Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "gate_proj",
+    "v_proj",
     "k_proj",
     "q_proj",
-    "v_proj",
     "o_proj",
     "down_proj",
-    "gate_proj"
+    "up_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 sha256:2ec3db661b00bab4f7b6da47ed3f3e0b3df0fb1e36e30b111dc6f28019c1c61d
+oid sha256:de422ca50a4d4480077592243659f2794756ab36a8449635d64e90cdfcfa2333
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1360b214dc305ce0c7fca0fdb3feecc9d03ca3af798b10af45b117b0f4bff123
+oid sha256:5d0ba80f16c2c94e21775a2856af67517c490b5afe3b70fa1114b06962e15827
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881ed1971ee90da02c9d8278916e25bf523f50547cc2f4f79366d2794d2ff939
+oid sha256:87583a48306ee1d35adf4173063a70066de7e46756273f7a10cc8987b7b54fd7
 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": 0.00049800796812749,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.006474103585657371,
+  "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": 0.00049800796812749,
       "eval_loss": NaN,
-      "eval_runtime": 57.8723,
-      "eval_samples_per_second": 14.618,
-      "eval_steps_per_second": 7.309,
+      "eval_runtime": 58.1469,
+      "eval_samples_per_second": 14.549,
+      "eval_steps_per_second": 7.275,
       "step": 1
+    },
+    {
+      "epoch": 0.00249003984063745,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0049800796812749,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0049800796812749,
+      "eval_loss": NaN,
+      "eval_runtime": 57.1906,
+      "eval_samples_per_second": 14.793,
+      "eval_steps_per_second": 7.396,
+      "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": 217829505761280.0,
+  "total_flos": 2701085871439872.0,
   "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 sha256:868286621688afdbefc89495cb0966782816031ee2c7fa332d97d5703d3230d2
+oid sha256:462a982b004846c5748aa61fe95700830c93f8db52e66be352c06c142ae5c04d
 size 6776