Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd0ebde736f01e915e6365cac9be20c32259fc6e434ce14d5f9a5609c6c6149
+oid sha256:269bc92048a2a202ac87c945e1cc8cc9a952460c3abed2a111fef89f8bb63612
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:151252e060bf55966d2a123b12fbef6ec770f7d9dea120675db1e72b2df42f99
+oid sha256:969b86ce42d7615fa487bbf65efa06456317188e02bac76b01109dd32c498b5a
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d0fd7dddacd3e53f1224210e1a7004beb37dba9057edac948ebf9ad3bf400f6
+oid sha256:e330c31250ff7fb1f2d3601bdc27866c8168963926e614da3d224b1ce464f50e
 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": 0.1275781416117372,
+  "epoch": 0.1701041888156496,
   "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": 28.75,
       "eval_steps_per_second": 14.404,
       "step": 150
+    },
+    {
+      "epoch": 0.13608335105251967,
+      "grad_norm": 2.079286813735962,
+      "learning_rate": 0.0002,
+      "loss": 6.5172,
+      "step": 160
+    },
+    {
+      "epoch": 0.14458856049330215,
+      "grad_norm": 1.3619401454925537,
+      "learning_rate": 0.0002,
+      "loss": 6.367,
+      "step": 170
+    },
+    {
+      "epoch": 0.15309376993408463,
+      "grad_norm": 0.9493538737297058,
+      "learning_rate": 0.0002,
+      "loss": 6.197,
+      "step": 180
+    },
+    {
+      "epoch": 0.1615989793748671,
+      "grad_norm": 1.0273698568344116,
+      "learning_rate": 0.0002,
+      "loss": 6.6096,
+      "step": 190
+    },
+    {
+      "epoch": 0.1701041888156496,
+      "grad_norm": 1.0309791564941406,
+      "learning_rate": 0.0002,
+      "loss": 6.1175,
+      "step": 200
+    },
+    {
+      "epoch": 0.1701041888156496,
+      "eval_loss": 1.5528790950775146,
+      "eval_runtime": 17.2234,
+      "eval_samples_per_second": 28.74,
+      "eval_steps_per_second": 14.399,
+      "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": 1.6936239819128832e+16,
+  "total_flos": 2.2696397264388096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null