Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "o_proj",
-    "up_proj",
     "q_proj",
-    "v_proj",
+    "down_proj",
+    "up_proj",
     "k_proj",
-    "down_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:c338b841fd89d9899e0caf9913ec7f669bdaa0ffd0f68a206f60826f4910fe9b
+oid sha256:37d359d63d494f31e5005aeaabe028c78c58a1e1fa9c6135316638841bb6ff1d
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab1326ea425dec2e4698eca4475f2ef6024f9641d5b78d9d1261362a10caa3b5
+oid sha256:bc5cf301cd7a94ae51d119d43b463708291400e3c0a82508a931a1024fbcc06e
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a81a9b7890bdf704e9b34fcbba9863620101f0015e924e4a60f04e5fece2c5
+oid sha256:f92ff5a5b676a9b8b9f1a4521e56d6a9c9ca74b909b133a54f52c8e597e8f5a1
 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": 0.00010654733365297533,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0013851153374886793,
+  "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": 0.00010654733365297533,
       "eval_loss": 2.4550228118896484,
-      "eval_runtime": 109.662,
-      "eval_samples_per_second": 36.038,
-      "eval_steps_per_second": 18.019,
+      "eval_runtime": 110.5566,
+      "eval_samples_per_second": 35.746,
+      "eval_steps_per_second": 17.873,
       "step": 1
+    },
+    {
+      "epoch": 0.0005327366682648767,
+      "grad_norm": 3.4158077239990234,
+      "learning_rate": 5e-05,
+      "loss": 2.43,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010654733365297534,
+      "grad_norm": 1.921109676361084,
+      "learning_rate": 0.0001,
+      "loss": 2.2942,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010654733365297534,
+      "eval_loss": 2.208928346633911,
+      "eval_runtime": 110.6655,
+      "eval_samples_per_second": 35.711,
+      "eval_steps_per_second": 17.856,
+      "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": 25579197825024.0,
+  "total_flos": 351713970094080.0,
   "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:a58711db86cee91eed5175652d67d9c540d2372411e07dc70a66ffcb6f352d45
+oid sha256:af8ce9937af3d4e2e74c17785658da9c7188d1c4448e5e1931627bf2fa687578
 size 6776