Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64d9ec370dc378c6fcb3bdc09df8767712ede4b88f54165d82520d7e3d23215
+oid sha256:40b0dad0f47e9185c7141a1b5781e54ad7f03b88fceb62e18911b44f0bf18a57
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de1891be5c0c175283992403ef2258ffb68e9a378708a6a8ebfa0d40e34fbadd
+oid sha256:09d5775b3cf5223b23468d6f24880a63496a878da2596a010e0fe5a52c3b7f9c
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a44e67e7afe750fe86df1f191491956aa5374ed00de2fe34a89e159730d72861
+oid sha256:36f0d7161dd9ad8e601b265301b55ba4312cb15819580d045ab5f9b066af22db
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2754321098327637,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 1.0666666666666667,
+  "best_metric": 1.2672399282455444,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 1.2,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 15.237,
       "eval_steps_per_second": 1.911,
       "step": 800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 0.0002,
+      "loss": 1.0956,
+      "step": 900
+    },
+    {
+      "epoch": 1.2,
+      "eval_loss": 1.2672399282455444,
+      "eval_runtime": 126.5881,
+      "eval_samples_per_second": 15.246,
+      "eval_steps_per_second": 1.912,
+      "step": 900
     }
   ],
   "logging_steps": 100,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.836263099222835e+16,
+  "total_flos": 3.1897626964783104e+16,
   "trial_name": null,
   "trial_params": null
 }