Training in progress, step 200

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5b9f4dc32699676ed5aa5adc17bcffbf6920fd246efc1c3bbbb6199972d581e
+oid sha256:1f260a8859bd7b12f563e4671818d7103f51af6030a50d5e3520c496388f6baa
 size 35668592

metrics.json

@@ -1,3 +1,4 @@
 {"Step":50,"eval_loss":1.7071695328,"eval_runtime":27.6118,"eval_samples_per_second":3.622,"eval_steps_per_second":0.471,"epoch":0.08}
 {"Step":100,"eval_loss":1.4855879545,"eval_runtime":27.6396,"eval_samples_per_second":3.618,"eval_steps_per_second":0.47,"epoch":0.16}
 {"Step":150,"eval_loss":1.4662159681,"eval_runtime":27.5933,"eval_samples_per_second":3.624,"eval_steps_per_second":0.471,"epoch":0.24}
+{"Step":200,"eval_loss":1.4602761269,"eval_runtime":27.615,"eval_samples_per_second":3.621,"eval_steps_per_second":0.471,"epoch":0.32}

state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.32,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,21 @@
       "eval_samples_per_second": 3.618,
       "eval_steps_per_second": 0.47,
       "step": 100
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.034023039042949677,
+      "learning_rate": 0.00039627659574468084,
+      "loss": 1.5186,
+      "step": 150
+    },
+    {
+      "epoch": 0.24,
+      "eval_loss": 1.466215968132019,
+      "eval_runtime": 27.5933,
+      "eval_samples_per_second": 3.624,
+      "eval_steps_per_second": 0.471,
+      "step": 150
     }
   ],
   "logging_steps": 50,
@@ -56,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8026528503644160.0,
+  "total_flos": 1.205403212832768e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null