Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "gate_proj",
-    "up_proj",
     "q_proj",
+    "up_proj",
     "down_proj",
-    "k_proj",
-    "v_proj"
+    "o_proj",
+    "v_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:b22e934726370bd40ce0b2be90027a5848e6027479420ebf8e11385b17c56208
+oid sha256:55ff5182d7e58a36387a0af18749259b37868c1014f1af14b51aa576ffefc182
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b09014506f1d3c3fb7cb2ba3d20dde9d907c2a64c8922ca44af709ee4910b55
+oid sha256:7c78f53d9e8166f5c8d01369271fe32c615b5712d351293661324a37a6c8c4d5
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db583067794f20b01832d4ddabaad594d5a607a594a6f04f852e2b423222180d
+oid sha256:e721ecdf324014b5c67b4c5b3c114aad793eb305cdd4f64c984d0a4b1909ad19
 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": 0.00025152486952147396,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0032698233037791614,
+  "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": 0.00025152486952147396,
       "eval_loss": 0.7711982727050781,
-      "eval_runtime": 114.1323,
-      "eval_samples_per_second": 14.676,
-      "eval_steps_per_second": 7.342,
+      "eval_runtime": 114.3608,
+      "eval_samples_per_second": 14.647,
+      "eval_steps_per_second": 7.328,
       "step": 1
+    },
+    {
+      "epoch": 0.0012576243476073697,
+      "grad_norm": 0.17833726108074188,
+      "learning_rate": 5e-05,
+      "loss": 0.7628,
+      "step": 5
+    },
+    {
+      "epoch": 0.0025152486952147394,
+      "grad_norm": 0.2529178261756897,
+      "learning_rate": 0.0001,
+      "loss": 0.7841,
+      "step": 10
+    },
+    {
+      "epoch": 0.0025152486952147394,
+      "eval_loss": 0.7362951040267944,
+      "eval_runtime": 115.5562,
+      "eval_samples_per_second": 14.495,
+      "eval_steps_per_second": 7.252,
+      "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": 139144609136640.0,
+  "total_flos": 1808879918776320.0,
   "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 sha256:702306d3aa76d758212c79d09b42edb66a36da582c6a4ff05391fd77a130dd23
+oid sha256:d5f8c1d3a8d77e3b6b1de6520c18e06f9cb003f267cef475d5c26b867421352e
 size 6776