Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "v_proj",
     "up_proj",
+    "k_proj",
     "down_proj",
+    "q_proj",
     "o_proj",
-    "k_proj",
-    "gate_proj",
-    "q_proj"
+    "gate_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 sha256:751c61640093b3f127d9dd6ced0a5b7fede7c7999053aa7d4bf2daf5bb8162ff
+oid sha256:390304a4585b93766ac7c6a3e3a7bd55001aa6d98d926e58ee24cf19b907d120
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635d1ef381f16d943aa405f12ee71e0ed68064dca0f600c69d5b0b8a47270ddc
+oid sha256:2eb6461bfc7025f7aaf2bef579dd95948eb1d48cfae8cd4a9e11d901c4ac29bf
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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": 0.0008806693086745927,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.011448701012769706,
+  "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": 0.0008806693086745927,
       "eval_loss": 2.842715263366699,
-      "eval_runtime": 27.9906,
-      "eval_samples_per_second": 17.113,
-      "eval_steps_per_second": 8.574,
+      "eval_runtime": 28.0509,
+      "eval_samples_per_second": 17.076,
+      "eval_steps_per_second": 8.556,
       "step": 1
+    },
+    {
+      "epoch": 0.004403346543372964,
+      "grad_norm": 3.535202741622925,
+      "learning_rate": 5e-05,
+      "loss": 2.7568,
+      "step": 5
+    },
+    {
+      "epoch": 0.008806693086745927,
+      "grad_norm": 2.774446487426758,
+      "learning_rate": 0.0001,
+      "loss": 2.427,
+      "step": 10
+    },
+    {
+      "epoch": 0.008806693086745927,
+      "eval_loss": 1.8638564348220825,
+      "eval_runtime": 28.2356,
+      "eval_samples_per_second": 16.964,
+      "eval_steps_per_second": 8.5,
+      "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": 164782292336640.0,
+  "total_flos": 2142169800376320.0,
   "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 sha256:4c36d01b6a6bdd775d924b600c71f58d273ad00a209deb2e7b252c1b53b88d18
+oid sha256:34fb7d7ef67ef39748cb9b44218ef2af7d86010d7b96ad8bb9b0de278b0dbc86
 size 6776