Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34dff9b81c5a01b4e58e26af9ff3d94726dcf3fbfd8df467a5b2b3ca91f55c31
+oid sha256:dc223b1f7a1f91499c6fce1d9c7b9777a001cfe758ed08b366efeaf34c67c8e2
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5055a21ea311851fcf516b2248e5a06f15c0402c2bc16301d1bcb3390e648c
+oid sha256:a3d3f7959fdeb60dff6f4ccbb618b2866aed60776f61dc00bb8c8a81aaf08a53
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0baef92f29724762003fb5a5e60a068b25f0dcaabdd1738999cdd71657bcdcc2
+oid sha256:a68ff03bce9d2cb56819b178dca5e85d0900211ca081621ebca96dbb0b14518a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c07f2bd0b59249f39d32534072619919b7f36bea7e48a381937d6e08de9e282
+oid sha256:a885f4d2be962a847ad04a40c0900fb3136769296a180ac63536e4bcec83f515
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7052733743125202,
+  "epoch": 0.7117437722419929,
   "eval_steps": 386,
-  "global_step": 545,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3838,6 +3838,41 @@
       "learning_rate": 9.589264199393776e-05,
       "loss": 1.0543,
       "step": 545
+    },
+    {
+      "epoch": 0.7065674538984148,
+      "grad_norm": 0.7370772361755371,
+      "learning_rate": 9.587626204220171e-05,
+      "loss": 0.8853,
+      "step": 546
+    },
+    {
+      "epoch": 0.7078615334843092,
+      "grad_norm": 0.7535960674285889,
+      "learning_rate": 9.585985089885552e-05,
+      "loss": 0.8419,
+      "step": 547
+    },
+    {
+      "epoch": 0.7091556130702038,
+      "grad_norm": 0.7049685716629028,
+      "learning_rate": 9.584340857505722e-05,
+      "loss": 0.8282,
+      "step": 548
+    },
+    {
+      "epoch": 0.7104496926560984,
+      "grad_norm": 0.7157800197601318,
+      "learning_rate": 9.58269350819861e-05,
+      "loss": 0.8282,
+      "step": 549
+    },
+    {
+      "epoch": 0.7117437722419929,
+      "grad_norm": 0.7660270929336548,
+      "learning_rate": 9.581043043084259e-05,
+      "loss": 0.9006,
+      "step": 550
     }
   ],
   "logging_steps": 1,
@@ -3857,7 +3892,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.092757585729946e+17,
+  "total_flos": 6.148654444314624e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null