Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "k_proj",
     "o_proj",
-    "down_proj",
-    "gate_proj",
+    "v_proj",
     "up_proj",
-    "k_proj",
-    "v_proj"
+    "gate_proj",
+    "down_proj"
   ],
   "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 sha256:88680db69abc2dce1f385b2140190d10c69c27d75331f154b617e54fe45e9fd7
+oid sha256:82eae30cad5b29368e050d7444c6bfd96fc319cdcfe12aa85434f9d323a111e8
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9c211295e852a6f1f11dc71e81a19518b64c1d12a5ff6ba8fe56fd4683bb85
+oid sha256:b320bdff87bb8823ee9465f66629e25f23795394634c196167930d877c317f02
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1e11f532e67beeeeeaf9c2ddf2a6ed5e116ee96012aebc5d0634822ecd38f7
+oid sha256:311ebeed04d0f61c03df33f8b12e2b83d96fcfcaa46ade7e86d87e96b5020def
 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": 0.00025552574421873004,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0033218346748434906,
+  "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": 0.00025552574421873004,
       "eval_loss": 0.44080615043640137,
-      "eval_runtime": 169.8256,
-      "eval_samples_per_second": 9.704,
-      "eval_steps_per_second": 4.852,
+      "eval_runtime": 163.4805,
+      "eval_samples_per_second": 10.081,
+      "eval_steps_per_second": 5.04,
       "step": 1
+    },
+    {
+      "epoch": 0.0012776287210936501,
+      "grad_norm": 0.6050224304199219,
+      "learning_rate": 5e-05,
+      "loss": 0.3806,
+      "step": 5
+    },
+    {
+      "epoch": 0.0025552574421873002,
+      "grad_norm": 0.3790658712387085,
+      "learning_rate": 0.0001,
+      "loss": 0.3812,
+      "step": 10
+    },
+    {
+      "epoch": 0.0025552574421873002,
+      "eval_loss": 0.36030489206314087,
+      "eval_runtime": 168.9311,
+      "eval_samples_per_second": 9.755,
+      "eval_steps_per_second": 4.878,
+      "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": 48109103087616.0,
+  "total_flos": 607377426481152.0,
   "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:e5b43cc81ed7669cb447eaef30701e25b4e423456398def5c7248a4c1637259f
+oid sha256:2059fc755bc583eee55ac16f31d45c41979b1359a41835e2f1258a5c698396cc
 size 6776