Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "q_proj",
     "o_proj",
     "v_proj",
+    "down_proj",
+    "k_proj",
     "gate_proj",
-    "up_proj",
-    "down_proj"
+    "q_proj",
+    "up_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 sha256:3c3665fa451ea9b563a4b651048fd51e2aa64104dc4a203998a6618968150879
+oid sha256:2977ff02f96b8ad37d41b0ffea9189064261e8948f7b80501db327c6364b9a68
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b366972346d444cc5bb8c1c5f918fc7362efb221282a44ff422976349ece6ee1
+oid sha256:c80c5aec7e6696beadf47ce9428ab42cbea82422599fdf75b7e997fb5f5940b8
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4865c784751f08fb8deff9071128988f7eb961f669d74f7bc3864ebf22f64623
+oid sha256:a59a506f34fbd0cd7e326900f2d9cbbf2c685843b55573b447b901880a1ad61a
 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": 0.0008871146595697493,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.011532490574406742,
+  "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": 0.0008871146595697493,
       "eval_loss": 1.7183804512023926,
-      "eval_runtime": 28.7774,
-      "eval_samples_per_second": 16.506,
-      "eval_steps_per_second": 8.27,
+      "eval_runtime": 26.9655,
+      "eval_samples_per_second": 17.615,
+      "eval_steps_per_second": 8.826,
       "step": 1
+    },
+    {
+      "epoch": 0.004435573297848747,
+      "grad_norm": 0.6569576263427734,
+      "learning_rate": 5e-05,
+      "loss": 1.7603,
+      "step": 5
+    },
+    {
+      "epoch": 0.008871146595697495,
+      "grad_norm": 1.0358091592788696,
+      "learning_rate": 0.0001,
+      "loss": 1.7299,
+      "step": 10
+    },
+    {
+      "epoch": 0.008871146595697495,
+      "eval_loss": 1.4282162189483643,
+      "eval_runtime": 27.198,
+      "eval_samples_per_second": 17.465,
+      "eval_steps_per_second": 8.751,
+      "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": 123007299747840.0,
+  "total_flos": 1783605846343680.0,
   "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 sha256:80e9f3ad6c14a5d5e8ec354eb0db2a90448df6d5e826db9e380ccdfda623eac8
+oid sha256:b266fc2b67d2ed61c8c186848c5757d0799b2eb7e5e294d6ff54ffda59e2026e
 size 6776