Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f057a2197471b7f639c5d813d1ef9d5a5b63c52d0d36065e3250d176d14265b
+oid sha256:82b5d62c62e1cb61cecd486c3cd33e2ac4dee102b9ff2ee58d908249f6bb7ec5
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a2ea44a05c9c444d9672d07afc049e2e779193cf3dfa0afded237eea3043f2
+oid sha256:91cddd1e0059c07092f6923eb4c8201a8ced613a6c428b10fc4a6703cce0733a
 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": 1.4184046983718872,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.4164544343948364,
+  "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": 15.56,
       "eval_steps_per_second": 1.952,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 1.1698,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.4164544343948364,
+      "eval_runtime": 93.4373,
+      "eval_samples_per_second": 15.529,
+      "eval_steps_per_second": 1.948,
+      "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
 }