Training in progress, step 10

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a7f9067104ba188f808a51c9fa02a0efe307c1fa192f76821eb446bfdce94c
+oid sha256:1a4ee09134693faa7983f5fe727d61f4d6dca23f0ebcf928a221772b3ae314f8
 size 35668592

state.json

@@ -1,108 +1,17 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 0.08,
   "eval_steps": 20,
-  "global_step": 125,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.16,
-      "grad_norm": 0.02559720166027546,
-      "learning_rate": 9.375e-05,
-      "loss": 1.9237,
-      "step": 20
-    },
-    {
-      "epoch": 0.16,
-      "eval_loss": 1.8701050281524658,
-      "eval_runtime": 294.1893,
-      "eval_samples_per_second": 3.399,
-      "eval_steps_per_second": 0.425,
-      "step": 20
-    },
-    {
-      "epoch": 0.32,
-      "grad_norm": 0.07340741157531738,
-      "learning_rate": 7.589285714285714e-05,
-      "loss": 1.8479,
-      "step": 40
-    },
-    {
-      "epoch": 0.32,
-      "eval_loss": 1.7706382274627686,
-      "eval_runtime": 296.242,
-      "eval_samples_per_second": 3.376,
-      "eval_steps_per_second": 0.422,
-      "step": 40
-    },
-    {
-      "epoch": 0.48,
-      "grad_norm": 0.08102620393037796,
-      "learning_rate": 5.803571428571429e-05,
-      "loss": 1.7419,
-      "step": 60
-    },
-    {
-      "epoch": 0.48,
-      "eval_loss": 1.6613901853561401,
-      "eval_runtime": 295.5311,
-      "eval_samples_per_second": 3.384,
-      "eval_steps_per_second": 0.423,
-      "step": 60
-    },
-    {
-      "epoch": 0.64,
-      "grad_norm": 0.07056039571762085,
-      "learning_rate": 4.107142857142857e-05,
-      "loss": 1.674,
-      "step": 80
-    },
-    {
-      "epoch": 0.64,
-      "eval_loss": 1.6176079511642456,
-      "eval_runtime": 295.123,
-      "eval_samples_per_second": 3.388,
-      "eval_steps_per_second": 0.424,
-      "step": 80
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 0.06708831340074539,
-      "learning_rate": 2.3214285714285715e-05,
-      "loss": 1.6024,
-      "step": 100
-    },
-    {
-      "epoch": 0.8,
-      "eval_loss": 1.5983840227127075,
-      "eval_runtime": 296.3017,
-      "eval_samples_per_second": 3.375,
-      "eval_steps_per_second": 0.422,
-      "step": 100
-    },
-    {
-      "epoch": 0.96,
-      "grad_norm": 0.07054605334997177,
-      "learning_rate": 5.357142857142857e-06,
-      "loss": 1.6203,
-      "step": 120
-    },
-    {
-      "epoch": 0.96,
-      "eval_loss": 1.5859812498092651,
-      "eval_runtime": 295.6456,
-      "eval_samples_per_second": 3.382,
-      "eval_steps_per_second": 0.423,
-      "step": 120
-    }
-  ],
+  "log_history": [],
   "logging_steps": 20,
-  "max_steps": 125,
+  "max_steps": 375,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 10,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -110,13 +19,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
+        "should_save": false,
         "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 9518169977733120.0,
+  "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:225e3f04ba656cad0bf2fa42949f5c5d1fb5107f8809a23333b8bb9683442f0f
+oid sha256:d5d622493f1ded4a4395a8a495be5ddb356e13976d1325eca2493ea80f1c746a
 size 5432