Training in progress, step 700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d29af4f759bc67cce2aefb78d310ec98a8df9e207e038573f4f3d7653672bcd
+oid sha256:fa5909f0a9994c40cc63ab73d78a9b828af0471a2a3983463378f2ac8e9d44a7
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eb11725e58f643998cf25b803d6f0624be48d97c7c35d98243264498a87855b
+oid sha256:ff7c11257e50ab93e4ac86192837132e542b18318988b37567f67604518ac8db
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:736aa12ab6d5c2752499f4b6cc92b34030f49fdd84c8300d2601eb487bc8024a
+oid sha256:6ff68bc1413209b0087a6b2cf9fed69a476793fcd5e396a94dfdeb01c5356ea6
 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": 1.0176780223846436,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8,
+  "best_metric": 1.0153926610946655,
+  "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": 5.468,
       "eval_steps_per_second": 0.686,
       "step": 600
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 0.0002,
+      "loss": 0.8786,
+      "step": 700
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.0153926610946655,
+      "eval_runtime": 353.3606,
+      "eval_samples_per_second": 5.462,
+      "eval_steps_per_second": 0.685,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.6961466390695117e+17,
+  "total_flos": 1.9797272643079373e+17,
   "trial_name": null,
   "trial_params": null
 }