Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "k_proj",
-    "v_proj",
     "up_proj",
-    "q_proj",
+    "v_proj",
+    "down_proj",
     "gate_proj",
-    "down_proj"
+    "o_proj",
+    "q_proj",
+    "k_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 sha256:1152129a153221165e56fb5f6463db8285562295a7a19f4806e9a5395b80f63d
+oid sha256:eca097b83951fc437d37b35faaf2c28a32801c9cb0afd785a6124312f5833c9d
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882a4c886ce814f4de4a8225f950d13e76594f3d7a8872d5c8830901fdd53e84
+oid sha256:fede4208ff04dfdb995b788299dfacd82c979b8d77ee4e0635b5934395ae0a8d
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 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": 0.0003604902667627974,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004686373467916366,
+  "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": 0.0003604902667627974,
       "eval_loss": 9.072793960571289,
-      "eval_runtime": 14.4566,
-      "eval_samples_per_second": 80.863,
-      "eval_steps_per_second": 40.466,
+      "eval_runtime": 14.3551,
+      "eval_samples_per_second": 81.434,
+      "eval_steps_per_second": 40.752,
       "step": 1
+    },
+    {
+      "epoch": 0.001802451333813987,
+      "grad_norm": 13.476539611816406,
+      "learning_rate": 5e-05,
+      "loss": 8.6803,
+      "step": 5
+    },
+    {
+      "epoch": 0.003604902667627974,
+      "grad_norm": 10.52963638305664,
+      "learning_rate": 0.0001,
+      "loss": 8.4533,
+      "step": 10
+    },
+    {
+      "epoch": 0.003604902667627974,
+      "eval_loss": 8.595951080322266,
+      "eval_runtime": 14.1045,
+      "eval_samples_per_second": 82.881,
+      "eval_steps_per_second": 41.476,
+      "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": 65558544384.0,
+  "total_flos": 852261076992.0,
   "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:fd81c0badc3f746996cb1e52a03dd766799c07e5538c6e6fa64eb85c72a0b5ac
+oid sha256:a4423ffbe53b19992f861cde94b46ab16fe1e1178c7a3229231d98ee1a3eb151
 size 6776