Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
+    "down_proj",
+    "gate_proj",
     "up_proj",
-    "k_proj",
     "v_proj",
-    "gate_proj",
-    "down_proj"
+    "k_proj",
+    "o_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 sha256:07f4e2dd92a49e0c77ae0fc99584f405afabac828cc7f5165c21ab84ea7d5aec
+oid sha256:cf99f322e8f0ad917a5571cf02a32f7ce6d5dffc8f5583e3c93c8dbff5534706
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:465bc97f6e9998b79338f01cd5a68b15193155dd3db629e3d68306b78b092515
+oid sha256:bcd7320952d3e90955ad13a7b1752d6231952acae7adf7f1bfc191823f60e4ca
 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": 0.00017571604287471446,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.002284308557371288,
+  "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": 0.00017571604287471446,
       "eval_loss": 1.1193796396255493,
-      "eval_runtime": 297.0531,
-      "eval_samples_per_second": 8.069,
-      "eval_steps_per_second": 4.036,
+      "eval_runtime": 297.8621,
+      "eval_samples_per_second": 8.047,
+      "eval_steps_per_second": 4.025,
       "step": 1
+    },
+    {
+      "epoch": 0.0008785802143735723,
+      "grad_norm": 0.3865303099155426,
+      "learning_rate": 5e-05,
+      "loss": 1.1009,
+      "step": 5
+    },
+    {
+      "epoch": 0.0017571604287471446,
+      "grad_norm": 0.4401898682117462,
+      "learning_rate": 0.0001,
+      "loss": 1.0403,
+      "step": 10
+    },
+    {
+      "epoch": 0.0017571604287471446,
+      "eval_loss": 1.0582906007766724,
+      "eval_runtime": 297.7028,
+      "eval_samples_per_second": 8.052,
+      "eval_steps_per_second": 4.028,
+      "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": 369912849629184.0,
+  "total_flos": 4808867045179392.0,
   "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 sha256:700b17bc15b76b4d38adb923cbfe2057ef0e882a405ae4bfea7333f9aacc8181
+oid sha256:53c9e96b873e3c7207998735c85031588f89259191e649d73fb71ff0149cf87e
 size 6776