Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b679e0c75a8643214afae860a6ac9005a9f9a75a2f2f5c537c9e222964481a43
+oid sha256:624b055197f3606c6eb4eb68495cba1cb3612390711cd369d9751c0de46decb1
 size 12595704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c72c670e793ff2c7d8d8e295289dbdf4f7506db32a0c57072c1daae89d0c0167
+oid sha256:02250fadcda502c739eeb1c85cb88d86f2afd595b0bc32fbddb661b3038abb37
 size 25222341

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78e602e0905f2f4cd3eaf79c0118d57897fc5559f4a434cf3e4f71108013ea94
+oid sha256:2bd2949875db2332096831c954b2d0057ba1bf8d4b09f9a5ce64cdf0ae619b0a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0996404886245728,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.098088026046753,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.3333333333333333,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 10.346,
       "eval_steps_per_second": 1.297,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.9489,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.098088026046753,
+      "eval_runtime": 186.2211,
+      "eval_samples_per_second": 10.364,
+      "eval_steps_per_second": 1.3,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.2719281132194202e+17,
+  "total_flos": 1.413720701218898e+17,
   "trial_name": null,
   "trial_params": null
 }