Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "down_proj",
-    "q_proj",
     "gate_proj",
-    "up_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj",
     "o_proj",
-    "k_proj"
+    "up_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 sha256:9453663326526c10f6c0a083695792725da8e77d0f275686c323f498a777dd52
+oid sha256:69c694786a162fe421be3b141fb0d43ef08035250087020c314429e3d179b035
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433a550fd7fccd96138e9361bd6dedd9a574e5b2c127ae6ecb1053eb1d93b43d
+oid sha256:6426c56b304918910a6b5e46214fd1d21ebfe46b028b43839e6cd0323b6d322f
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:772c12aea0055e16597749ef8f0cf5d107fb6f555f61b38319bdf80a27064f18
+oid sha256:0eefaa47e55c8b641285f20788c3c6ccb8efe04d5676c94fb09af90185b85664
 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": 0.00038902937171756465,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0050573818323283405,
+  "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": 0.00038902937171756465,
       "eval_loss": 2.161581039428711,
-      "eval_runtime": 181.537,
-      "eval_samples_per_second": 5.966,
-      "eval_steps_per_second": 2.986,
+      "eval_runtime": 231.553,
+      "eval_samples_per_second": 4.677,
+      "eval_steps_per_second": 2.341,
       "step": 1
+    },
+    {
+      "epoch": 0.0019451468585878235,
+      "grad_norm": 0.3031664490699768,
+      "learning_rate": 5e-05,
+      "loss": 2.1486,
+      "step": 5
+    },
+    {
+      "epoch": 0.003890293717175647,
+      "grad_norm": 0.3501927852630615,
+      "learning_rate": 0.0001,
+      "loss": 2.1731,
+      "step": 10
+    },
+    {
+      "epoch": 0.003890293717175647,
+      "eval_loss": 2.1431446075439453,
+      "eval_runtime": 230.9198,
+      "eval_samples_per_second": 4.69,
+      "eval_steps_per_second": 2.347,
+      "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": 64859651702784.0,
+  "total_flos": 843175472136192.0,
   "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 sha256:611a094eb8e9ecde94703555a531c392cd62287a89fcd17602b37b894314a52b
+oid sha256:cc193e38b83662d3084779bd035e25eb1c67e293a8d13b451bde63dca954a886
 size 6776