Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af35a222312aef679fe5aae00dac30e19df7d435406cc8032ec285370ec6fdf4
+oid sha256:9431104886add9484e9a908263c404a811f2182da11c5c59ba22d999f155bd12
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b09c6cfa2eeeda68b57107706bed3b6c783643f9a1e6d3a4b2b82032f3e2d9
+oid sha256:61c61a56239e70904df54c63aefaa5ca175622aefee4045a39933a01fffff9e0
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec23ca2803e86ffe0ecabecaee4205cf8d5ab9995615c74625e51baf4b0bcb5b
+oid sha256:b44c27a4571e6eb1a7ee928ce7b6d2caa61e9848f87f288e6907748065a8b638
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4751445055007935,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.441214680671692,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 12.448,
       "eval_steps_per_second": 1.561,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.2006,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.441214680671692,
+      "eval_runtime": 151.6424,
+      "eval_samples_per_second": 12.727,
+      "eval_steps_per_second": 1.596,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6376101833687040.0,
+  "total_flos": 1.273189776703488e+16,
   "trial_name": null,
   "trial_params": null
 }