Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
     "o_proj",
+    "k_proj",
     "down_proj",
     "v_proj",
-    "k_proj",
-    "gate_proj",
-    "q_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 sha256:29c593dfdcbd4c5fa22c7eed790b07f4a725c1756cdcaca8634aaefabb0106e9
+oid sha256:3737dcf325ebf8f56647523debee54b606fcad4e232652ebc2ad4898898c3ac4
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdc83b03c54fcbb0006c8b53dde7eb33353a5fff9844a40dc2a868a7d3e9c7b4
+oid sha256:3b21df50c5bd910578076177c90b61bbb1280aae1dfab472b890bc33eb8c2d8d
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f2b1fe1ee433d0949425d85cbc1e7db562c93cb1fc4f9c675368fbffc7b15d
+oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
 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": 0.003864734299516908,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.050241545893719805,
+  "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": 0.003864734299516908,
       "eval_loss": 1.2902684211730957,
-      "eval_runtime": 3.4955,
-      "eval_samples_per_second": 31.183,
-      "eval_steps_per_second": 15.735,
+      "eval_runtime": 3.5672,
+      "eval_samples_per_second": 30.556,
+      "eval_steps_per_second": 15.418,
       "step": 1
+    },
+    {
+      "epoch": 0.01932367149758454,
+      "grad_norm": 0.6564427018165588,
+      "learning_rate": 5e-05,
+      "loss": 1.3111,
+      "step": 5
+    },
+    {
+      "epoch": 0.03864734299516908,
+      "grad_norm": 0.5247552394866943,
+      "learning_rate": 0.0001,
+      "loss": 1.2628,
+      "step": 10
+    },
+    {
+      "epoch": 0.03864734299516908,
+      "eval_loss": 1.176567554473877,
+      "eval_runtime": 3.5334,
+      "eval_samples_per_second": 30.848,
+      "eval_steps_per_second": 15.566,
+      "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": 25579197825024.0,
+  "total_flos": 332529571725312.0,
   "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 sha256:3165d3e24c823a3c015f65ff33f082acd4085a83176039813568cf7489f9d1bf
+oid sha256:99878e6a2d1d4b692480ebeeb2632b34e7f53d1d94e721e8c4d1e71e93f1d163
 size 6776