Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cead8642df60f1a5ffbdbffbb252762321d5d0479ed722b82e9ae8186a31be7e
+oid sha256:d0b3ddb24075672017937ed3bc3c47497af8691215538fe35cbcec9f3c590f24
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a9def7dd7f9552aa09238e22aa685d5b21066cfdbafe738b1aea76f22053c55
+oid sha256:e183901845d2c7224b7e38ffba813ab5debef0ea6910db9a55e90175149f9479
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:238d91f489adef697523368efde471946ec4962b97178a433b03cee9c743141e
+oid sha256:1094888e690d760f5dc6beb93863816b44facd96c60f74f3826e1336734dec25
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
+oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006291591046581972,
+  "epoch": 0.009437386569872959,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 50.267,
       "eval_steps_per_second": 25.133,
       "step": 26
+    },
+    {
+      "epoch": 0.006533575317604356,
+      "grad_norm": 3.0940749645233154,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 6.2322,
+      "step": 27
+    },
+    {
+      "epoch": 0.006775559588626739,
+      "grad_norm": 2.8410699367523193,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 5.9674,
+      "step": 28
+    },
+    {
+      "epoch": 0.007017543859649123,
+      "grad_norm": 3.7612247467041016,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 6.2043,
+      "step": 29
+    },
+    {
+      "epoch": 0.007259528130671506,
+      "grad_norm": 2.866365671157837,
+      "learning_rate": 0.0001,
+      "loss": 5.4941,
+      "step": 30
+    },
+    {
+      "epoch": 0.00750151240169389,
+      "grad_norm": 3.132918119430542,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 5.7106,
+      "step": 31
+    },
+    {
+      "epoch": 0.007743496672716273,
+      "grad_norm": 3.546154499053955,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.2481,
+      "step": 32
+    },
+    {
+      "epoch": 0.007985480943738656,
+      "grad_norm": 3.2497243881225586,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 5.8963,
+      "step": 33
+    },
+    {
+      "epoch": 0.00822746521476104,
+      "grad_norm": 2.7139110565185547,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.1744,
+      "step": 34
+    },
+    {
+      "epoch": 0.008469449485783424,
+      "grad_norm": 3.148625373840332,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 5.7334,
+      "step": 35
+    },
+    {
+      "epoch": 0.008711433756805808,
+      "grad_norm": 3.692917823791504,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 5.1302,
+      "step": 36
+    },
+    {
+      "epoch": 0.00895341802782819,
+      "grad_norm": 3.0616631507873535,
+      "learning_rate": 4.7750143528405126e-05,
+      "loss": 5.4077,
+      "step": 37
+    },
+    {
+      "epoch": 0.009195402298850575,
+      "grad_norm": 2.9874343872070312,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 5.458,
+      "step": 38
+    },
+    {
+      "epoch": 0.009437386569872959,
+      "grad_norm": 3.2835030555725098,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 6.9377,
+      "step": 39
+    },
+    {
+      "epoch": 0.009437386569872959,
+      "eval_loss": 1.4466110467910767,
+      "eval_runtime": 34.6976,
+      "eval_samples_per_second": 50.148,
+      "eval_steps_per_second": 25.074,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1007681745715200.0,
+  "total_flos": 1492861845504000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null