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:d4c11d5c1c990abf7d8314fea9f0075071fc70c09322b6aaf30e13704ffba818
+oid sha256:9167f5490b690afc521f0cb72836025d5dcafcc9e7b0cda3c0ffbb83279cf75b
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ca978b685fb676166bf8dc89b64f1e2d1105fc3bb42d39ad15826c823c369e2
+oid sha256:356b8a8547be4e42aeec8af622914c9a56aff52b6a0faece0c79961887c236d6
 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:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 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": 26.799,
       "eval_steps_per_second": 13.399,
       "step": 150
+    },
+    {
+      "epoch": 0.01944934054579712,
+      "grad_norm": 1.7567479610443115,
+      "learning_rate": 0.0002,
+      "loss": 8.761,
+      "step": 160
+    },
+    {
+      "epoch": 0.020664924329909438,
+      "grad_norm": 1.3298070430755615,
+      "learning_rate": 0.0002,
+      "loss": 8.6619,
+      "step": 170
+    },
+    {
+      "epoch": 0.021880508114021757,
+      "grad_norm": 1.3300223350524902,
+      "learning_rate": 0.0002,
+      "loss": 8.9402,
+      "step": 180
+    },
+    {
+      "epoch": 0.02309609189813408,
+      "grad_norm": 1.8174155950546265,
+      "learning_rate": 0.0002,
+      "loss": 8.7659,
+      "step": 190
+    },
+    {
+      "epoch": 0.0243116756822464,
+      "grad_norm": 1.6860878467559814,
+      "learning_rate": 0.0002,
+      "loss": 9.0848,
+      "step": 200
+    },
+    {
+      "epoch": 0.0243116756822464,
+      "eval_loss": 2.1836845874786377,
+      "eval_runtime": 129.2197,
+      "eval_samples_per_second": 26.807,
+      "eval_steps_per_second": 13.404,
+      "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