Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a6ed06695c4db14bd59e5c8aeb68e38ef6848f2dc1af659b300cd8b57c36e4c
+oid sha256:b319640ac2ae9f4fd71e3238a1e503a4af539aff7cdf83bdfc2fd320a5eb0b2a
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:502d9aa237ca4474d20271d7fb45b1569aa15624cabe8abc86de78b4de3df594
+oid sha256:7b774059a3d91eba9d43657e0eddd567a691032eb2e5cf9263968f6f48551aba
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d6d20de2aca44cf7cdb6eb2a7b0945d14233d0b35daf6c1772715fc68cd541
+oid sha256:738c17c6e6d914a3eabbb6235b37f959587632bfbbcd42656e9153f0dd4ced17
 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": 0.008432295692502284,
+  "epoch": 0.011243060923336379,
   "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": 12.292,
       "eval_steps_per_second": 6.146,
       "step": 150
+    },
+    {
+      "epoch": 0.008994448738669102,
+      "grad_norm": 0.3397560119628906,
+      "learning_rate": 0.0002,
+      "loss": 0.3234,
+      "step": 160
+    },
+    {
+      "epoch": 0.009556601784835922,
+      "grad_norm": 0.4362323582172394,
+      "learning_rate": 0.0002,
+      "loss": 0.3112,
+      "step": 170
+    },
+    {
+      "epoch": 0.010118754831002741,
+      "grad_norm": 0.3360973596572876,
+      "learning_rate": 0.0002,
+      "loss": 0.3057,
+      "step": 180
+    },
+    {
+      "epoch": 0.010680907877169559,
+      "grad_norm": 0.40133044123649597,
+      "learning_rate": 0.0002,
+      "loss": 0.3276,
+      "step": 190
+    },
+    {
+      "epoch": 0.011243060923336379,
+      "grad_norm": 0.4047779142856598,
+      "learning_rate": 0.0002,
+      "loss": 0.2977,
+      "step": 200
+    },
+    {
+      "epoch": 0.011243060923336379,
+      "eval_loss": 0.30774378776550293,
+      "eval_runtime": 609.1932,
+      "eval_samples_per_second": 12.295,
+      "eval_steps_per_second": 6.147,
+      "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": 5.14124601140183e+16,
+  "total_flos": 6.880649602085683e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null