Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "k_proj",
-    "gate_proj",
-    "v_proj",
     "up_proj",
+    "down_proj",
+    "gate_proj",
     "o_proj",
-    "down_proj"
+    "v_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 sha256:68a369512a9df19cc38d8406ee0472fc379ade2ba2eb9eae4addfad498983251
+oid sha256:20dcfe1bf39321b720e82ea91671044d131a1bb2082db5fd9180d4226d3e472f
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ae1336463de3e9e02cbab814a0054f872601f7dceaac950a7e10856512eded
+oid sha256:fe773f2043084813bb2eee625f43a0fa2c6f07eefe923b76e20f6243fc7e051f
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4865c784751f08fb8deff9071128988f7eb961f669d74f7bc3864ebf22f64623
+oid sha256:b4d54922533a99f5b48c8c09cecf7d3009079b051f1aa5e7b604a383f3e69c83
 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": 0.00018389959082341041,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0023906946807043354,
+  "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": 0.00018389959082341041,
       "eval_loss": 1.2216368913650513,
-      "eval_runtime": 139.095,
-      "eval_samples_per_second": 16.464,
-      "eval_steps_per_second": 8.232,
+      "eval_runtime": 139.2415,
+      "eval_samples_per_second": 16.446,
+      "eval_steps_per_second": 8.223,
       "step": 1
+    },
+    {
+      "epoch": 0.0009194979541170521,
+      "grad_norm": 0.311225950717926,
+      "learning_rate": 5e-05,
+      "loss": 1.2753,
+      "step": 5
+    },
+    {
+      "epoch": 0.0018389959082341042,
+      "grad_norm": 0.36874568462371826,
+      "learning_rate": 0.0001,
+      "loss": 1.1951,
+      "step": 10
+    },
+    {
+      "epoch": 0.0018389959082341042,
+      "eval_loss": 1.1231805086135864,
+      "eval_runtime": 135.6701,
+      "eval_samples_per_second": 16.879,
+      "eval_steps_per_second": 8.44,
+      "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": 123007299747840.0,
+  "total_flos": 1763104629719040.0,
   "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:b74392e8badd63f15e8b9edcbbf269e136f3881a67b2a2fbe051cf4f5b4072a3
+oid sha256:12df241744a70b82d5b8058723d1ea1560cc54d3116fa01e9ebda8c22a85625c
 size 6776