Training in progress, step 8, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "k_proj",
     "up_proj",
-    "o_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj"
+    "o_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:bab5cd2d82667aa88babe328886b13420e4373f17083ea84cc760b6bb2acb50d
+oid sha256:271e910b49bbc3a70bbece333bb98b8044250f5312389fc58f4477edee664bb4
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c5f0a191227b3b77966e183f85fa44b193a2a65cf2ac6bca0d328d98456ad14
+oid sha256:b9205d0be73afe8a749d60d92088051b9d1a742460111451262ff97efce9ec32
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be8b1b9e7bfbfa0a07c044af5d4d41c9b69c03fb50ecb3685b8b3b42939557eb
+oid sha256:33e0496dcdb9c09786e531fcb26e12c27114121c2227d15a22d343188a83ccc7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:a517b5553fd7c8042f9435a157576adf1654dadecdce942dd5274f1a6454ed0a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03333333333333333,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.26666666666666666,
+  "eval_steps": 6,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.03333333333333333,
       "eval_loss": 1.7954519987106323,
-      "eval_runtime": 12.6676,
-      "eval_samples_per_second": 15.946,
-      "eval_steps_per_second": 2.052,
+      "eval_runtime": 12.6939,
+      "eval_samples_per_second": 15.913,
+      "eval_steps_per_second": 2.048,
       "step": 1
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.587748646736145,
+      "eval_runtime": 13.1935,
+      "eval_samples_per_second": 15.311,
+      "eval_steps_per_second": 1.971,
+      "step": 6
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 30,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 8,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 3057746266030080.0,
+  "total_flos": 2.446197012824064e+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:c919ce5487abf058b6597df3579004fa77c2ac1a2b5c50aed2a11faf30f0f667
+oid sha256:a83544229dc0d8d1596052bdfbbc9ee05a61596a97a8a28c412d20b2c7cef39c
 size 6776