Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -10,23 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 8,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 4,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "up_proj",
-    "o_proj",
-    "down_proj",
-    "k_proj",
     "q_proj",
+    "gate_proj",
+    "k_proj",
     "v_proj",
-    "gate_proj"
+    "down_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 sha256:3447474c1eadcf4f901c99e8776f12703ebfa5acb68b872510304a7f0be6d86b
-size 14696
+oid sha256:b6cf0b38fd50b5592fcdd90cde67f3953803b845427a6da838198ae49e8910ea
+size 9048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db15b1c0ba74c5b202eea1a776cf1b2b9304bf9a895cd078cb783959b6ac7320
-size 39398
+oid sha256:0af2a114dc19c38ea0fe32439070f4761f409a156cb638aaa327dcd8483430c3
+size 28134

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
+oid sha256:89dbad7a5f4eb47d4580585d91b020d1a7f5dc2fd4d54175561c1eb48d2175e4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:e6da16eefab22daee3fb0999c7651be192feb36b73810bf419e9165c7023ec02
 size 1064

last-checkpoint/trainer_state.json

@@ -1,114 +1,34 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005047672462142457,
-  "eval_steps": 3,
-  "global_step": 9,
+  "epoch": 0.0002666666666666667,
+  "eval_steps": 500,
+  "global_step": 1,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0005608524957936063,
-      "grad_norm": 0.015257853083312511,
-      "learning_rate": 2e-05,
-      "loss": 11.9315,
+      "epoch": 0.0002666666666666667,
+      "grad_norm": 0.017395144328475,
+      "learning_rate": 0.0,
+      "loss": 11.9308,
       "step": 1
     },
     {
-      "epoch": 0.0005608524957936063,
-      "eval_loss": 11.931306838989258,
-      "eval_runtime": 2.6755,
-      "eval_samples_per_second": 280.695,
-      "eval_steps_per_second": 140.534,
+      "epoch": 0.0002666666666666667,
+      "eval_loss": 11.933906555175781,
+      "eval_runtime": 0.059,
+      "eval_samples_per_second": 271.03,
+      "eval_steps_per_second": 67.757,
       "step": 1
-    },
-    {
-      "epoch": 0.0011217049915872126,
-      "grad_norm": 0.009659971110522747,
-      "learning_rate": 4e-05,
-      "loss": 11.9304,
-      "step": 2
-    },
-    {
-      "epoch": 0.0016825574873808188,
-      "grad_norm": 0.011888088658452034,
-      "learning_rate": 6e-05,
-      "loss": 11.9319,
-      "step": 3
-    },
-    {
-      "epoch": 0.0016825574873808188,
-      "eval_loss": 11.931303977966309,
-      "eval_runtime": 2.7274,
-      "eval_samples_per_second": 275.355,
-      "eval_steps_per_second": 137.861,
-      "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.01530472096055746,
-      "learning_rate": 8e-05,
-      "loss": 11.9328,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": 0.0182462427765131,
-      "learning_rate": 0.0001,
-      "loss": 11.9248,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": 0.008574016392230988,
-      "learning_rate": 0.00012,
-      "loss": 11.926,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.93128776550293,
-      "eval_runtime": 2.8374,
-      "eval_samples_per_second": 264.68,
-      "eval_steps_per_second": 132.516,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": 0.013426216319203377,
-      "learning_rate": 0.00014,
-      "loss": 11.9324,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.006309770978987217,
-      "learning_rate": 0.00016,
-      "loss": 11.935,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": 0.015631036832928658,
-      "learning_rate": 0.00018,
-      "loss": 11.9287,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": 11.93126106262207,
-      "eval_runtime": 2.8029,
-      "eval_samples_per_second": 267.939,
-      "eval_steps_per_second": 134.148,
-      "step": 9
     }
   ],
   "logging_steps": 1,
-  "max_steps": 10,
+  "max_steps": 1,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 3,
+  "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -116,13 +36,13 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1092993024.0,
-  "train_batch_size": 2,
+  "total_flos": 10444800.0,
+  "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42859b767e48a28bd6aa4d7de82f9e080fc3f6e573f77325e209b5bb86fef1a3
+oid sha256:9728de9c04ba459f8a150ca989a490b015c26610cf896681f245b555b37edd32
 size 6776