Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "down_proj",
     "o_proj",
-    "q_proj",
-    "v_proj",
+    "gate_proj",
+    "up_proj",
     "k_proj",
-    "gate_proj"
+    "v_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:df785838a4b8cad1f0192a0a68c2bcfab62a7bebaf387a5d63d146793af6c900
+oid sha256:c7c08aa1c3ff8e868972a92c40968030743f58c592b9a6e0741ea481c91c914f
 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 sha256:48707ce5b888f5fb4ed0bb81e0d8f92699172e8647e4e04f8cf50ce6a8cd793a
+oid sha256:c8df54173348c1bc22e4c12321edb602dcf96b990f64926a9d0d91d3ab2bcd75
 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": 0.0007910610105804411,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.010283793137545733,
+  "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": 0.0007910610105804411,
       "eval_loss": NaN,
-      "eval_runtime": 164.005,
-      "eval_samples_per_second": 51.925,
-      "eval_steps_per_second": 6.494,
+      "eval_runtime": 164.1202,
+      "eval_samples_per_second": 51.889,
+      "eval_steps_per_second": 6.489,
       "step": 1
+    },
+    {
+      "epoch": 0.00791061010580441,
+      "grad_norm": NaN,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00791061010580441,
+      "eval_loss": NaN,
+      "eval_runtime": 162.7431,
+      "eval_samples_per_second": 52.328,
+      "eval_steps_per_second": 6.544,
+      "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": 518877213622272.0,
+  "total_flos": 6745403777089536.0,
   "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:e115508c851326cdd676ec97745954b650f33232d5347383eaf70945aed7a995
+oid sha256:ce4104b5250c29b699f4838a618a9b223d2b2e70075390cd91a70a57e46b7099
 size 6776