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:f477210cd0186301a35dc15e99a715f4fb6353158b38d0b7939525a1ce161c46
+oid sha256:b701eee32a990cd09490efe4034e70c9467c18204b560a31b7d19f0f57856147
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051a11b8e2cafed50674564fb5e2350c35f752d2b9f5d33fd97d8165265ff007
+oid sha256:4ff6613aaca07e5d91dcd312faafc534fe7f0549f95c455741774fd0fec1df4f
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab796cb22d1f99e1a64175a4124c719d63af93d54a8325b07b8b479b7426620f
+oid sha256:3ac0a8b470048cdb4c96752220e831580920123f93d34998d2eff45f95da23c8
 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": 1.274288535118103,
-  "best_model_checkpoint": "./outputs/checkpoint-500",
-  "epoch": 0.6666666666666666,
+  "best_metric": 1.2627606391906738,
+  "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": 4.131,
       "eval_steps_per_second": 0.518,
       "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0002,
+      "loss": 1.0502,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.2627606391906738,
+      "eval_runtime": 465.7624,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 0.52,
+      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.6636259895410688e+16,
+  "total_flos": 1.996145225446195e+16,
   "trial_name": null,
   "trial_params": null
 }