Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "k_proj",
-    "gate_proj",
-    "down_proj",
     "v_proj",
+    "gate_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 sha256:6544a8268c8b99413db242e86aebf3be5e6fcf23187799b916dc6da534020889
+oid sha256:a363b5f2bc1dd46765e15f138e5c5059f897b129ffa42d11b4a5bc46228be72e
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd05fdf1063a99679392fb377f95e5cf92c5a935f4bd24e4b1d129cf9d5588ed
+oid sha256:b0b8e7b1b57345c29e156ac92ddec455ee25bc31897b005a6b81206d8e3badff
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:181b2dd047c8efb22ee2b4a33b6abf561a98690af84a38dcd124735ba4b4129b
+oid sha256:cada282df88fa872ae241f328070b3d154b7f83d7651e8c9b3eb27f30d23c8fe
 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": 3.0105066682722702e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0003913658668753951,
+  "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": 3.0105066682722702e-05,
       "eval_loss": 2.0711593627929688,
-      "eval_runtime": 519.5813,
-      "eval_samples_per_second": 26.92,
-      "eval_steps_per_second": 13.461,
+      "eval_runtime": 528.8979,
+      "eval_samples_per_second": 26.446,
+      "eval_steps_per_second": 13.224,
       "step": 1
+    },
+    {
+      "epoch": 0.00015052533341361352,
+      "grad_norm": 0.18690688908100128,
+      "learning_rate": 5e-05,
+      "loss": 2.0801,
+      "step": 5
+    },
+    {
+      "epoch": 0.00030105066682722703,
+      "grad_norm": 0.18453490734100342,
+      "learning_rate": 0.0001,
+      "loss": 2.0853,
+      "step": 10
+    },
+    {
+      "epoch": 0.00030105066682722703,
+      "eval_loss": 2.0662031173706055,
+      "eval_runtime": 521.92,
+      "eval_samples_per_second": 26.799,
+      "eval_steps_per_second": 13.401,
+      "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": 63277451182080.0,
+  "total_flos": 814697183969280.0,
   "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 sha256:8d7ff41a33a1f475fe6e478381fec896ca4cd9c4ec23e494d00c83709ab63258
+oid sha256:b4508c3a0c2d160fc872c9b19380a5683cf75a2a854f6abcf533d1d2559c71dc
 size 6776