Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_4h_to_h",
     "dense_h_to_4h",
+    "dense",
     "query_key_value",
-    "dense"
+    "dense_4h_to_h"
   ],
   "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 sha256:3fdfe74044799c2d681ddeb8f795fa19b7b298007751b096d62a1d240b818aeb
+oid sha256:e00d8b2572c06729206ac0d5ffd9e3067507921142b1ee6a970cb44a8dee74e9
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130b6d9b8600523f59d7b7c0ffafd7aa1f2bbb4bda6ea545b24188a174453250
+oid sha256:074e65caee7a885b06f613ecbdda741540666ec2e71262a1c1982162c41595cf
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e41786d93022ecb8c77c66c54399ef1b8e95dd48a633f70ac7335d6fde4af8f
+oid sha256:1467d43e650401a3b512d395f9a9d91640b9c9a50e1c12bdce5220b151890407
 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": 0.002793296089385475,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.036312849162011177,
+  "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": 0.002793296089385475,
       "eval_loss": 2.4049742221832275,
-      "eval_runtime": 13.3264,
-      "eval_samples_per_second": 11.331,
-      "eval_steps_per_second": 5.703,
+      "eval_runtime": 13.2901,
+      "eval_samples_per_second": 11.362,
+      "eval_steps_per_second": 5.719,
       "step": 1
+    },
+    {
+      "epoch": 0.013966480446927373,
+      "grad_norm": 2.8598062992095947,
+      "learning_rate": 5e-05,
+      "loss": 9.1267,
+      "step": 5
+    },
+    {
+      "epoch": 0.027932960893854747,
+      "grad_norm": 4.437131881713867,
+      "learning_rate": 0.0001,
+      "loss": 8.7871,
+      "step": 10
+    },
+    {
+      "epoch": 0.027932960893854747,
+      "eval_loss": 2.1106879711151123,
+      "eval_runtime": 12.4419,
+      "eval_samples_per_second": 12.136,
+      "eval_steps_per_second": 6.108,
+      "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": 285280535838720.0,
+  "total_flos": 3708646965903360.0,
   "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 sha256:115376dd420f3056c40be76cdefe89e15ba8cd96b0c572ae21c3204e7eb59b24
+oid sha256:e2da5b5df9750b789e8d32d33105fbbe059f3a5a7a2c0ad93921c3612cff93f8
 size 6776