Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "up_proj",
     "gate_proj",
     "k_proj",
-    "down_proj",
-    "o_proj"
+    "o_proj",
+    "q_proj",
+    "up_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 sha256:386fd992f3512198b7ad2012b738c8ead6278ed2de7ca6a8a899a63d7a3f019f
+oid sha256:55d12c5116fab96711d308ca66cb502c6210c4d46b79aca8d5359be77bccc55c
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6d995c383a5bf80e9f3aaaa99e7f0de2434c4c1072e47f3e0e092f7e2fd0a9
+oid sha256:ef971f69aa8dacfc6f6d53d68db5bc29f2bfbd4ab9e8e2ccb7d0863e41851538
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce945f99ac704cf861b77342aba88e612f716dc47a81d0549654f9bc53ed780c
+oid sha256:4a8512b20c9bb9b60255851076439eb2a112cbd82efd02375a96c1cb3aa27d06
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00176522506619594,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02294792586054722,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.00176522506619594,
       "eval_loss": 19.31140899658203,
-      "eval_runtime": 61.884,
-      "eval_samples_per_second": 3.862,
-      "eval_steps_per_second": 1.939,
+      "eval_runtime": 61.8597,
+      "eval_samples_per_second": 3.864,
+      "eval_steps_per_second": 1.94,
       "step": 1
+    },
+    {
+      "epoch": 0.0088261253309797,
+      "grad_norm": 60.404327392578125,
+      "learning_rate": 5e-05,
+      "loss": 20.5111,
+      "step": 5
+    },
+    {
+      "epoch": 0.0176522506619594,
+      "grad_norm": 70.15036010742188,
+      "learning_rate": 0.0001,
+      "loss": 13.7811,
+      "step": 10
+    },
+    {
+      "epoch": 0.0176522506619594,
+      "eval_loss": 5.2021636962890625,
+      "eval_runtime": 62.7015,
+      "eval_samples_per_second": 3.812,
+      "eval_steps_per_second": 1.914,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "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 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 382218283253760.0,
+  "total_flos": 4968837682298880.0,
   "train_batch_size": 2,
   "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:a32cacbbb089a31321e8182187f2208ea48630e80dcaa5ffbdc6f57cefa8e55f
+oid sha256:6f0e51e4acb57eae2c7e9ce0cf1331a685632ca15b4b7146ae3fcef17258289a
 size 6776