Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "down_proj",
-    "gate_proj",
-    "o_proj",
     "up_proj",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "v_proj",
+    "gate_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 sha256:8cc0b9e8703a258e425c8893bce1f2726338234744ab51800b76656e6b9e09ac
+oid sha256:f3814dc660832d55c2bb40d2ad3d99795436d8bc62ab17ac4e58f293371e60c9
 size 6804608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:105c8b058b90bb0419b4d0ca5f2b2abf075e71b1a86732ce8345da8b4c9e92b9
+oid sha256:1e0780a4ef307d8f6befe37e4468d68934340db91d4a6d7a386b0e46fc82b40e
 size 3633530

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35958045b9b1816d8bf8120af9d731df3e24f85e96921fc463cc18ebbaf0c2e6
+oid sha256:68d619f0a0b38410fb70c6f171e70d6491ec81ae876beaf702a4465ab5b7139f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016666666666666666,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.21666666666666667,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.016666666666666666,
       "eval_loss": 6.828747272491455,
-      "eval_runtime": 3.1215,
-      "eval_samples_per_second": 129.747,
-      "eval_steps_per_second": 16.339,
+      "eval_runtime": 3.1635,
+      "eval_samples_per_second": 128.022,
+      "eval_steps_per_second": 16.121,
       "step": 1
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 2.298238754272461,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 6.479,
+      "step": 10
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "eval_loss": 6.025122165679932,
+      "eval_runtime": 3.1802,
+      "eval_samples_per_second": 127.352,
+      "eval_steps_per_second": 16.037,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 109736481521664.0,
+  "total_flos": 1426574259781632.0,
   "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 sha256:8e181bc4214b2cc34bfb22ae10e15a3814855d471909c4a1bc5911ce410a6e78
+oid sha256:b2e10855a7d8bac476e8e79f4afd43b810fb81fa2eee30c420b61ec7d246f02e
 size 6776