Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "dense_h_to_4h",
     "dense_4h_to_h",
     "query_key_value",
-    "dense",
-    "dense_h_to_4h"
+    "dense"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d5c4598052e516aee4e0dd2753b56216cb2d958509d81bccf05f60b295550d
+oid sha256:4ca8381dd207192a4b6e0923e7ea38f7940dd581fc09d344fbfeca03232f7f3e
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c073e444693a4d7ff2cca3e10d9077513fad8d33f0aba9bc4e2b0c23840538a2
+oid sha256:1c219b8288517976b571705eb7ae165ad80e19a2adfe2c949b3b47aa4aaf1aa5
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b1d1b309a6677be71a8938daa809110565e16401744df9934ffc4e3496689ba
+oid sha256:97b5dc87a4766b3e3dc1e8f7483cd297cd500798a50cd9b235a3d6b5f24ced20
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005694760820045558,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007403189066059226,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0005694760820045558,
       "eval_loss": 11.059797286987305,
-      "eval_runtime": 4.2052,
-      "eval_samples_per_second": 175.974,
-      "eval_steps_per_second": 87.987,
+      "eval_runtime": 4.4025,
+      "eval_samples_per_second": 168.085,
+      "eval_steps_per_second": 84.043,
       "step": 1
+    },
+    {
+      "epoch": 0.0028473804100227792,
+      "grad_norm": 7.55947732925415,
+      "learning_rate": 5e-05,
+      "loss": 44.2062,
+      "step": 5
+    },
+    {
+      "epoch": 0.0056947608200455585,
+      "grad_norm": 8.039371490478516,
+      "learning_rate": 0.0001,
+      "loss": 44.1306,
+      "step": 10
+    },
+    {
+      "epoch": 0.0056947608200455585,
+      "eval_loss": 11.009163856506348,
+      "eval_runtime": 3.5052,
+      "eval_samples_per_second": 211.116,
+      "eval_steps_per_second": 105.558,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 14467203072.0,
+  "total_flos": 197718441984.0,
   "train_batch_size": 2,
   "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:c3cff6edc4bc49bb55a5d819b9bb3dae71a53266424ce7f014ec670c2a952087
+oid sha256:4287f29f524264e96299b942bc4d65781aa8556bf6b22c90b20c8a4f5bf318a4
 size 6776