Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41901007bffc24fc7ba4b06b9bcf23f31452e5d4a785a47f5a28605786f1fd4b
+oid sha256:7dd3fe0d8ddb00cd9d54d20395d833a781803f9c73d18f3dac543d1bb2421550
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db55cd874351fb09c810dd3ebc54a22a609209da0b08c801071e9bd58b3b44b
+oid sha256:dd82e14cd473ec5edd21b225ef7ebf8b5ebf5069ac6cc7a61ef909d3aaa5b2e8
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9b9a145f461c330c4f2e250c90b749998d50cc3dbf87c28e8a88b623df91449
+oid sha256:988a44fa4d42762c87a90679fb6d9f4aa9dddf28a1bf48d4897d87d467919f8f
 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": 0.01720972923359339,
+  "epoch": 0.02294630564479119,
   "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": 28.026,
       "eval_steps_per_second": 14.013,
       "step": 150
+    },
+    {
+      "epoch": 0.018357044515832952,
+      "grad_norm": 0.0016395815182477236,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.0011,
+      "step": 160
+    },
+    {
+      "epoch": 0.01950435979807251,
+      "grad_norm": 0.0021897745318710804,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.0019,
+      "step": 170
+    },
+    {
+      "epoch": 0.02065167508031207,
+      "grad_norm": 0.0021913335658609867,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.0002,
+      "step": 180
+    },
+    {
+      "epoch": 0.02179899036255163,
+      "grad_norm": 0.002481397008523345,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.0011,
+      "step": 190
+    },
+    {
+      "epoch": 0.02294630564479119,
+      "grad_norm": 0.009852674789726734,
+      "learning_rate": 0.0,
+      "loss": 0.0026,
+      "step": 200
+    },
+    {
+      "epoch": 0.02294630564479119,
+      "eval_loss": 0.0012154106516391039,
+      "eval_runtime": 130.9478,
+      "eval_samples_per_second": 28.026,
+      "eval_steps_per_second": 14.013,
+      "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": 2.880970310025216e+16,
+  "total_flos": 3.84607147524096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null