Training in progress, step 9, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "o_proj",
     "gate_proj",
-    "k_proj",
+    "up_proj",
     "v_proj",
-    "down_proj",
+    "k_proj",
     "q_proj",
-    "o_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 sha256:958484c9c19c822720cbeab14528d2bcbf63220cb367bc57b0a37ad430c6b750
+oid sha256:e5e6cc3f5ade40a8e874e995d657e610d46cc8ae5fbd62a777483ca05a6a1f19
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d45854fcfef3b1ed9a06c1c2d594b4915b33ae4be8ae887fd09cfd0d772686
+oid sha256:9b549c7992556bf7ede8945185f5fd3055a9a22839c885d48347ca92d6cf8193
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2c76845d1a198321567d417f508e36c6488ae79ee6a5814ae3463528c38bff
+oid sha256:cf191b7c52ae0f5950e3f1f1dec5b3d92cc3089d5753f800d4b1b7550aa71db3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:793e67e8ce9008665aa65ff20b6ea7fbcd694d12c7efb6b4719021ac264b7609
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.029906542056074768,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2691588785046729,
+  "eval_steps": 7,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.029906542056074768,
       "eval_loss": 3.908674716949463,
-      "eval_runtime": 11.9354,
-      "eval_samples_per_second": 18.935,
-      "eval_steps_per_second": 2.43,
+      "eval_runtime": 11.8982,
+      "eval_samples_per_second": 18.995,
+      "eval_steps_per_second": 2.437,
       "step": 1
+    },
+    {
+      "epoch": 0.20934579439252338,
+      "eval_loss": 0.4576127827167511,
+      "eval_runtime": 11.8715,
+      "eval_samples_per_second": 19.037,
+      "eval_steps_per_second": 2.443,
+      "step": 7
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 34,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 9,
   "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": 2804271657517056.0,
+  "total_flos": 2.5238444917653504e+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:c2e77e6560d4c60acc50761a210684b63e4c4126a6a404fbf4f01bc2f62ed741
+oid sha256:1909a4ab886ef315f8588ba049957232591c98f393de80c59fbfbade927d5a62
 size 6776