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:b701eee32a990cd09490efe4034e70c9467c18204b560a31b7d19f0f57856147
+oid sha256:e15a2dcd50865060d9ffb3d7d58fa3fd04a2427bff340114b00965888dabcc6f
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff6613aaca07e5d91dcd312faafc534fe7f0549f95c455741774fd0fec1df4f
+oid sha256:abbb2bda55e7aab355b59c1e1b8ed339c8cc050328c7e4d97e77a4aa4182e059
 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": 1.2627606391906738,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.256902813911438,
+  "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": 4.144,
       "eval_steps_per_second": 0.52,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 1.0419,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.256902813911438,
+      "eval_runtime": 459.9211,
+      "eval_samples_per_second": 4.196,
+      "eval_steps_per_second": 0.526,
+      "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
 }