Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
     "dense_h_to_4h",
+    "query_key_value",
     "dense_4h_to_h",
     "dense"
   ],

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dde000f1add6f4709f738b159e72672b64592bef3fef5faf17a69994e23002f
+oid sha256:6cc2f36fedd765e5d1f9b570d28a00c7d79ecc2fcfdd3d3f929b9becf9f87a8a
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c58ee35216f334a95be62e621245735218bee02ee61a73df90b180fc4b8fb743
+oid sha256:0a51298471d8824e62b642ff7fc8903a12092fd82e1f4d435816512347109e7a
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fdaa60a3ae0f613f863964ef3bdc5e3fbd146397b93279209f02b86c77cb917
+oid sha256:8d6b093e0c4c8b051f5b9e0d212403e2828523b63325a698accc0ed53ad100b1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:d162f01aa043f9810802c3a765a643409e22677d06ecb4e3f1f9962ebaab1f5c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05653710247349823,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2826855123674912,
+  "eval_steps": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.05653710247349823,
       "eval_loss": 11.090624809265137,
-      "eval_runtime": 0.9934,
-      "eval_samples_per_second": 120.8,
-      "eval_steps_per_second": 15.1,
+      "eval_runtime": 0.9998,
+      "eval_samples_per_second": 120.028,
+      "eval_steps_per_second": 15.004,
       "step": 1
+    },
+    {
+      "epoch": 0.22614840989399293,
+      "eval_loss": 11.055208206176758,
+      "eval_runtime": 0.224,
+      "eval_samples_per_second": 535.754,
+      "eval_steps_per_second": 66.969,
+      "step": 4
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 18,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 5,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 163961634816.0,
+  "total_flos": 839097778176.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c761e03f1685e886c6a1533ee19094f9290a8cd630e1909623089da540828139
+oid sha256:4126eb0bef31a4c33a0617eb533bc56a610ff635500150d9490d625c1e8e94ee
 size 6776