Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49e704b92b235ac44f45e6e503c34fb330b085d5b28bb58e4af65542ddb4b221
+oid sha256:472217efae7707b2675db5a9625c69b7858c1dad807b613f4a711e31654fde15
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b67e4814ee68340ec3c2df874521a0f4d8e5e2e8c42a8795862846922633c0fe
+oid sha256:d34cfcefeaf970fc31d4bb3708fc6bd9eb1de20f831abcfc0cd44ea23ed61346
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a50de3ecd1b9dd3f4fd61276cacff48c49a7b616391063a41547790d04f8152
+oid sha256:48900473ba9e70eaf1de889139c7aa3a04f9a37391cf86fcda68bcaac2c87d6a
 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": 0.0026542800265428003,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.034505640345056404,
+  "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": 0.0026542800265428003,
       "eval_loss": 1.4482953548431396,
-      "eval_runtime": 8.3088,
-      "eval_samples_per_second": 19.136,
-      "eval_steps_per_second": 9.628,
+      "eval_runtime": 8.4074,
+      "eval_samples_per_second": 18.912,
+      "eval_steps_per_second": 9.515,
       "step": 1
+    },
+    {
+      "epoch": 0.013271400132714002,
+      "grad_norm": 0.5261042714118958,
+      "learning_rate": 5e-05,
+      "loss": 1.3651,
+      "step": 5
+    },
+    {
+      "epoch": 0.026542800265428004,
+      "grad_norm": 0.548517107963562,
+      "learning_rate": 0.0001,
+      "loss": 1.5137,
+      "step": 10
+    },
+    {
+      "epoch": 0.026542800265428004,
+      "eval_loss": 1.435921549797058,
+      "eval_runtime": 6.2884,
+      "eval_samples_per_second": 25.284,
+      "eval_steps_per_second": 12.722,
+      "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": 17807632760832.0,
+  "total_flos": 224821363605504.0,
   "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:bbb410b750208dd7d4ca44b15129592be1ac1beafa057c6d063988009193384d
+oid sha256:30ba35c1732ce5876af94ee5229a1362f4732d1390d86b46506c3c05d766b361
 size 6776