Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "gate_proj",
-    "k_proj",
     "v_proj",
     "q_proj",
+    "o_proj",
     "up_proj",
-    "down_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:a0eb2553bc29fb78a857e4b7eeb01d3bbaa78d3d166edf8707a8f070086ff590
+oid sha256:0bb3407424c49c91dad0456696a8df2fd9ca261ad6353aa477cc734321028efb
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e78a5be7949652e86af157ae067dadfcff0f857b4bd10f8c97b3895d735b947f
+oid sha256:2674926d5ae268a65ec6b212f17c334fe1e9b0f6ed5ac1799705787ef664ee0d
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db583067794f20b01832d4ddabaad594d5a607a594a6f04f852e2b423222180d
+oid sha256:e721ecdf324014b5c67b4c5b3c114aad793eb305cdd4f64c984d0a4b1909ad19
 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": 0.0014154281670205238,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01840056617126681,
+  "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": 0.0014154281670205238,
       "eval_loss": 1.6379996538162231,
-      "eval_runtime": 20.5575,
-      "eval_samples_per_second": 14.496,
-      "eval_steps_per_second": 7.248,
+      "eval_runtime": 20.5529,
+      "eval_samples_per_second": 14.499,
+      "eval_steps_per_second": 7.25,
       "step": 1
+    },
+    {
+      "epoch": 0.007077140835102618,
+      "grad_norm": 0.28412914276123047,
+      "learning_rate": 5e-05,
+      "loss": 1.5999,
+      "step": 5
+    },
+    {
+      "epoch": 0.014154281670205236,
+      "grad_norm": 0.3511485457420349,
+      "learning_rate": 0.0001,
+      "loss": 1.6283,
+      "step": 10
+    },
+    {
+      "epoch": 0.014154281670205236,
+      "eval_loss": 1.5943732261657715,
+      "eval_runtime": 20.8027,
+      "eval_samples_per_second": 14.325,
+      "eval_steps_per_second": 7.163,
+      "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": 139144609136640.0,
+  "total_flos": 1808879918776320.0,
   "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:d1ee993a689d8ff5f6a2e3c31ba1ddc87badf10216619d698014d75ad7ceaf07
+oid sha256:1a0bfdfac12ba6a2b40b0bb6a078309f8dfd52f0ab0d9759f371785a1a1be098
 size 6776