Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50d992ba5edf2df73687974a690a79fa8f263ef680c0b437615ccb8fffbeb7b3
+oid sha256:f5db22bc2322145e6b64fed6d219aad7081630a302322855043a95d08d3b300a
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:940095018d05a25649ffb47da852e89f7555af35b3d08342f9bd3cc29e31f5cc
+oid sha256:86806ff980ae9a6107589b972ffa989afe38a08a1acdc84a3efcaec05294a831
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f85e4abb78831eb1bde44d2a42765725c100a0771b8e7eee558b5dbbd2981ee
+oid sha256:3e2d51a2182c594cb223abc4747fbe69b20a40a4dbbb3d5728b59aa9a1c00b84
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3538635969161987,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.3417681455612183,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.3333333333333333,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 12.726,
       "eval_steps_per_second": 1.596,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 1.0936,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.3417681455612183,
+      "eval_runtime": 151.5959,
+      "eval_samples_per_second": 12.731,
+      "eval_steps_per_second": 1.596,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.738831856027648e+16,
+  "total_flos": 6.377953518913536e+16,
   "trial_name": null,
   "trial_params": null
 }