Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc6981a9a3b464a92ca4893919b3ce592883f8cb80e5c66b94bd99f24ab4f8c
+oid sha256:198b80ec28ce5ce0b3d455500f182b56ea364aa1528ced46756d7be144210032
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca03c1d13032d2c82a90bfbcf54d219887e9cb321beff9e40593f7d0a5370d1e
+oid sha256:ce776e8b16137f8ecdb7f2407056410613034570db744a54ed5a4598b6eed8d5
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de49c048068e4ff056f002888046f6d50e4b4c2a5714da6751173a978b5ccfc4
+oid sha256:aa8e202d1e724bd48d211480607ebff7d50e6294a8b7441e06c81ba075040699
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
+oid sha256:d85eac2daddfe8e3f78a5d6ef1e9ba13c04651694635a9ed76369a20726389db
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7275789473684211,
+  "epoch": 0.8488421052631578,
   "eval_steps": 50,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -401,6 +401,69 @@
       "learning_rate": 9.25084022891929e-05,
       "loss": 1.3016,
       "step": 54
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 0.6199703812599182,
+      "learning_rate": 8.963177415120962e-05,
+      "loss": 1.5274,
+      "step": 55
+    },
+    {
+      "epoch": 0.7545263157894737,
+      "grad_norm": 0.6474433541297913,
+      "learning_rate": 8.673258487801731e-05,
+      "loss": 1.3812,
+      "step": 56
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 0.5689646601676941,
+      "learning_rate": 8.381530480933783e-05,
+      "loss": 1.4005,
+      "step": 57
+    },
+    {
+      "epoch": 0.7814736842105263,
+      "grad_norm": 0.5995835661888123,
+      "learning_rate": 8.088443217958837e-05,
+      "loss": 1.2694,
+      "step": 58
+    },
+    {
+      "epoch": 0.7949473684210526,
+      "grad_norm": 0.5566097497940063,
+      "learning_rate": 7.794448618193015e-05,
+      "loss": 1.4341,
+      "step": 59
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 0.6118280291557312,
+      "learning_rate": 7.5e-05,
+      "loss": 1.378,
+      "step": 60
+    },
+    {
+      "epoch": 0.8218947368421052,
+      "grad_norm": 0.5662732124328613,
+      "learning_rate": 7.205551381806987e-05,
+      "loss": 1.4138,
+      "step": 61
+    },
+    {
+      "epoch": 0.8353684210526315,
+      "grad_norm": 0.5312877893447876,
+      "learning_rate": 6.911556782041163e-05,
+      "loss": 1.4356,
+      "step": 62
+    },
+    {
+      "epoch": 0.8488421052631578,
+      "grad_norm": 0.5712493062019348,
+      "learning_rate": 6.618469519066217e-05,
+      "loss": 1.4667,
+      "step": 63
     }
   ],
   "logging_steps": 1,
@@ -420,7 +483,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.500448517239603e+16,
+  "total_flos": 5.25052327011287e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null