Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "v_proj",
-    "gate_proj",
+    "k_proj",
     "q_proj",
+    "v_proj",
     "down_proj",
     "o_proj",
-    "k_proj"
+    "up_proj",
+    "gate_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:b3f93e4b9b96584759de456782dc60a7e5068d36b3c17a3f6972c828618995af
+oid sha256:b678e7bf1677a175fea27faa499ac73a4e67f832f5c64cc70c6298cb317c662f
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba915761e1b241a21b4fd2e1e47ab781d3c02655aedc8ddc9261ace2dfd70f3
+oid sha256:caf5c627eb9fcfb39d7b5b726231fa2ff79edd928bbee3315aa5477f2b033a6d
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db5312ddb8f626229a291c72b544634e2d97dd8ec4ceca4550f1b24f37a77647
+oid sha256:41e8229120dce69fa1081c29f9ca7f12647fb8db9c60a1f8dce12e8d0bda6beb
 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": 0.00033225350942769335,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004319295622560013,
+  "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": 0.00033225350942769335,
       "eval_loss": 1.356743574142456,
-      "eval_runtime": 70.8598,
-      "eval_samples_per_second": 17.894,
-      "eval_steps_per_second": 8.947,
+      "eval_runtime": 69.6151,
+      "eval_samples_per_second": 18.214,
+      "eval_steps_per_second": 9.107,
       "step": 1
+    },
+    {
+      "epoch": 0.0016612675471384666,
+      "grad_norm": 1.057161569595337,
+      "learning_rate": 5e-05,
+      "loss": 1.2723,
+      "step": 5
+    },
+    {
+      "epoch": 0.003322535094276933,
+      "grad_norm": 1.0211741924285889,
+      "learning_rate": 0.0001,
+      "loss": 1.2354,
+      "step": 10
+    },
+    {
+      "epoch": 0.003322535094276933,
+      "eval_loss": 1.090079426765442,
+      "eval_runtime": 69.432,
+      "eval_samples_per_second": 18.262,
+      "eval_steps_per_second": 9.131,
+      "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": 50009733070848.0,
+  "total_flos": 650126529921024.0,
   "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:cdea783cb006cfbd6f966f338f108d12cb5f4773d37425385fba56abc6d2b337
+oid sha256:b7df3ab1426c1cb29a580357514332f2f890c6676605bc4539122fbcf8c7186f
 size 6776