Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cf4e00b8099408aafed876b80738e0c42553c008722bd4afdb56d4cba414963
+oid sha256:67ce3faec7f7e1a79f00b8dfdced98692bf54047a0ff9fd3ad96c9f8d366eb0e
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f8aae0c08dceba9a9a03bb4c91c78adfa4c4273a9d915d9802c0998237297da
+oid sha256:b05438ad0df3fd35feb336af17b2727b5cc735968a239d3fca95b35ba3f8d2de
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827a56bfe4c6afb079f57f26558d3affe524c442face20728497852fc2f042de
+oid sha256:28934f12b9c2a11845de68b32f74934b975c4c0d6f33f18c99b741ee821528e0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.936788558959961,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.5625,
+  "best_metric": 1.929431438446045,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.7045454545454546,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 27.791,
       "eval_steps_per_second": 3.483,
       "step": 1100
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0002,
+      "loss": 2.0684,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7,
+      "eval_loss": 1.929431438446045,
+      "eval_runtime": 53.7712,
+      "eval_samples_per_second": 27.747,
+      "eval_steps_per_second": 3.478,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.3312013733376e+16,
+  "total_flos": 3.634363552684032e+16,
   "trial_name": null,
   "trial_params": null
 }