Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bebdbcfd778eb61aa33255c7b6e4f5e98776953d08f078cd9dc6e72acfee2e1
+oid sha256:bbac07c54af71b1523ccefd010ed4fa8f29f41bccaf7f00fb9a8c48c135a05e9
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4a822114554dfcdc0639a75d789eb568e9bf7e20f0408f42575fe5310fb21f
+oid sha256:0c288537365d7d6c7fdaf368f5b2b898c07485a5f0c1b7a22ef52e77417be877
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f5e974d9a5182c0220936ec7ed26d0817f1e2d86d0852117aad18130cf4452
+oid sha256:2780285db9dcbedfa558cb2cf6f7a6604eabefd92d06bfa1eb702ad38e4c4f00
 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": 1.0260452032089233,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.0152662992477417,
+  "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": 2.643,
       "eval_steps_per_second": 0.331,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 0.8496,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.0152662992477417,
+      "eval_runtime": 732.4802,
+      "eval_samples_per_second": 2.635,
+      "eval_steps_per_second": 0.33,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 100,
-  "total_flos": 1.2948397906255872e+17,
+  "total_flos": 1.5536474436108288e+17,
   "trial_name": null,
   "trial_params": null
 }