Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95600bf18b4f30430eec454c6e8a6517cf09bd306be2f0840bd1aad7bbb361ec
+oid sha256:d6277e8699c3ab515b4a95a1a1f3eb9a3e37776355082a4d116ba9f3fe7bfa7d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b8878ebca6c8d0f2b048abb63b4d514505fe3e671fc8a8309b11446a4ffc980
+oid sha256:d2223f3bcf07fa11273593b2598d1a328ec57bbcf7862d75dfd440f440b97cb1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2fbbcfec39a266c55920bef9e4f13dec185fbafadb2891cdbdeaddfff2bb90
+oid sha256:6e39d3bd6aca35d9c2c4af115bc55fc6bc26ea5767dd3a367c3979f22ceabe3d
 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": 0.060144346431435444,
+  "epoch": 0.08019246190858059,
   "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": 31.844,
       "eval_steps_per_second": 15.937,
       "step": 150
+    },
+    {
+      "epoch": 0.06415396952686447,
+      "grad_norm": 1.7491146326065063,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 2.5669,
+      "step": 160
+    },
+    {
+      "epoch": 0.0681635926222935,
+      "grad_norm": 1.4665255546569824,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 2.5827,
+      "step": 170
+    },
+    {
+      "epoch": 0.07217321571772253,
+      "grad_norm": 1.5994822978973389,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 2.6776,
+      "step": 180
+    },
+    {
+      "epoch": 0.07618283881315156,
+      "grad_norm": 1.5955567359924316,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 2.5381,
+      "step": 190
+    },
+    {
+      "epoch": 0.08019246190858059,
+      "grad_norm": 1.6761857271194458,
+      "learning_rate": 0.0,
+      "loss": 2.5529,
+      "step": 200
+    },
+    {
+      "epoch": 0.08019246190858059,
+      "eval_loss": 2.536346673965454,
+      "eval_runtime": 32.996,
+      "eval_samples_per_second": 31.852,
+      "eval_steps_per_second": 15.941,
+      "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": 2.77434637221888e+16,
+  "total_flos": 3.69912849629184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null