Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:441fe7c0aeb3a8ca922e3700372d02b6f386faf91257feea2c24d6c0444b25a5
+oid sha256:24390df001b8724384d2c690a86ccba4f13210972ca7484304ecf4bca6d4bb87
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b64c33a9ef37e366a1d24db27393fc1bbd38f4d83b80a5494eca61bfeaaa58
+oid sha256:78f3358ba5b2a98f8641ad719d405695dadb657aaaa4e908654748d58748cf51
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917adaa20d62fb616cea0abf8f6c84a3f7c5f416c800b7d601903d4c10c88a33
+oid sha256:0dcd564b6fd64cf6b2e516ad9d47417c7cc5db0e41ac6fa163353b0dfbf4c062
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020518300828212665,
+  "epoch": 0.02564787603526583,
   "eval_steps": 8,
-  "global_step": 24,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -207,6 +207,48 @@
       "eval_samples_per_second": 28.093,
       "eval_steps_per_second": 14.046,
       "step": 24
+    },
+    {
+      "epoch": 0.02137323002938819,
+      "grad_norm": 3.553572416305542,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3512,
+      "step": 25
+    },
+    {
+      "epoch": 0.022228159230563718,
+      "grad_norm": 7.732612133026123,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4699,
+      "step": 26
+    },
+    {
+      "epoch": 0.023083088431739247,
+      "grad_norm": 6.753180503845215,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.4656,
+      "step": 27
+    },
+    {
+      "epoch": 0.023938017632914775,
+      "grad_norm": 4.395815372467041,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4115,
+      "step": 28
+    },
+    {
+      "epoch": 0.024792946834090304,
+      "grad_norm": 6.47470235824585,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.3571,
+      "step": 29
+    },
+    {
+      "epoch": 0.02564787603526583,
+      "grad_norm": 3.6524059772491455,
+      "learning_rate": 0.0,
+      "loss": 0.4213,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -221,12 +263,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.858027333563187e+16,
+  "total_flos": 2.322534166953984e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null