Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "down_proj",
-    "q_proj",
     "o_proj",
-    "k_proj",
+    "q_proj",
+    "up_proj",
+    "v_proj",
     "gate_proj",
-    "up_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:d6b4c1926f577f8139c61cb47f4809c40970f28677bc2731d82a99833e921c31
+oid sha256:b29f1013f41f0e0c06dec8c213eb2ce9d8af88c7fffce07a76fe784a12f3cf8b
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb75bd6bc618b114d1882ad92569960f61087f7ac0bdcc9a2186503c240e35c
+oid sha256:dd06243d848f92832f8a3e527e7f47cee960b501f7e3db01eb514e798ad38604
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165ffe955f1fff238d7fa55fc3e704ed1175348f65c16d2a2296ab05188c0b98
+oid sha256:c5e599ebf8c42bf4256978eb4e60b65fa52201162f66abf71b04010cf02aa5e2
 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": 0.00010829542993285683,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0014078405891271388,
+  "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": 0.00010829542993285683,
       "eval_loss": 4.484375,
-      "eval_runtime": 190.9415,
-      "eval_samples_per_second": 20.362,
-      "eval_steps_per_second": 10.181,
+      "eval_runtime": 191.0247,
+      "eval_samples_per_second": 20.353,
+      "eval_steps_per_second": 10.177,
       "step": 1
+    },
+    {
+      "epoch": 0.0005414771496642842,
+      "grad_norm": 5.39006233215332,
+      "learning_rate": 5e-05,
+      "loss": 3.3685,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010829542993285683,
+      "grad_norm": 5.86919641494751,
+      "learning_rate": 0.0001,
+      "loss": 3.1762,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010829542993285683,
+      "eval_loss": 2.7510037422180176,
+      "eval_runtime": 190.2451,
+      "eval_samples_per_second": 20.437,
+      "eval_steps_per_second": 10.218,
+      "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": 891288626921472.0,
   "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 sha256:79a25000c79e01689113bbba5d5ef35268c064bf8c57fd6b4ba59bd504ca9547
+oid sha256:10e380b9b065a5ac1f1c5256fc72e51f2f51135641a3f2a5f53a2a78ebfc73f2
 size 6776