Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
     "o_proj",
-    "up_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj",
-    "gate_proj"
+    "k_proj",
+    "q_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:ba37acf2c230c2f9da505eb7804cf6afa877eeed382073169214813b7ff73bc6
+oid sha256:24d7fe7e78b817e9b011a5139e671005ffeee6fdb9c8850a80f88c6443aaafb7
 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 sha256:5ed413ffc1f3bedbef14e57f493d3e8611649fb25a4d11d4dded6eabfeeb78de
+oid sha256:2c752e25fa55e56f2a8dad1c8b0834854e88973b92db4d3744ac8830817a5dbd
 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": 8.432396423820677e-06,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0001096211535096688,
+  "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": 8.432396423820677e-06,
       "eval_loss": NaN,
-      "eval_runtime": 2035.4194,
-      "eval_samples_per_second": 24.532,
-      "eval_steps_per_second": 12.266,
+      "eval_runtime": 2042.9263,
+      "eval_samples_per_second": 24.442,
+      "eval_steps_per_second": 12.221,
       "step": 1
+    },
+    {
+      "epoch": 4.216198211910338e-05,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 8.432396423820676e-05,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 8.432396423820676e-05,
+      "eval_loss": NaN,
+      "eval_runtime": 2055.2843,
+      "eval_samples_per_second": 24.295,
+      "eval_steps_per_second": 12.148,
+      "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": 40537282314240.0,
+  "total_flos": 608059234713600.0,
   "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 sha256:3962486fe2bd4e58a37dd33c92b0ba41c7867358c04ea0c7bfe139005ade670a
+oid sha256:83a80d3b1e8d10f7222744fcb78229e074a9e9153ee034011cde41457b2ff52d
 size 6776