Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c55acfc38a8f5ebc538bb4857303d8b69594af69afda35f319690e33df5ff4d
+oid sha256:7e4960a2790675b7d117312eca46352c4ab0c74c4b9dad4342a1f65c3da74724
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e47c8a8fa4418637786695448c02418586e028a8c312f603df0ab085bd6ff0cd
+oid sha256:b5da294e38819b9b42ac4e308e02bfd13e0f39d35863244e428fe5f7adb095c2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3193b984ee6c9c87727ec9e0d931b36e45ba25698e5e55b9b21758f517eb75c
+oid sha256:c5fc8b167d9f76ec96255fcc3f5d78b3cac91bb0ab9af02ea5dd69f279d71afe
 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": 0.01128180057537183,
+  "epoch": 0.015042400767162439,
   "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": 31.652,
       "eval_steps_per_second": 15.829,
       "step": 150
+    },
+    {
+      "epoch": 0.01203392061372995,
+      "grad_norm": 0.9646604061126709,
+      "learning_rate": 0.0002,
+      "loss": 2.4079,
+      "step": 160
+    },
+    {
+      "epoch": 0.012786040652088073,
+      "grad_norm": 1.2489317655563354,
+      "learning_rate": 0.0002,
+      "loss": 2.4017,
+      "step": 170
+    },
+    {
+      "epoch": 0.013538160690446195,
+      "grad_norm": 1.2970277070999146,
+      "learning_rate": 0.0002,
+      "loss": 2.3398,
+      "step": 180
+    },
+    {
+      "epoch": 0.014290280728804318,
+      "grad_norm": 1.0927326679229736,
+      "learning_rate": 0.0002,
+      "loss": 2.2798,
+      "step": 190
+    },
+    {
+      "epoch": 0.015042400767162439,
+      "grad_norm": 1.2469350099563599,
+      "learning_rate": 0.0002,
+      "loss": 2.3109,
+      "step": 200
+    },
+    {
+      "epoch": 0.015042400767162439,
+      "eval_loss": 2.385679244995117,
+      "eval_runtime": 176.8829,
+      "eval_samples_per_second": 31.654,
+      "eval_steps_per_second": 15.83,
+      "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": 2.8113376571817984e+16,
+  "total_flos": 3.759239334356582e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null