Training in progress, step 12, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
     "gate_proj",
     "up_proj",
-    "q_proj",
-    "o_proj",
-    "k_proj",
-    "v_proj"
+    "v_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 sha256:9a7b1a7c0b441fb030c06b97b7dbb60b7d91f44df909a3dd180febcacbb48850
+oid sha256:acdc6c79042793bb0349b1d043f53d0c7fd841fd1df0d187358bdacba3681934
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a7813130911693d5a0e897cb352532e882d3c4c44af893779ebbce35365b21
+oid sha256:2d3c1fdce11be054ccec91ab2fb443c398d5d31d42b2ea37389ac81886b6be3a
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b76b336792a659bf71c4342297577ae1a29c83058d83e060278f3e4892b1ec99
+oid sha256:ca57f6d22d1fd352df674eaaa93a75565b2c5a98cc3901814cd5d09f8d3f8ed4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:6b16484e0674b1fd075ed0f801729c12a5a1d0090aec132c58e1287d0be87e5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022222222222222223,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.26666666666666666,
+  "eval_steps": 9,
+  "global_step": 12,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.022222222222222223,
       "eval_loss": 1.8410741090774536,
-      "eval_runtime": 16.6034,
-      "eval_samples_per_second": 18.249,
-      "eval_steps_per_second": 2.289,
+      "eval_runtime": 16.746,
+      "eval_samples_per_second": 18.094,
+      "eval_steps_per_second": 2.269,
       "step": 1
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 1.0834723711013794,
+      "eval_runtime": 15.6719,
+      "eval_samples_per_second": 19.334,
+      "eval_steps_per_second": 2.425,
+      "step": 9
+    },
+    {
+      "epoch": 0.2222222222222222,
+      "grad_norm": 1.0347282886505127,
+      "learning_rate": 9.16998908944939e-05,
+      "loss": 1.536,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 45,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 12,
   "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": 2788217673744384.0,
+  "total_flos": 3.345861208493261e+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:cf4e605432cc9232047caadeb581e383d6cbdd149f2997f185b511e68f8b8505
+oid sha256:65c513cdd2b8de52b0afed3c06c5b2884159c0953c6351e8c009a33e2a6e956b
 size 6776