Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67fa1a990016c32db2c71bd695712356a2164dec51e53cea96b9be7f501221ea
+oid sha256:30e4a6799efb319c75ef0b774d040d1dd19e439578ceb0a91c02d19628c9d64f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceebbd488559c9a0e405cfb3806f733813a7096df2afcc861eee191d1576e1ad
+oid sha256:761c0841510269facb4c1aac8c3449c6f51dc9943307ccc476720b1cd61de33d
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a701f637c15f3cdfd7666884f9cc5c15b42b346d8a6766fda320843e4c8da6b3
+oid sha256:ebbddc67b5a5d80790a3311604f7069d5cfe6a52d51be3de51787e6a74e494a5
 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": 0.0182337567616848,
+  "epoch": 0.0243116756822464,
   "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": 26.753,
       "eval_steps_per_second": 13.376,
       "step": 150
+    },
+    {
+      "epoch": 0.01944934054579712,
+      "grad_norm": 1.8313133716583252,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 8.7938,
+      "step": 160
+    },
+    {
+      "epoch": 0.020664924329909438,
+      "grad_norm": 1.3177337646484375,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 8.6881,
+      "step": 170
+    },
+    {
+      "epoch": 0.021880508114021757,
+      "grad_norm": 1.4380029439926147,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 8.9628,
+      "step": 180
+    },
+    {
+      "epoch": 0.02309609189813408,
+      "grad_norm": 2.021592140197754,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 8.7991,
+      "step": 190
+    },
+    {
+      "epoch": 0.0243116756822464,
+      "grad_norm": 1.8787529468536377,
+      "learning_rate": 0.0,
+      "loss": 9.1146,
+      "step": 200
+    },
+    {
+      "epoch": 0.0243116756822464,
+      "eval_loss": 2.1915578842163086,
+      "eval_runtime": 129.4737,
+      "eval_samples_per_second": 26.754,
+      "eval_steps_per_second": 13.377,
+      "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": 2.8014486963093504e+16,
+  "total_flos": 3.762410749113139e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null