Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "o_proj",
     "gate_proj",
-    "down_proj",
     "k_proj",
+    "q_proj",
     "up_proj",
-    "v_proj",
-    "o_proj",
-    "q_proj"
+    "down_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:e3f25d9d96c73893ef46f77711b9e7ef708192c5bd86921264d5b328b3c65c31
+oid sha256:7dbde18a8c891e56796fa346abb177443ca6fd117cd5e10dc0773eb9caeae589
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f05ebf01cd0c7481dbd606b72a4f78b4f40fac0a654071cf2ad7ced71562297
+oid sha256:610e0ec6f1c0ddd57634282590d6ed45c5344f70caeb1552807b09abdec25b32
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bda8d6410a5049d09d7281ac42f6aabbc53ef016bd2bc3e3b5e1e711409ad67
+oid sha256:6a727a9f9a32d53a3870d1b46204881ec1a62b1997d14881c68b92d5a3844f50
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.009111617312072893,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.11845102505694761,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.009111617312072893,
       "eval_loss": 13.944470405578613,
-      "eval_runtime": 28.7611,
-      "eval_samples_per_second": 25.729,
-      "eval_steps_per_second": 3.234,
+      "eval_runtime": 28.8071,
+      "eval_samples_per_second": 25.688,
+      "eval_steps_per_second": 3.228,
       "step": 1
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "grad_norm": 8.145538330078125,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 12.18,
+      "step": 10
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "eval_loss": 8.518851280212402,
+      "eval_runtime": 27.4623,
+      "eval_samples_per_second": 26.946,
+      "eval_steps_per_second": 3.386,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1005324601393152.0,
+  "total_flos": 1.3393518076624896e+16,
   "train_batch_size": 8,
   "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:a427d5771abc3dcafc9629288d07446eb22f69f77389b9513ff563c6b0a58b33
+oid sha256:d05f5702eca792bfa83320bdf156975181b28b70da20d7247eae005067552d20
 size 6776