Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "q_proj",
-    "k_proj",
     "up_proj",
     "v_proj",
+    "q_proj",
+    "o_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:cc68e9249496f953e631a20d5351f25de4982a87396fe94b3651fa0a33278439
+oid sha256:5897f7cc08ae0016a7e223cd7a5e863b24fe189ebf6e5c9e534f2f2c4962e8d0
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb42603c6ea93282cd7b812e4230cfeb74ceecfc7f6b103a7e0220f43cb7ac48
+oid sha256:16df58a38a19b7b1f9f5565b44c53c75669a622cbaf622cac5c2ed8badf7bd6a
 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": 1.1256539345826217e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00014633501149574082,
+  "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": 1.1256539345826217e-05,
       "eval_loss": NaN,
-      "eval_runtime": 1405.2675,
-      "eval_samples_per_second": 26.618,
-      "eval_steps_per_second": 13.309,
+      "eval_runtime": 1423.2317,
+      "eval_samples_per_second": 26.282,
+      "eval_steps_per_second": 13.141,
       "step": 1
+    },
+    {
+      "epoch": 5.628269672913108e-05,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00011256539345826216,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00011256539345826216,
+      "eval_loss": NaN,
+      "eval_runtime": 1422.0509,
+      "eval_samples_per_second": 26.304,
+      "eval_steps_per_second": 13.152,
+      "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": 32429825851392.0,
+  "total_flos": 421587736068096.0,
   "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 sha256:4a6d62f7df6ccdfbf754194dfa47373cb38687275fb0f6fae10a37282c882344
+oid sha256:39929e09cb7502a48c4f7878a26c0fa22a93ccc446522daeb68661c0ec807266
 size 6776