Training in progress, step 8, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "v_proj",
-    "q_proj",
     "o_proj",
+    "down_proj",
     "k_proj",
-    "gate_proj"
+    "gate_proj",
+    "up_proj",
+    "q_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 sha256:12ce88980959c985233b3c7142357b18d496bb43c59fa234d42fccd21174ac51
+oid sha256:09d9cd9d64b8665ecd6ec2ebd855d88bdb2112636d72ac67a02d08e65f893f69
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9776b1c2b13cb23a55c535faf5dba790917c67ac6dd02df51d7c56b7d120cecc
+oid sha256:b97dba664b3181de2851240619dc83adf18deef4358946e5c600b266b86b05c3
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b36908b214dde88065d7655823e9333990bb44dc527e44ce630a6e70ab4c930
+oid sha256:1075dc06372e74a6dd6d15cbcc83eba2ddad9340f54aebf9ab084cafc6234362
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:8de9e474f1c6268aa67c74a46e97e6502d38b40ebf11528de80b392fa9163e1d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035555555555555556,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.28444444444444444,
+  "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": 0.035555555555555556,
       "eval_loss": 12.9937105178833,
-      "eval_runtime": 0.9367,
-      "eval_samples_per_second": 202.83,
-      "eval_steps_per_second": 25.621,
+      "eval_runtime": 0.9451,
+      "eval_samples_per_second": 201.043,
+      "eval_steps_per_second": 25.395,
       "step": 1
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 12.368244171142578,
+      "eval_runtime": 0.9262,
+      "eval_samples_per_second": 205.147,
+      "eval_steps_per_second": 25.913,
+      "step": 6
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 29,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "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": 2097873420288.0,
+  "total_flos": 16782987362304.0,
   "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 sha256:98b15012b0f3b76d8f16dfd85ca8cbdf9adbf3ad923f6380022480221176c6bb
+oid sha256:bb521ed129943c3fedae014a018e8342121a2325febde4656aebff17d9908317
 size 6776