Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d830c36e96ef39ed8b80e4474520f8fc9b03d03a7b4f3be69a26479ce6bc418
+oid sha256:9d3d730ad81ed703ebdbed4f4a8da72207c28104bde39c7a2c6b78d7fa3b7ee0
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e797cbd6b2526bae2f882f9e2822c24d3d0caa2e71e3e71431b8e59140f40d
+oid sha256:14dcf136e4ff08fce5e782e80b80922e5a68ded767f7bd51c61fbf4c53e385ac
 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:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 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": 27.866,
       "eval_steps_per_second": 13.961,
       "step": 150
+    },
+    {
+      "epoch": 0.13608335105251967,
+      "grad_norm": 2.175602436065674,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 6.5291,
+      "step": 160
+    },
+    {
+      "epoch": 0.14458856049330215,
+      "grad_norm": 1.4054992198944092,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 6.3717,
+      "step": 170
+    },
+    {
+      "epoch": 0.15309376993408463,
+      "grad_norm": 0.9893892407417297,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 6.2178,
+      "step": 180
+    },
+    {
+      "epoch": 0.1615989793748671,
+      "grad_norm": 1.1106479167938232,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 6.6456,
+      "step": 190
+    },
+    {
+      "epoch": 0.1701041888156496,
+      "grad_norm": 1.054567575454712,
+      "learning_rate": 0.0,
+      "loss": 6.1472,
+      "step": 200
+    },
+    {
+      "epoch": 0.1701041888156496,
+      "eval_loss": 1.5651204586029053,
+      "eval_runtime": 17.837,
+      "eval_samples_per_second": 27.751,
+      "eval_steps_per_second": 13.904,
+      "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