Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "k_proj",
-    "gate_proj",
-    "o_proj",
-    "q_proj",
     "down_proj",
+    "o_proj",
     "up_proj",
-    "v_proj"
+    "q_proj",
+    "gate_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 sha256:1c52ee176cc7598004a1cf983e0a6c020788da0832d79618da61a489bcd65682
+oid sha256:b770c27793ff7a6d2735ce36c14d524d95eeac8a06d24bf534fe6274695df909
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f378c2c22c4ab5a8283984b149b2a33a2f2321dd3cffc54460057b3c45c73d9f
+oid sha256:40ff4e0def5297001858087f81598a95f9c21227426c5da895cb1fc89336434f
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e567974070fd68964e0b5796ff57d20608d79f191555f462c21bdf57303c9795
+oid sha256:b5ed94d3f701716d000966a79dc83b9c7cb22d520c60aa3219af11d89dc9f6e3
 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": 0.0005689900426742532,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007396870554765292,
+  "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": 0.0005689900426742532,
       "eval_loss": 2.423877239227295,
-      "eval_runtime": 72.3353,
-      "eval_samples_per_second": 10.23,
-      "eval_steps_per_second": 5.115,
+      "eval_runtime": 72.3765,
+      "eval_samples_per_second": 10.224,
+      "eval_steps_per_second": 5.112,
       "step": 1
+    },
+    {
+      "epoch": 0.002844950213371266,
+      "grad_norm": 1.9417362213134766,
+      "learning_rate": 5e-05,
+      "loss": 2.1288,
+      "step": 5
+    },
+    {
+      "epoch": 0.005689900426742532,
+      "grad_norm": 1.8670800924301147,
+      "learning_rate": 0.0001,
+      "loss": 2.0875,
+      "step": 10
+    },
+    {
+      "epoch": 0.005689900426742532,
+      "eval_loss": 2.0842385292053223,
+      "eval_runtime": 72.7118,
+      "eval_samples_per_second": 10.177,
+      "eval_steps_per_second": 5.089,
+      "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": 205239361732608.0,
+  "total_flos": 2668111702523904.0,
   "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:d391a7da8f2ab51768727f224b4f2a65640242e39a861178f401cf73d1cdc6ed
+oid sha256:dc5748ad54a08cd543f606562395fe530c2d266f004ac83b5b836778d92ae078
 size 6776