Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "v_proj",
     "o_proj",
-    "k_proj",
     "down_proj",
-    "q_proj"
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "v_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 sha256:9f6cf5b4dfec7e3b74ae9fa287a794d2c1d57c7f2dc0eb3b1af6c17cc6348037
+oid sha256:4ed26db1cf798cdc1529be9bf308d0cc9012544f31bbeefb5862c581e68057a4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31033abbc6f9dcd74fda14068ad65435722322ae5c7bdd0545bee992b5f57589
+oid sha256:f51a83c7fa54fe12c07cc7a6017aec1c250bdbd7dd769a042d15ddb16763f621
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0525df66869b0adf8d756d9e95d76ef7874d6f8df8ffd52f14c9f432ae93afc8
+oid sha256:c25690fee540c8a083995f9d671371c1b023b3c333abe69506927a0de708bf9f
 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": 0.0010649627263045794,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.013844515441959531,
+  "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": 0.0010649627263045794,
       "eval_loss": 1.6592028141021729,
-      "eval_runtime": 35.2664,
-      "eval_samples_per_second": 11.229,
-      "eval_steps_per_second": 5.614,
+      "eval_runtime": 34.8289,
+      "eval_samples_per_second": 11.37,
+      "eval_steps_per_second": 5.685,
       "step": 1
+    },
+    {
+      "epoch": 0.005324813631522897,
+      "grad_norm": 0.9289127588272095,
+      "learning_rate": 5e-05,
+      "loss": 1.4958,
+      "step": 5
+    },
+    {
+      "epoch": 0.010649627263045794,
+      "grad_norm": 0.9269077181816101,
+      "learning_rate": 0.0001,
+      "loss": 1.7006,
+      "step": 10
+    },
+    {
+      "epoch": 0.010649627263045794,
+      "eval_loss": 1.5683319568634033,
+      "eval_runtime": 35.2172,
+      "eval_samples_per_second": 11.244,
+      "eval_steps_per_second": 5.622,
+      "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": 323673743425536.0,
+  "total_flos": 3329215646662656.0,
   "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 sha256:4f51c146006ff2467fc569e621083c9afd4e91e8e156c8a29fdd6e055d463718
+oid sha256:6c64cc809c47afcc18f66387de2bc07fca1627c25aef989e968f8018da579612
 size 6776