Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "v_proj",
     "down_proj",
+    "gate_proj",
     "o_proj",
     "up_proj",
-    "q_proj",
     "k_proj",
-    "gate_proj"
+    "q_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 sha256:5d24092171a9a104a61515a8740974060a9a447352fdddb705bd3583a52eef4f
+oid sha256:4465989d6b7c811ef2c3517010e3ff250cdf63de512bfe49eb958ee717229d61
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ee7c7c59da0d520537fd3cf39ee29259370f3c4657ea659bdbd0ffd3a92cd5
+oid sha256:053f081ad9b7705387563322017e169eba99a9d0e4d99bf251ac5484b5d91699
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
 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": 0.0020151133501259445,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02619647355163728,
+  "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": 0.0020151133501259445,
       "eval_loss": 11.928855895996094,
-      "eval_runtime": 2.8431,
-      "eval_samples_per_second": 73.51,
-      "eval_steps_per_second": 36.931,
+      "eval_runtime": 2.8749,
+      "eval_samples_per_second": 72.699,
+      "eval_steps_per_second": 36.523,
       "step": 1
+    },
+    {
+      "epoch": 0.010075566750629723,
+      "grad_norm": 0.01261623203754425,
+      "learning_rate": 5e-05,
+      "loss": 11.9283,
+      "step": 5
+    },
+    {
+      "epoch": 0.020151133501259445,
+      "grad_norm": 0.008780092932283878,
+      "learning_rate": 0.0001,
+      "loss": 11.9228,
+      "step": 10
+    },
+    {
+      "epoch": 0.020151133501259445,
+      "eval_loss": 11.928825378417969,
+      "eval_runtime": 2.8934,
+      "eval_samples_per_second": 72.232,
+      "eval_steps_per_second": 36.289,
+      "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": 177242112.0,
+  "total_flos": 2954035200.0,
   "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:b3a31f6fd3447019882644843437ab629f232b6d7498b91fb92df73ee0511204
+oid sha256:b2d26b4ccfe99cb870b769e8e4399085210809ce2352fcb545ca7929316450c1
 size 6776