Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "up_proj",
-    "down_proj",
+    "gate_proj",
     "v_proj",
-    "k_proj",
+    "down_proj",
     "q_proj",
-    "gate_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 sha256:2a2f329b1f43921411cf8b88767a515ab6f2e5415f29de8311018a49b90e27f3
+oid sha256:73c7bbe340ec5d3bea05f4d1f49c64a155f2a353673df56d1d53849c22240441
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05b8e997c55270beb98ba6c7c37d5eb8f72b242cc47358221a5298cebd8a0db5
+oid sha256:171fea00ba7c487a1c08f2309e0d8d6c9e74d62350b312936db34900a1427be6
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b8ef222641ce7e54c4b1d49b5a2e66fce7ea5b5f86a8130c3ee2866221fbc5a
+oid sha256:6b8f0aa4af7093e810b0c7cb148aec740829a8c9ba7fcee1f5bd39e83d3fc49a
 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": 4.21474105684632e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005479163373900216,
+  "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": 4.21474105684632e-05,
       "eval_loss": 0.9627321362495422,
-      "eval_runtime": 1148.6894,
-      "eval_samples_per_second": 8.697,
-      "eval_steps_per_second": 4.348,
+      "eval_runtime": 1144.236,
+      "eval_samples_per_second": 8.731,
+      "eval_steps_per_second": 4.365,
       "step": 1
+    },
+    {
+      "epoch": 0.000210737052842316,
+      "grad_norm": 3.8283772468566895,
+      "learning_rate": 5e-05,
+      "loss": 3.9116,
+      "step": 5
+    },
+    {
+      "epoch": 0.000421474105684632,
+      "grad_norm": 4.155479907989502,
+      "learning_rate": 0.0001,
+      "loss": 3.9087,
+      "step": 10
+    },
+    {
+      "epoch": 0.000421474105684632,
+      "eval_loss": 0.9144762754440308,
+      "eval_runtime": 1151.498,
+      "eval_samples_per_second": 8.676,
+      "eval_steps_per_second": 4.338,
+      "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": 350533957189632.0,
+  "total_flos": 4469307954167808.0,
   "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:b724bb9f42715dd9afb194703c97cc97efd4d0fc13e36e5125e2418c6773c0db
+oid sha256:bee9f6729425be8b7fca57d4c1791c32ebd1b8fa5793e8984e6fe35e07c321a7
 size 6776