Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1f1153548a08abc38cd3b5f63054427db73fd12659b0e43adfbb4d8c133d807
+oid sha256:b2e55a44aaf92d249e31e206ac08ef973e30c7697ad6a53ce491eef5a74cea3b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b957375b650b204e121bc8b5b10777228d046d712dfb9af475d5cc5f96ecd93a
+oid sha256:2fc777f2ba4eb3b89cf776190c8b4e7d168e24c585aa3711238ee471d3aa9745
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0704dd557dce4febe99f56d14200e6282ff3f71d203ef70d72c678236f04eb88
+oid sha256:dd8b98e2024de40ef400abf18ba3f39e1a6407c6f5496016292c9acbf052f0dd
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4200090169906616,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.4181303977966309,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 15.55,
       "eval_steps_per_second": 1.95,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.1697,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.4181303977966309,
+      "eval_runtime": 93.16,
+      "eval_samples_per_second": 15.575,
+      "eval_steps_per_second": 1.954,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.43012944795648e+16,
+  "total_flos": 7.01220463147008e+16,
   "trial_name": null,
   "trial_params": null
 }