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",
-    "dense",
     "query_key_value",
-    "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:b75aa88eb76a1b04e3f1a5e6a51fd332ae773a643aee281cbf877e8e8dd5f120
+oid sha256:474623393d054bda57a3fb00afe0660c46ded34c58ed4143e5ac3f51d66a3e67
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87cdec6dc1a28c37aaa13cbd988342c66d83d0ff19fbaddb447af157c0596e31
+oid sha256:e114a67525756350ed32d4254f694e4e94834b57548caa333beaa569b73fef61
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b78f5518cedba787787cb66fdb8dc9153feef900a07f6153a2dbab3f3b8f6140
+oid sha256:6b65d909e6c6ee30cc3f6c3c7041369a7088779e6cd2c5df217fb6454aed7be9
 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": 0.0036900369003690036,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.04797047970479705,
+  "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": 0.0036900369003690036,
       "eval_loss": 11.171310424804688,
-      "eval_runtime": 2.0815,
-      "eval_samples_per_second": 55.247,
-      "eval_steps_per_second": 27.864,
+      "eval_runtime": 2.1084,
+      "eval_samples_per_second": 54.543,
+      "eval_steps_per_second": 27.509,
       "step": 1
+    },
+    {
+      "epoch": 0.01845018450184502,
+      "grad_norm": 2.670919895172119,
+      "learning_rate": 5e-05,
+      "loss": 44.6709,
+      "step": 5
+    },
+    {
+      "epoch": 0.03690036900369004,
+      "grad_norm": 2.698882818222046,
+      "learning_rate": 0.0001,
+      "loss": 44.6349,
+      "step": 10
+    },
+    {
+      "epoch": 0.03690036900369004,
+      "eval_loss": 11.152227401733398,
+      "eval_runtime": 0.8795,
+      "eval_samples_per_second": 130.758,
+      "eval_steps_per_second": 65.947,
+      "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": 19289604096.0,
+  "total_flos": 248353652736.0,
   "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:fc009df8789897ddcda59e56590569a6024ec1f887a78dac3853c086a47c5f90
+oid sha256:cc871524a196d7f53a29f717f6c46505922d38455a7dac95e98b69431451083a
 size 6776