Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e702b14829d11f50416692b7314645eed8edb9ef55004a134630ab89f21564
+oid sha256:703111afd8de5da31434bbffcf1751ae8c1729bfa301e3e14ad6aaec1d7b1465
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51a6dc0f4490063fd77dbc7abd15e069a4ceba0555b0127116aa94a284c08b7f
+oid sha256:03db6c7c5ee7f73fa9f854f673d04717d0ae9a0bf00b4dbd1c0ad0b07dbff2a0
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df98b952a993c028712d01917c33ffa810e4469add5fd029bc7022e9ce56793
+oid sha256:09fbf705d0b0068815c843aaa33a8af71fae90cfe1af355c27f9a01b44f5b835
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d43bd90ad476e419738deb9472ad85fd5991005a147e1627aa99867bdfc5655
+oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9701052631578947,
+  "epoch": 1.0913684210526315,
   "eval_steps": 50,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -527,6 +527,69 @@
       "learning_rate": 4.095071251953399e-05,
       "loss": 1.3472,
       "step": 72
+    },
+    {
+      "epoch": 0.983578947368421,
+      "grad_norm": 0.5706843733787537,
+      "learning_rate": 3.83534068877284e-05,
+      "loss": 1.4041,
+      "step": 73
+    },
+    {
+      "epoch": 0.9970526315789474,
+      "grad_norm": 0.5967234373092651,
+      "learning_rate": 3.5812607646303834e-05,
+      "loss": 1.31,
+      "step": 74
+    },
+    {
+      "epoch": 1.0105263157894737,
+      "grad_norm": 1.052331566810608,
+      "learning_rate": 3.333223252352985e-05,
+      "loss": 2.0664,
+      "step": 75
+    },
+    {
+      "epoch": 1.024,
+      "grad_norm": 0.6153193712234497,
+      "learning_rate": 3.091610607806452e-05,
+      "loss": 1.516,
+      "step": 76
+    },
+    {
+      "epoch": 1.0374736842105263,
+      "grad_norm": 0.5821354389190674,
+      "learning_rate": 2.856795380176244e-05,
+      "loss": 1.2732,
+      "step": 77
+    },
+    {
+      "epoch": 1.0509473684210526,
+      "grad_norm": 0.6261878609657288,
+      "learning_rate": 2.6291396375236232e-05,
+      "loss": 1.2817,
+      "step": 78
+    },
+    {
+      "epoch": 1.064421052631579,
+      "grad_norm": 0.5795064568519592,
+      "learning_rate": 2.4089944085029363e-05,
+      "loss": 1.3216,
+      "step": 79
+    },
+    {
+      "epoch": 1.0778947368421052,
+      "grad_norm": 0.5134410262107849,
+      "learning_rate": 2.1966991411008938e-05,
+      "loss": 1.2917,
+      "step": 80
+    },
+    {
+      "epoch": 1.0913684210526315,
+      "grad_norm": 0.6312588453292847,
+      "learning_rate": 1.99258117923236e-05,
+      "loss": 1.1945,
+      "step": 81
     }
   ],
   "logging_steps": 1,
@@ -546,7 +609,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.000598022986138e+16,
+  "total_flos": 6.750672775859405e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null