Training in progress, step 300

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69cf6ad416ebd5240085fafc1a17ba4e8e8be0b1bc9626b3c2dc5b27526f0418
+oid sha256:434782c549dbe8ed1dbedf21fe6576551ba71dc5c73bffa488fe9c90b1647456
 size 35668592

metrics.json

@@ -3,3 +3,4 @@
 {"Step":150,"eval_loss":2.2559566498,"eval_runtime":29.4433,"eval_samples_per_second":3.396,"eval_steps_per_second":0.442,"epoch":0.1178318932}
 {"Step":200,"eval_loss":2.1369433403,"eval_runtime":29.6429,"eval_samples_per_second":3.373,"eval_steps_per_second":0.439,"epoch":0.1571091909}
 {"Step":250,"eval_loss":2.0804655552,"eval_runtime":29.5575,"eval_samples_per_second":3.383,"eval_steps_per_second":0.44,"epoch":0.1963864886}
+{"Step":300,"eval_loss":2.0563046932,"eval_runtime":29.4932,"eval_samples_per_second":3.391,"eval_steps_per_second":0.441,"epoch":0.2356637863}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.19638648860958366,
+  "epoch": 0.2356637863315004,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,21 @@
       "eval_samples_per_second": 3.373,
       "eval_steps_per_second": 0.439,
       "step": 200
+    },
+    {
+      "epoch": 0.19638648860958366,
+      "grad_norm": 0.18973998725414276,
+      "learning_rate": 0.0003272251308900523,
+      "loss": 2.0834,
+      "step": 250
+    },
+    {
+      "epoch": 0.19638648860958366,
+      "eval_loss": 2.08046555519104,
+      "eval_runtime": 29.5575,
+      "eval_samples_per_second": 3.383,
+      "eval_steps_per_second": 0.44,
+      "step": 250
     }
   ],
   "logging_steps": 50,
@@ -86,7 +101,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2505234065571840.0,
+  "total_flos": 3148782074265600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null