Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
-    "o_proj",
-    "down_proj",
-    "v_proj",
     "up_proj",
+    "k_proj",
+    "o_proj",
     "q_proj",
-    "k_proj"
+    "down_proj",
+    "v_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 sha256:01d7da2832289071615933436018344bcd30275502975bcb58813f1587116cfa
+oid sha256:5f58e489ee9d0fcbdc29e6236ced6835090d61b3bae5fef87bf924b4a4bcd4b9
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:47c4b1b1022476a667133913254b988ff83885ee227e03c4f7dc228d6177ea10
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:319df9a8a6544e8b77e9d5e0c24b6c99c0c09176b51d435e36d005bdf8f1e849
+oid sha256:f67d05ef0585b4d1c04a69bc36795294f7de8a231383992baa4e5bd6ce9c37b9
 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": 0.0007965350724349081,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.010354955941653806,
+  "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": 0.0007965350724349081,
       "eval_loss": NaN,
-      "eval_runtime": 257.2053,
-      "eval_samples_per_second": 32.884,
-      "eval_steps_per_second": 4.113,
+      "eval_runtime": 257.2896,
+      "eval_samples_per_second": 32.873,
+      "eval_steps_per_second": 4.112,
       "step": 1
+    },
+    {
+      "epoch": 0.007965350724349082,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.007965350724349082,
+      "eval_loss": NaN,
+      "eval_runtime": 255.6607,
+      "eval_samples_per_second": 33.083,
+      "eval_steps_per_second": 4.138,
+      "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": 908035123838976.0,
+  "total_flos": 1.0961281137770496e+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 sha256:41b9428166de10ff00aa5a292753b313eb05adcffc7c02539cbea6b039d7cf6c
+oid sha256:9c5fc328d78f2a6ad6969cb4b91f75b91d75a18aa58fd62ea5a3c5540778a88d
 size 6776