Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1749ade8c756bb6e89201b8f861f3e6d6c2c5ca34b24ee31b0cdcacfdfb4531b
+oid sha256:bcc321d51cab90609e035f12a406a5bb45ee8d923dc57d4cec27eedb14780d00
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14fe98ab187bdbaa5926a17bc0799e4ece51281bc83c95ac6a3578fa67c6052b
+oid sha256:375d8fc73ac1f566c79172b47db6ed9a30c695c47eaf6914706ecdc1e533c5b3
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c3cef82a77b8c5738ee503d413c0a4f9866d1a3db207e359a45ff19926f30c
+oid sha256:d59909266d557f32bffeea210ce4bd1afe3e0d5ed78b3f0bf0cc9ca4af9ca766
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012829559304637885,
+  "epoch": 0.017106079072850514,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 34.699,
       "eval_steps_per_second": 17.353,
       "step": 150
+    },
+    {
+      "epoch": 0.013684863258280411,
+      "grad_norm": 5.578930377960205,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 7.9683,
+      "step": 160
+    },
+    {
+      "epoch": 0.014540167211922937,
+      "grad_norm": 5.688002109527588,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 8.0386,
+      "step": 170
+    },
+    {
+      "epoch": 0.015395471165565463,
+      "grad_norm": 4.525981903076172,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 7.3559,
+      "step": 180
+    },
+    {
+      "epoch": 0.01625077511920799,
+      "grad_norm": 5.752941608428955,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 7.7123,
+      "step": 190
+    },
+    {
+      "epoch": 0.017106079072850514,
+      "grad_norm": 15.219685554504395,
+      "learning_rate": 0.0,
+      "loss": 8.2222,
+      "step": 200
+    },
+    {
+      "epoch": 0.017106079072850514,
+      "eval_loss": 1.9949531555175781,
+      "eval_runtime": 142.5551,
+      "eval_samples_per_second": 34.534,
+      "eval_steps_per_second": 17.271,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.656857995005133e+16,
+  "total_flos": 3.534314936519885e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null