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:d3dae2f92b5f85c8c933aa4e093567a01e12118f277729c074bb2ec768f6e653
+oid sha256:4f8cd0879cc70bd36c0b989c637a5a7be59c2c3eb5ee26f22a08cae42b244765
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9483d0253d7ca08d544fe13f4f3893256cd2261811907f002e01e8e46ba054f3
+oid sha256:b1e703ea94df392598c07cd95b11ab1ab66596e416e02afd67e872651ef6f949
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1853f509782e38882f5227487982b49b7f532fd0c75007e3e04a3912c0a8d124
+oid sha256:412c9bed97eb5a08d377271155c33e58f0845b5e57a3849cf1314679188366dd
 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": 0.008208608093687581,
+  "epoch": 0.01094481079158344,
   "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": 65.391,
       "eval_steps_per_second": 32.7,
       "step": 150
+    },
+    {
+      "epoch": 0.008755848633266752,
+      "grad_norm": 4.9402947425842285,
+      "learning_rate": 0.0002,
+      "loss": 9.9399,
+      "step": 160
+    },
+    {
+      "epoch": 0.009303089172845924,
+      "grad_norm": 4.9847307205200195,
+      "learning_rate": 0.0002,
+      "loss": 9.745,
+      "step": 170
+    },
+    {
+      "epoch": 0.009850329712425096,
+      "grad_norm": 6.109457492828369,
+      "learning_rate": 0.0002,
+      "loss": 9.747,
+      "step": 180
+    },
+    {
+      "epoch": 0.010397570252004268,
+      "grad_norm": 4.003091335296631,
+      "learning_rate": 0.0002,
+      "loss": 9.7692,
+      "step": 190
+    },
+    {
+      "epoch": 0.01094481079158344,
+      "grad_norm": 6.683061122894287,
+      "learning_rate": 0.0002,
+      "loss": 9.8331,
+      "step": 200
+    },
+    {
+      "epoch": 0.01094481079158344,
+      "eval_loss": 2.4174001216888428,
+      "eval_runtime": 117.0167,
+      "eval_samples_per_second": 65.76,
+      "eval_steps_per_second": 32.884,
+      "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": 1236772533043200.0,
+  "total_flos": 1630888211251200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null