Training in progress, step 260, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abad106b26a177c80a55998c565b87e8d8e322882f0ee0d82dfa1bc33ce78be
+oid sha256:62dd58f5f07e9cfe5165e4ee91690a196110eda1989f229f57e089616cbea092
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15391496ce979fc31bfa4b89cf7a1b8ef5dc88ae859e2b82b3f5c1003f85f097
-size 49846260
+oid sha256:c6e698cb8a9f1b2feee9bca00e0a141b2948dbdee0009ec8f7c9aeccb939cad8
+size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92f080d6a96737273ff3f2c3aa9a0b978c372496e285abadb5ac87a0c88bd369
+oid sha256:0ab3419023c7faeaec921cfbb345173fbd2d7548f26f89a44a67a4f452b92d5d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727d568946636c509efe7945204da61e120d33ba9eb30256473171e8dfb29ed3
+oid sha256:e1b8e5ce2718054463127476242d5f2ee90d1229b9c9ce677374004099bb2fb5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3299902944031058,
+  "epoch": 0.33646069233257847,
   "eval_steps": 386,
-  "global_step": 255,
+  "global_step": 260,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1800,6 +1800,41 @@
       "learning_rate": 9.92873715063483e-05,
       "loss": 0.9571,
       "step": 255
+    },
+    {
+      "epoch": 0.33128437398900035,
+      "grad_norm": 1.0638468265533447,
+      "learning_rate": 9.92804188409717e-05,
+      "loss": 1.0293,
+      "step": 256
+    },
+    {
+      "epoch": 0.33257845357489485,
+      "grad_norm": 0.7083877325057983,
+      "learning_rate": 9.927343266947356e-05,
+      "loss": 0.875,
+      "step": 257
+    },
+    {
+      "epoch": 0.3338725331607894,
+      "grad_norm": 0.7915517091751099,
+      "learning_rate": 9.92664129966038e-05,
+      "loss": 0.8848,
+      "step": 258
+    },
+    {
+      "epoch": 0.3351666127466839,
+      "grad_norm": 0.8054295182228088,
+      "learning_rate": 9.925935982713518e-05,
+      "loss": 0.8981,
+      "step": 259
+    },
+    {
+      "epoch": 0.33646069233257847,
+      "grad_norm": 1.012574553489685,
+      "learning_rate": 9.925227316586316e-05,
+      "loss": 0.8119,
+      "step": 260
     }
   ],
   "logging_steps": 1,
@@ -1819,7 +1854,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8507397878185984e+17,
+  "total_flos": 2.906636646403277e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null