Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "dense",
     "dense_h_to_4h",
-    "dense_4h_to_h",
     "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 sha256:3d72389f132b4acdda498a88a0dfd156ade2325cf1b0af0792a60a72b5df5577
+oid sha256:ba198556ebcb3b50ae49143d1e9d0870a7cea8ea86845087925b5a4db49a3ce3
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7732af4552aa16eda415815cc0f6ea7f835d18982e7f864a68caba07b0954363
+oid sha256:5a603c8af1846e5da17ccc562e87815f56e20b933a2f6b2a2bf8db62361540d6
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77bba18256fafda32f39805d8a79bd94ed0adb267c51253610b58903e54ff6d3
+oid sha256:adc65900b1800458289c8c21bab3eeedd0bb320c47305aa0de9c35ef282f5293
 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": 0.0014035087719298245,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.018245614035087718,
+  "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": 0.0014035087719298245,
       "eval_loss": 11.166300773620605,
-      "eval_runtime": 1.6754,
-      "eval_samples_per_second": 179.061,
-      "eval_steps_per_second": 89.531,
+      "eval_runtime": 1.7265,
+      "eval_samples_per_second": 173.758,
+      "eval_steps_per_second": 86.879,
       "step": 1
+    },
+    {
+      "epoch": 0.007017543859649123,
+      "grad_norm": 4.016921043395996,
+      "learning_rate": 5e-05,
+      "loss": 44.6916,
+      "step": 5
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "grad_norm": 4.227939605712891,
+      "learning_rate": 0.0001,
+      "loss": 44.5734,
+      "step": 10
+    },
+    {
+      "epoch": 0.014035087719298246,
+      "eval_loss": 11.1311674118042,
+      "eval_runtime": 1.3958,
+      "eval_samples_per_second": 214.926,
+      "eval_steps_per_second": 107.463,
+      "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": 9644802048.0,
+  "total_flos": 125382426624.0,
   "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:b88dd99886236c1b7ebd6990f503e28421dc576d9c590b4f65c20f3b3f4b4a24
+oid sha256:7b06c9887a116b251f4b3f12db8afdb72c1672cd3025d406b66681e897ff9542
 size 6776