Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ae4f64e3e27b703c51d2a4228a527670c033261a35d7a2b34afd0c6d53a42a
+oid sha256:d08e7548567d86124e4fbba8ce76106934c9f547f066151fd3de78ad0a08f37e
 size 241895584

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c6cedb706163a8260631ac2c77ca7ca0e8af370dafc6eeaaa3117b16928be6b
+oid sha256:b047ebdc69a8b57ad351cbb5ff17e2f8f5c0ec0e954a5073a15faec4d0d52a7a
 size 123396357

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:746292b776e70f12d4c33e6be6cb963a26635d1670de1973ab3a32c9a8c60a0d
+oid sha256:18c428de3d337e366235ac71e21db0dee376009a830ae7e06fe3af1eec7f3a00
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54ccbc889d1c38a21ecce182cf4adbf347b91b44d80537c158dc7c0e1f7ad46f
+oid sha256:1f94ebdc28f5491fc51fc2ecbab5d9e2e3ba6be348d92d880d778a28fcd2cbce
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 800,
-  "best_metric": 0.613548219203949,
-  "best_model_checkpoint": "outputs/checkpoint-800",
-  "epoch": 0.6304176516942475,
+  "best_global_step": 1000,
+  "best_metric": 0.6114270687103271,
+  "best_model_checkpoint": "outputs/checkpoint-1000",
+  "epoch": 0.7880220646178093,
   "eval_steps": 200,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -264,6 +264,70 @@
       "eval_samples_per_second": 10.206,
       "eval_steps_per_second": 5.108,
       "step": 800
+    },
+    {
+      "epoch": 0.6501182033096927,
+      "grad_norm": 0.32342788577079773,
+      "learning_rate": 1.8285510166487152e-05,
+      "loss": 0.646,
+      "step": 825
+    },
+    {
+      "epoch": 0.6698187549251379,
+      "grad_norm": 0.40992236137390137,
+      "learning_rate": 1.3572519804629536e-05,
+      "loss": 0.6419,
+      "step": 850
+    },
+    {
+      "epoch": 0.6895193065405831,
+      "grad_norm": 0.36296817660331726,
+      "learning_rate": 9.517294753398064e-06,
+      "loss": 0.5924,
+      "step": 875
+    },
+    {
+      "epoch": 0.7092198581560284,
+      "grad_norm": 0.28041669726371765,
+      "learning_rate": 6.1506977240444074e-06,
+      "loss": 0.6353,
+      "step": 900
+    },
+    {
+      "epoch": 0.7289204097714737,
+      "grad_norm": 0.3714691996574402,
+      "learning_rate": 3.4983505527688586e-06,
+      "loss": 0.6522,
+      "step": 925
+    },
+    {
+      "epoch": 0.7486209613869188,
+      "grad_norm": 0.40027645230293274,
+      "learning_rate": 1.580439203075812e-06,
+      "loss": 0.6376,
+      "step": 950
+    },
+    {
+      "epoch": 0.7683215130023641,
+      "grad_norm": 0.3009302318096161,
+      "learning_rate": 4.115601384029666e-07,
+      "loss": 0.6226,
+      "step": 975
+    },
+    {
+      "epoch": 0.7880220646178093,
+      "grad_norm": 0.43267834186553955,
+      "learning_rate": 6.092342209607083e-10,
+      "loss": 0.6157,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7880220646178093,
+      "eval_loss": 0.6114270687103271,
+      "eval_runtime": 104.2904,
+      "eval_samples_per_second": 10.25,
+      "eval_steps_per_second": 5.13,
+      "step": 1000
     }
   ],
   "logging_steps": 25,
@@ -278,12 +342,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.827027177282765e+16,
+  "total_flos": 4.773356252585165e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null