Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
     "q_proj",
     "down_proj",
-    "gate_proj",
-    "up_proj",
     "k_proj",
+    "up_proj",
     "o_proj",
-    "v_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 sha256:1819f6f87ac211050125f6641c25c40c884e7b3b18ea2ff3912e577784b3dd45
+oid sha256:92cb13354f2801e28dbeab35ccda2fc7cd98d78bb9fc74e50a01e509a1ac48f2
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cce6089770afddb29012fbb0af74a07b3a8397ffc13d3c09928d7070b5a4abc3
+oid sha256:a8409936268ef6e63d83c45324a103a9024df5c9ccc8055839348ff414a0f693
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165ffe955f1fff238d7fa55fc3e704ed1175348f65c16d2a2296ab05188c0b98
+oid sha256:b23e3563cff8d6d68500bc74b7edbd65bc82eb522ab07e96964bdd71f95b3032
 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": 0.000457351932311914,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0059455751200548825,
+  "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": 0.000457351932311914,
       "eval_loss": 1.0455454587936401,
-      "eval_runtime": 47.228,
-      "eval_samples_per_second": 19.501,
-      "eval_steps_per_second": 9.761,
+      "eval_runtime": 47.9877,
+      "eval_samples_per_second": 19.192,
+      "eval_steps_per_second": 9.607,
       "step": 1
+    },
+    {
+      "epoch": 0.00228675966155957,
+      "grad_norm": 0.5073609352111816,
+      "learning_rate": 5e-05,
+      "loss": 0.9017,
+      "step": 5
+    },
+    {
+      "epoch": 0.00457351932311914,
+      "grad_norm": 0.5990011096000671,
+      "learning_rate": 0.0001,
+      "loss": 0.8177,
+      "step": 10
+    },
+    {
+      "epoch": 0.00457351932311914,
+      "eval_loss": 0.9886856079101562,
+      "eval_runtime": 44.8827,
+      "eval_samples_per_second": 20.52,
+      "eval_steps_per_second": 10.271,
+      "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": 68560663609344.0,
+  "total_flos": 908428792823808.0,
   "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 sha256:852d54f4b5f69cd1185de1f35b51570c1145858931c2f55b892d53547bf9aafb
+oid sha256:9ba1c790ba3904fbfea97ca6bc8d5de6fa23f2f323440550d1324cb494b8bc6a
 size 6776