Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
     "gate_proj",
     "o_proj",
+    "down_proj",
     "v_proj",
+    "q_proj",
     "k_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 sha256:94a8037930b740c3fb0259bf639d27321244e82f56f56556535bf14e8b454939
+oid sha256:08316c7dfa8b0638648823f5f557eded2e7af17ba525802b046adcde03e143ad
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af86a04cd825edd648369bec721c032530cf0103728c56ce7e66a7afdd81a776
+oid sha256:e1a8b8551ce3894027ac2f7c994870bedb0a338fe8a55caf89efeaa463e8476d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 4.3767028109373806e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005689713654218595,
+  "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": 4.3767028109373806e-05,
       "eval_loss": NaN,
-      "eval_runtime": 1118.7512,
-      "eval_samples_per_second": 8.6,
-      "eval_steps_per_second": 4.3,
+      "eval_runtime": 1118.6366,
+      "eval_samples_per_second": 8.601,
+      "eval_steps_per_second": 4.301,
       "step": 1
+    },
+    {
+      "epoch": 0.00021883514054686903,
+      "grad_norm": 149.75144958496094,
+      "learning_rate": 5e-05,
+      "loss": 44.7515,
+      "step": 5
+    },
+    {
+      "epoch": 0.00043767028109373805,
+      "grad_norm": 97.91552734375,
+      "learning_rate": 0.0001,
+      "loss": 33.6816,
+      "step": 10
+    },
+    {
+      "epoch": 0.00043767028109373805,
+      "eval_loss": NaN,
+      "eval_runtime": 1117.0239,
+      "eval_samples_per_second": 8.613,
+      "eval_steps_per_second": 4.307,
+      "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": 4556941443465216.0,
   "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 sha256:505a1afcc7f63719ba6589608dbacf1cb239d0054a9fa059b6852571c2c8016a
+oid sha256:5e8ec0852a3f49b894f25f0126fbf3846d70323f02bf28a20e7b7ba3272c1069
 size 6776