Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
-    "dense_4h_to_h",
     "query_key_value",
-    "dense_h_to_4h"
+    "dense_h_to_4h",
+    "dense_4h_to_h",
+    "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 sha256:3c3a74208880d0e8c601e25cee3b5fd3cf05b0fd133e1ab798d3917604847b4b
+oid sha256:2ae43fae577678bad6a328ca6e2cb8877663a1822a35c6731f9011372f3c0d31
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf1dad324c99fc1344a285adc82621d9302b9a1a760cc787d5a3a53b1772f63a
+oid sha256:27241c3daf763fe55b064bd5f8ca9a76fbca37d1f158318468aec66049912c68
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c766b4d62663337935def85e855c51710570c9b8ad32b975ff8ed13c8762f95d
+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": 6.094123741182565e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0007922360863537334,
+  "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": 6.094123741182565e-05,
       "eval_loss": 11.085816383361816,
-      "eval_runtime": 29.3952,
-      "eval_samples_per_second": 235.072,
-      "eval_steps_per_second": 117.536,
+      "eval_runtime": 29.9488,
+      "eval_samples_per_second": 230.727,
+      "eval_steps_per_second": 115.364,
       "step": 1
+    },
+    {
+      "epoch": 0.00030470618705912824,
+      "grad_norm": 0.844322919845581,
+      "learning_rate": 5e-05,
+      "loss": 44.3361,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006094123741182565,
+      "grad_norm": 0.6493428349494934,
+      "learning_rate": 0.0001,
+      "loss": 44.3361,
+      "step": 10
+    },
+    {
+      "epoch": 0.0006094123741182565,
+      "eval_loss": 11.084826469421387,
+      "eval_runtime": 28.9805,
+      "eval_samples_per_second": 238.436,
+      "eval_steps_per_second": 119.218,
+      "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": 747110400.0,
+  "total_flos": 9712435200.0,
   "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:b48698f1820aa06328b841e500a5da5bf2d3ada193607f0f2357ef6c9ca69060
+oid sha256:d631d1d60c7c0bfd9c83c8fe63cfad0d457d54c01741896fb44236e493506112
 size 6776