Training in progress, step 2100

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af5eae3b3bfb0c1bb395450fd4f9b7aab2f7072c7dfd321ed9feb4860c9ebe7
+oid sha256:0fd5640309c664961bddb645ea9f395168c8ffb25cac09476f629610ef2821c8
 size 35668592

metrics.json

@@ -39,3 +39,4 @@
 {"Step":1950,"eval_loss":1.8242964745,"eval_runtime":29.4834,"eval_samples_per_second":3.392,"eval_steps_per_second":0.441,"epoch":1.5318146112}
 {"Step":2000,"eval_loss":1.8210265636,"eval_runtime":29.5979,"eval_samples_per_second":3.379,"eval_steps_per_second":0.439,"epoch":1.5710919089}
 {"Step":2050,"eval_loss":1.8052531481,"eval_runtime":29.6699,"eval_samples_per_second":3.37,"eval_steps_per_second":0.438,"epoch":1.6103692066}
+{"Step":2100,"eval_loss":1.8001557589,"eval_runtime":29.4349,"eval_samples_per_second":3.397,"eval_steps_per_second":0.442,"epoch":1.6496465043}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6103692065985862,
+  "epoch": 1.6496465043205029,
   "eval_steps": 50,
-  "global_step": 2050,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -607,6 +607,21 @@
       "eval_samples_per_second": 3.379,
       "eval_steps_per_second": 0.439,
       "step": 2000
+    },
+    {
+      "epoch": 1.6103692065985862,
+      "grad_norm": 0.222442165017128,
+      "learning_rate": 0.00025734652313063716,
+      "loss": 1.829,
+      "step": 2050
+    },
+    {
+      "epoch": 1.6103692065985862,
+      "eval_loss": 1.8052531480789185,
+      "eval_runtime": 29.6699,
+      "eval_samples_per_second": 3.37,
+      "eval_steps_per_second": 0.438,
+      "step": 2050
     }
   ],
   "logging_steps": 50,
@@ -626,7 +641,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.516710641874944e+16,
+  "total_flos": 2.578486235584512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null