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:a0e59dff9775d0c98ba9d6624c5427cb0e2272b6f3226907c2f0dc95800d008f
+oid sha256:45c4ed7ec8b6469cc31c1abe9f35eceace7d3b5a392a7979810f960551716c6c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83056bfb54bd306db6f4f3662b00b5d3faa94a811c20d2fdb626fa40639fd7f7
+oid sha256:4d6fec20bb78e75973da53e5177b6b3bf9b934cdf94a06c56b3e55d05ff2218f
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33d0b48a8cae2e325fd3674077c1140034bb2089e3367f6296e12753d18b64ac
+oid sha256:22539dd0b6c660ccb804ae986f7b41413fb450c8cb78a061ce381c0a55c82fe7
 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": 1.3670101165771484,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.3592472076416016,
+  "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": 30.607,
       "eval_steps_per_second": 3.839,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 1.4583,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.3592472076416016,
+      "eval_runtime": 47.3317,
+      "eval_samples_per_second": 30.656,
+      "eval_steps_per_second": 3.845,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.017745003184128e+16,
+  "total_flos": 3.353119873302528e+16,
   "trial_name": null,
   "trial_params": null
 }