Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e529a33a2e67a7a487f373be6de76cbfec062dc66fafef1000196a7d36357a1a
+oid sha256:9f432b6ac988860c5e736c6adcd834f0e25b49e731ea8fde77f658eb5422be37
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7e63e4f8f17892b3724afc5649b94c0ba4c33bc05e3c617f78d1b06efc703e
+oid sha256:b2992de4b83cbffee70b65dadf54ab6ea4b1927a522a0b39deb496c35766d0d8
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54edf57dba3a9923bec7bf6c66a78fd0774a6a561f9a15bd2287923ae584c11c
+oid sha256:ec86ceb8d74fcdb02c7a500faa95db56c309f6ef4f9b4535c3180da9cf2b8f32
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4673335552215576,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.456375241279602,
+  "best_model_checkpoint": "./outputs/checkpoint-700",
+  "epoch": 0.9333333333333333,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 15.532,
       "eval_steps_per_second": 1.948,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 1.2216,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.456375241279602,
+      "eval_runtime": 93.4236,
+      "eval_samples_per_second": 15.531,
+      "eval_steps_per_second": 1.948,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.510926195245056e+16,
+  "total_flos": 4.094671702818816e+16,
   "trial_name": null,
   "trial_params": null
 }