273d1b6f06d909e0e16bc792d9da19239623894
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50427f411908ce94836f273c865fdeb10150f8c6848637c78bce147e39c52e9a
+oid sha256:5045a1eecb46de53b6cd1195ec2d1add713e18b2412bfe58472bed9fbf500eac
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ae4de6cae258994b2e610a17502d0e0897089893ff3ea440cdda7e7a8e9774
+oid sha256:f9e2e9d13f1fab954a76ecc1666482fd90d98438794e386126a6ee156ce5d270
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b577939e8ae09a93269bdd1ffbcc4ef41ec4027476aa914ab19034c5a6ebf492
+oid sha256:fb82cfc852da5eb6970b061692451307a303bfd2a3160c6d6a29266f8bb6adef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.061128430833180515,
+  "epoch": 0.06357356806650773,
   "eval_steps": 34,
-  "global_step": 125,
+  "global_step": 130,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -914,6 +914,41 @@
       "learning_rate": 8.162504821834295e-05,
       "loss": 1.0532,
       "step": 125
+    },
+    {
+      "epoch": 0.06161745827984596,
+      "grad_norm": 0.39318689703941345,
+      "learning_rate": 7.9811759084299e-05,
+      "loss": 1.06,
+      "step": 126
+    },
+    {
+      "epoch": 0.0621064857265114,
+      "grad_norm": 0.386799693107605,
+      "learning_rate": 7.800536421603317e-05,
+      "loss": 1.0903,
+      "step": 127
+    },
+    {
+      "epoch": 0.06259551317317684,
+      "grad_norm": 0.4709027409553528,
+      "learning_rate": 7.620648049573815e-05,
+      "loss": 0.9893,
+      "step": 128
+    },
+    {
+      "epoch": 0.06308454061984228,
+      "grad_norm": 0.38078197836875916,
+      "learning_rate": 7.441572224055644e-05,
+      "loss": 1.0638,
+      "step": 129
+    },
+    {
+      "epoch": 0.06357356806650773,
+      "grad_norm": 0.2914995849132538,
+      "learning_rate": 7.263370099279172e-05,
+      "loss": 1.0144,
+      "step": 130
     }
   ],
   "logging_steps": 1,
@@ -933,7 +968,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.54869274443776e+17,
+  "total_flos": 5.77064045421527e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null