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",
     "gate_proj",
-    "o_proj",
     "down_proj",
-    "q_proj",
-    "v_proj",
-    "k_proj",
-    "up_proj"
+    "up_proj",
+    "o_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 sha256:492ac3b4b680c89222c5bf820865a231d2bed9c80732ad111f9c695581208142
+oid sha256:45300c49b2c9acf8905d9ab5dadec2184e8efefb840d77cfa34aed8659e7f8ff
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a21f0d64771edfb86dc28a07b338db97f190e2b6a9efe19b88676d51e3ee1f24
+oid sha256:ced67eeca63e60c98d6c64aa10109d9aff27081b763b85103eeb4a0bc4899e1b
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c6aec7ebe1cf0946dfc9ec4cb3dac1a717cf177a62534e9c05548ccfc197a8
+oid sha256:aa0634b79427ffd6d4ab70a960890d62996d62c36b5f34ed12a9101043d0c7ea
 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": 0.005105296745373325,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.06636885768985322,
+  "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": 0.005105296745373325,
       "eval_loss": 0.6308530569076538,
-      "eval_runtime": 34.5901,
-      "eval_samples_per_second": 38.161,
-      "eval_steps_per_second": 4.77,
+      "eval_runtime": 34.3499,
+      "eval_samples_per_second": 38.428,
+      "eval_steps_per_second": 4.804,
       "step": 1
+    },
+    {
+      "epoch": 0.05105296745373325,
+      "grad_norm": 0.10898499190807343,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.6061,
+      "step": 10
+    },
+    {
+      "epoch": 0.05105296745373325,
+      "eval_loss": 0.6026803851127625,
+      "eval_runtime": 34.5662,
+      "eval_samples_per_second": 38.188,
+      "eval_steps_per_second": 4.773,
+      "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": 818534330400768.0,
+  "total_flos": 1.0640946295209984e+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:d4eda6be89501b232053eaea87f4894fc87d3f7ece3b89e247ad9c828141b231
+oid sha256:7f2c36495ffe3b9769cca0310456430bc45e2b19be44969c7ce705fc062b4547
 size 6776