Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj",
+    "k_proj",
     "up_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
     "gate_proj",
-    "k_proj",
-    "o_proj",
-    "down_proj"
+    "o_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 sha256:21d46f935a81e4377c13855a0d7d2ef83a0b49199df18e00a511ccc227db28f9
+oid sha256:eb72553886d5a34b7e86ee350fc261e3921408e0849b326f96d637d866fa74e5
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670cae13f7683a9f9eeba34650e3d5eadc7467b30669fcb3b8b484c2b13baf93
+oid sha256:5390b689c25e5dd48b5dfb83f352934ec035836e2e6300d303bb627d60150b5b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:f2a3d0f18704952f5e489fd373140093b1ec2232d5123df9941b8b0ec34244b4
 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": 0.0005684240443370755,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007389512576381981,
+  "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": 0.0005684240443370755,
       "eval_loss": 1.7579647302627563,
-      "eval_runtime": 55.0024,
-      "eval_samples_per_second": 13.472,
-      "eval_steps_per_second": 6.745,
+      "eval_runtime": 55.1355,
+      "eval_samples_per_second": 13.44,
+      "eval_steps_per_second": 6.729,
       "step": 1
+    },
+    {
+      "epoch": 0.002842120221685377,
+      "grad_norm": 0.6500794887542725,
+      "learning_rate": 5e-05,
+      "loss": 1.7961,
+      "step": 5
+    },
+    {
+      "epoch": 0.005684240443370754,
+      "grad_norm": 0.509131133556366,
+      "learning_rate": 0.0001,
+      "loss": 1.7088,
+      "step": 10
+    },
+    {
+      "epoch": 0.005684240443370754,
+      "eval_loss": 1.7291897535324097,
+      "eval_runtime": 54.7873,
+      "eval_samples_per_second": 13.525,
+      "eval_steps_per_second": 6.772,
+      "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": 164782292336640.0,
+  "total_flos": 2677712250470400.0,
   "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:c3668fc0ddfecb03e2461c161f27bb891f381f6fe28a219e085dcab710ad7df2
+oid sha256:f7963991be2e31464a0be962e884c2914d891ccdc3c86e1cf841f1f22bed4734
 size 6776