Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c943bb9a943634621468e46c64ea459e5ce06abd54049694b3bb85b13059d57
+oid sha256:15d235dd4f22474b64df8ce0ef64563bab763eee65a3610334d7384324c6d428
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058939e5f0d9ca64017411b6049b141a73228f398e75219ccadd2efac4824409
+oid sha256:5c1e3a91f081758f88234877225e82773ade292679f0d00129a5a4dddcdd21c3
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd8a24a385cb71560f44319d7f96b3f5db0ea1776994de824c1079951b7246d9
+oid sha256:736aa12ab6d5c2752499f4b6cc92b34030f49fdd84c8300d2601eb487bc8024a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
+oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0268442630767822,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.0178813934326172,
+  "best_model_checkpoint": "./outputs/checkpoint-600",
+  "epoch": 0.8,
   "eval_steps": 100,
-  "global_step": 500,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 5.474,
       "eval_steps_per_second": 0.686,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.8815,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.0178813934326172,
+      "eval_runtime": 353.5441,
+      "eval_samples_per_second": 5.459,
+      "eval_steps_per_second": 0.684,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.4137479027061555e+17,
+  "total_flos": 1.6961466390695117e+17,
   "trial_name": null,
   "trial_params": null
 }