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:b663e86233bb6951403cc67beeff63e15d4f1e892edb94f5f2efa75296545821
+oid sha256:9e435db4da752918854e894e46fc18d7c271b083637c44be9d1dee819c6c185d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2236a15503bca43c0f5c99a5c1ac509202af69b556205d5fadb1bf9129ac54a
+oid sha256:0f402351a48949d46ea1f3af7e4e3eb5b53499e1b25083283a62f1c71401e42c
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d6c6954105413e254c1dc776a27dd427206924cc5f1ee48db29b4f18851c42
+oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003553028957186001,
+  "epoch": 0.007106057914372002,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 11.634,
       "eval_steps_per_second": 5.817,
       "step": 15
+    },
+    {
+      "epoch": 0.004263634748623201,
+      "grad_norm": 3.084251880645752,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.4886,
+      "step": 18
+    },
+    {
+      "epoch": 0.004737371942914668,
+      "eval_loss": 1.5163520574569702,
+      "eval_runtime": 152.8342,
+      "eval_samples_per_second": 11.634,
+      "eval_steps_per_second": 5.817,
+      "step": 20
+    },
+    {
+      "epoch": 0.004974240540060401,
+      "grad_norm": 2.9578020572662354,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.5724,
+      "step": 21
+    },
+    {
+      "epoch": 0.005684846331497601,
+      "grad_norm": 2.541783094406128,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 1.3204,
+      "step": 24
+    },
+    {
+      "epoch": 0.005921714928643335,
+      "eval_loss": 1.361017107963562,
+      "eval_runtime": 152.84,
+      "eval_samples_per_second": 11.633,
+      "eval_steps_per_second": 5.817,
+      "step": 25
+    },
+    {
+      "epoch": 0.006395452122934802,
+      "grad_norm": 2.4790844917297363,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3091,
+      "step": 27
+    },
+    {
+      "epoch": 0.007106057914372002,
+      "grad_norm": 2.3881053924560547,
+      "learning_rate": 0.0,
+      "loss": 1.448,
+      "step": 30
+    },
+    {
+      "epoch": 0.007106057914372002,
+      "eval_loss": 1.3135907649993896,
+      "eval_runtime": 152.8429,
+      "eval_samples_per_second": 11.633,
+      "eval_steps_per_second": 5.816,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5564154626703360.0,
+  "total_flos": 1.112830925340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null