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:d930a8e932adfd85c65418b547e9309bdc58ead01c636e1c1f0c28d74eb189e1
+oid sha256:6734e529cf3852482915bcffa92f125ff98fc72d48cd7cca868b3c806354fb9e
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32f89ee16895b09ce51335d7b67e9be8c61e6e07cb63d7d1f2467ffbe8ca70e9
+oid sha256:735f851ecfc0ff9e92ebadaa91474b5d310f3ef77a407ab6d38303412d284baf
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ac0a8b470048cdb4c96752220e831580920123f93d34998d2eff45f95da23c8
+oid sha256:5624827400e5ff3446346fe4dc702eac7ea71bf5e585cc6625d60e5201ce73a4
 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": 1.2612242698669434,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.2570828199386597,
+  "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": 4.231,
       "eval_steps_per_second": 0.531,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 1.0415,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.2570828199386597,
+      "eval_runtime": 457.3356,
+      "eval_samples_per_second": 4.22,
+      "eval_steps_per_second": 0.529,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.996145225446195e+16,
+  "total_flos": 2.33018219126784e+16,
   "trial_name": null,
   "trial_params": null
 }