Training in progress, step 3800

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9983cfa75636d2ba6946e3991c3dff6bff54761764447b4cee2dbbc8bf3bf7
+oid sha256:4126a86cedcc673291758a54cbca8d13b3b7d163ea1261dae62eb96e248768df
 size 35668592

metrics.json

@@ -73,3 +73,4 @@
 {"Step":3650,"eval_loss":1.74048388,"eval_runtime":29.3962,"eval_samples_per_second":3.402,"eval_steps_per_second":0.442,"epoch":2.8672427337}
 {"Step":3700,"eval_loss":1.7404457331,"eval_runtime":29.4897,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":2.9065200314}
 {"Step":3750,"eval_loss":1.7380776405,"eval_runtime":29.4462,"eval_samples_per_second":3.396,"eval_steps_per_second":0.441,"epoch":2.9457973291}
+{"Step":3800,"eval_loss":1.7374665737,"eval_runtime":29.4954,"eval_samples_per_second":3.39,"eval_steps_per_second":0.441,"epoch":2.9850746269}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9457973291437547,
+  "epoch": 2.9850746268656714,
   "eval_steps": 50,
-  "global_step": 3750,
+  "global_step": 3800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1117,6 +1117,21 @@
       "eval_samples_per_second": 3.391,
       "eval_steps_per_second": 0.441,
       "step": 3700
+    },
+    {
+      "epoch": 2.9457973291437547,
+      "grad_norm": 0.2325269728899002,
+      "learning_rate": 1.0037823683444865e-05,
+      "loss": 1.7788,
+      "step": 3750
+    },
+    {
+      "epoch": 2.9457973291437547,
+      "eval_loss": 1.7380776405334473,
+      "eval_runtime": 29.4462,
+      "eval_samples_per_second": 3.396,
+      "eval_steps_per_second": 0.441,
+      "step": 3750
     }
   ],
   "logging_steps": 50,
@@ -1136,7 +1151,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.65347630681088e+16,
+  "total_flos": 4.720338670196736e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null