Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6981ec87fa6128720697a1d4d0297b31489f879a22c696a59a9c4d0c9010dc7d
+oid sha256:9f4f4b63ea1fbbc36b23e5e9f52e6f45d350c86d37ee27ac99ad00b41c11e8d9
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a30c5eaa191420933194779f57c2254c08a96b8470ae8baefbc4838f7d1a2f48
+oid sha256:9ae0d611b3147c5045233962cd25536207482629d4b3d7b1ae41d4178ef87c9b
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9a55ac0c992411009853207820ca4f6897afa3f8dc742e986d6f2be555193f7
+oid sha256:4835c70df5f83cc172ef7c6e37bc6d6753f39100497fa148de1cfae0a4d8124d
 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": 0.0008432295692502284,
+  "epoch": 0.0016864591385004567,
   "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": 4.297,
       "eval_steps_per_second": 2.149,
       "step": 15
+    },
+    {
+      "epoch": 0.001011875483100274,
+      "grad_norm": 0.8187156319618225,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.4061,
+      "step": 18
+    },
+    {
+      "epoch": 0.0011243060923336377,
+      "eval_loss": 0.591558575630188,
+      "eval_runtime": 1444.2835,
+      "eval_samples_per_second": 5.186,
+      "eval_steps_per_second": 2.593,
+      "step": 20
+    },
+    {
+      "epoch": 0.0011805213969503198,
+      "grad_norm": 0.8832042217254639,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.7429,
+      "step": 21
+    },
+    {
+      "epoch": 0.0013491673108003653,
+      "grad_norm": 2.113896131515503,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.782,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014053826154170473,
+      "eval_loss": 0.5766608119010925,
+      "eval_runtime": 733.9992,
+      "eval_samples_per_second": 10.204,
+      "eval_steps_per_second": 5.102,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015178132246504111,
+      "grad_norm": 0.7976486086845398,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.1941,
+      "step": 27
+    },
+    {
+      "epoch": 0.0016864591385004567,
+      "grad_norm": 0.8043156266212463,
+      "learning_rate": 0.0,
+      "loss": 2.4673,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016864591385004567,
+      "eval_loss": 0.5740684866905212,
+      "eval_runtime": 1103.3783,
+      "eval_samples_per_second": 6.788,
+      "eval_steps_per_second": 3.394,
+      "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": 3453921578188800.0,
+  "total_flos": 6861790868668416.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null