Training in progress, epoch 0, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "k_proj",
-    "up_proj",
     "v_proj",
     "down_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d253b566d126f3aba50addeec7b7eb765dcd73cb4b88bcfa0193f7cdfb91c3f5
+oid sha256:8dfe9076ca68332c8800b76be309707308999cea6fde6c924587a91918a82301
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d7ca924fd1345c00abf75278e6b67d1da97a8585f9d4fe25064f0dcd089c7f
+oid sha256:fd2f3dd40831dcb9a61550b30ceb021fd76a499faf698e24e0372cfb55613941
 size 107046

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adef08fda30a046b79221275438406fd995dd5a4dadb0a71a27682a7dcae8f3b
+oid sha256:8cc6143655f9449cd8116f34973ede555de22e2b5f4efa316d0986434dbbbc1d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ac0c876d99cedd1c7e14354171b8bdaaea7163f00b90c59253d9bf8b43e991
+oid sha256:0c429fe7554e31e133d2b97a95081dbbed81a5b94f15c6efd193ee9c92fb8a1b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,99 +1,40 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0020964360587,
+  "epoch": 0.9979035639412998,
   "eval_steps": 500,
-  "global_step": 358,
+  "global_step": 119,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.4192872117400419,
-      "grad_norm": 0.057723674923181534,
-      "learning_rate": 0.00021813031161473087,
-      "loss": 11.9272,
+      "grad_norm": 0.06033749505877495,
+      "learning_rate": 0.00019230769230769233,
+      "loss": 11.9275,
       "step": 50
     },
     {
       "epoch": 0.8385744234800838,
-      "grad_norm": 0.04375343769788742,
-      "learning_rate": 0.00018271954674220964,
-      "loss": 11.9208,
+      "grad_norm": 0.050237834453582764,
+      "learning_rate": 0.0001282051282051282,
+      "loss": 11.9214,
       "step": 100
     },
     {
       "epoch": 0.9979035639412998,
-      "eval_loss": 11.919021606445312,
-      "eval_runtime": 0.4164,
-      "eval_samples_per_second": 242.533,
-      "eval_steps_per_second": 62.434,
+      "eval_loss": 11.919645309448242,
+      "eval_runtime": 0.4167,
+      "eval_samples_per_second": 242.397,
+      "eval_steps_per_second": 62.399,
       "step": 119
-    },
-    {
-      "epoch": 1.2578616352201257,
-      "grad_norm": 0.028496425598859787,
-      "learning_rate": 0.00014730878186968837,
-      "loss": 12.1057,
-      "step": 150
-    },
-    {
-      "epoch": 1.6771488469601676,
-      "grad_norm": 0.027717996388673782,
-      "learning_rate": 0.00011189801699716715,
-      "loss": 11.9206,
-      "step": 200
-    },
-    {
-      "epoch": 1.9958071278825997,
-      "eval_loss": 11.916767120361328,
-      "eval_runtime": 0.4141,
-      "eval_samples_per_second": 243.91,
-      "eval_steps_per_second": 62.789,
-      "step": 238
-    },
-    {
-      "epoch": 2.0964360587002098,
-      "grad_norm": 0.03638681024312973,
-      "learning_rate": 7.64872521246459e-05,
-      "loss": 12.0807,
-      "step": 250
-    },
-    {
-      "epoch": 2.5157232704402515,
-      "grad_norm": 0.029723290354013443,
-      "learning_rate": 4.107648725212465e-05,
-      "loss": 11.927,
-      "step": 300
-    },
-    {
-      "epoch": 2.9350104821802936,
-      "grad_norm": 0.08462727814912796,
-      "learning_rate": 5.6657223796034e-06,
-      "loss": 11.916,
-      "step": 350
-    },
-    {
-      "epoch": 2.9937106918238996,
-      "eval_loss": 11.916586875915527,
-      "eval_runtime": 0.4094,
-      "eval_samples_per_second": 246.686,
-      "eval_steps_per_second": 63.503,
-      "step": 357
-    },
-    {
-      "epoch": 3.0020964360587,
-      "eval_loss": 11.916298866271973,
-      "eval_runtime": 0.4304,
-      "eval_samples_per_second": 234.654,
-      "eval_steps_per_second": 60.406,
-      "step": 358
     }
   ],
   "logging_steps": 50,
-  "max_steps": 358,
+  "max_steps": 200,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -102,12 +43,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 402704130048.0,
+  "total_flos": 134180413440.0,
   "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 sha256:0b72ad6f8496316ca67ff95e24c67b4d45a7065ba4f49d3236072eb77840500f
+oid sha256:fe1138b5d37c58217051b42dbc89cbbffcf2cf2a49a47b4580082cd863c6a61f
 size 6776