Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7136f996b0f21b932c755adb995522b6911eb02f048367b49cc8c76fdf35501
+oid sha256:466fbce9975c9c05303ad2e9f3211bd116287df8f6b5fe724fff725117351d68
 size 4785762744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d1c040596727cf0883cc18daf8552a0bb61b5b778051570510785deaee2a35a
+oid sha256:00654d0986b4c2807a076dcd6fb04da902863d7591267af0d0f07d64685e5591
 size 3497859804

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cc60d707915331e36250fa2473cb56c80daf35cba6f39f621da175f542017ff
+oid sha256:f4df07c96cd5b34fe2c47040206f73bf07f974f4e6c2b7b7219d670c2d00c146
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:869d08cbdb3ebaf2562454c023dc210d37d7757b871f2faef0bdbc8f8e514f1c
+oid sha256:91357e6edb760a8623172a8598e28f7bde5a301ce8f9e8873076c6ef6d8599e4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8280430582390285,
+  "epoch": 1.1040574109853711,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,41 @@
       "learning_rate": 9.869471512481871e-05,
       "loss": 0.4844,
       "step": 1500
+    },
+    {
+      "epoch": 0.883245928788297,
+      "grad_norm": 1.647222876548767,
+      "learning_rate": 9.822107419048758e-05,
+      "loss": 0.4732,
+      "step": 1600
+    },
+    {
+      "epoch": 0.9384487993375655,
+      "grad_norm": 1.128386378288269,
+      "learning_rate": 9.76757736856833e-05,
+      "loss": 0.4515,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9936516698868341,
+      "grad_norm": 1.1730600595474243,
+      "learning_rate": 9.705962396149427e-05,
+      "loss": 0.4496,
+      "step": 1800
+    },
+    {
+      "epoch": 1.0488545404361027,
+      "grad_norm": 1.2323981523513794,
+      "learning_rate": 9.637354065543631e-05,
+      "loss": 0.3201,
+      "step": 1900
+    },
+    {
+      "epoch": 1.1040574109853711,
+      "grad_norm": 1.3514504432678223,
+      "learning_rate": 9.561854333075736e-05,
+      "loss": 0.3029,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -131,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.944410411838996e+17,
+  "total_flos": 1.0607056890750566e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null