Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9ea19a14ed11592de0c6e2dcae9ced556eddf3c0b0b13211afc010d0f5b9d7
+oid sha256:a6eb24d9a2fab8b73c0bafe62e61b413d19fcc20d3473bde2091ba296af926d0
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d998e0791bba6243f188e62cbf6a59b367f43d52b8d76fc2a22133120e6a110a
+oid sha256:51b088d65cf61007d41d4d9d563bdad313e02732aadda5577049dd0517eed0fa
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f409da3dcc8d395470a77e66ec88ee64f503054e416b434d299f2eda08c45ccd
+oid sha256:17f0578d675217093ff9e12f497b1c195d79c069c4b5909c34203361b5c19bb4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
+oid sha256:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.250588297843933,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 2.0,
+  "best_metric": 1.2468171119689941,
+  "best_model_checkpoint": "./outputs/checkpoint-1600",
+  "epoch": 2.1333333333333333,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 15.282,
       "eval_steps_per_second": 1.916,
       "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 1.0763,
+      "step": 1600
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.2468171119689941,
+      "eval_runtime": 126.0777,
+      "eval_samples_per_second": 15.308,
+      "eval_steps_per_second": 1.919,
+      "step": 1600
     }
   ],
   "logging_steps": 100,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.317568138938368e+16,
+  "total_flos": 5.671234750998528e+16,
   "trial_name": null,
   "trial_params": null
 }