Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "v_proj",
     "up_proj",
+    "o_proj",
     "gate_proj",
-    "v_proj",
     "q_proj",
-    "down_proj",
-    "k_proj",
-    "o_proj"
+    "k_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 sha256:145571ae72093a71e49016117fedfae2154fe8ea4d814c8020f8c6b1f481de86
+oid sha256:155d439e73369b0d5d760de677bc7ce14fe41909c724ac4b88fe795a3872ec26
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0021b1f93f438bfc020ee060b31c9ad58e73663ab45b305a892c981db4ca5b46
+oid sha256:038b5c55e7840ce6802d7753d2c85be5de892c39bcc895b99fa0a8eaa1ef080e
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9673d22f265ed23c9ac8fe3534732259b5ca12d0692ce0ea4ceef5963b1b4fd
+oid sha256:12beed8359fe142c0bd78cf5e499f7058c2c13c901dc109a35a05e5a60f3c080
 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": 0.0011577424023154848,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.015050651230101303,
+  "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": 0.0011577424023154848,
       "eval_loss": 0.5778371095657349,
-      "eval_runtime": 23.16,
-      "eval_samples_per_second": 15.717,
-      "eval_steps_per_second": 7.858,
+      "eval_runtime": 23.1824,
+      "eval_samples_per_second": 15.702,
+      "eval_steps_per_second": 7.851,
       "step": 1
+    },
+    {
+      "epoch": 0.005788712011577424,
+      "grad_norm": 0.7782766222953796,
+      "learning_rate": 5e-05,
+      "loss": 0.6121,
+      "step": 5
+    },
+    {
+      "epoch": 0.011577424023154847,
+      "grad_norm": 0.7705448269844055,
+      "learning_rate": 0.0001,
+      "loss": 0.5238,
+      "step": 10
+    },
+    {
+      "epoch": 0.011577424023154847,
+      "eval_loss": 0.4204440414905548,
+      "eval_runtime": 22.911,
+      "eval_samples_per_second": 15.888,
+      "eval_steps_per_second": 7.944,
+      "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": 174263604609024.0,
+  "total_flos": 2265426859917312.0,
   "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 sha256:1f759c711f53a3cf25dd2dd272296be8f9d77909ce39b2521488baeae8ccae47
+oid sha256:f2bd37a2d3ae43fbd80736ae79710f85cb7536d0984886968f5b5bf7be4ed7ea
 size 6776