Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e58d72a351d17511c06801431693e0b8793c63854302800c5471cb2fa9e91d3
+oid sha256:a13a2b75dfca66b2916e228c17af86792aab4ab4928749f3c5cfa7d518106f19
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98dc6672b69eacc052acee0177b66f2fb7f98d2d73bd8be51cd6182c72c1aea9
+oid sha256:f10e31d35198118c35d5828a532bb2df4c4299700a69b7a6348155882744eca5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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": 8.730193373783229e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0011349251385918198,
+  "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": 8.730193373783229e-05,
       "eval_loss": 1.5492833852767944,
-      "eval_runtime": 1265.0266,
-      "eval_samples_per_second": 3.813,
-      "eval_steps_per_second": 1.907,
+      "eval_runtime": 1034.2004,
+      "eval_samples_per_second": 4.664,
+      "eval_steps_per_second": 2.332,
       "step": 1
+    },
+    {
+      "epoch": 0.00043650966868916146,
+      "grad_norm": 0.7586553692817688,
+      "learning_rate": 5e-05,
+      "loss": 1.3781,
+      "step": 5
+    },
+    {
+      "epoch": 0.0008730193373783229,
+      "grad_norm": 1.0461653470993042,
+      "learning_rate": 0.0001,
+      "loss": 1.5803,
+      "step": 10
+    },
+    {
+      "epoch": 0.0008730193373783229,
+      "eval_loss": 1.5048344135284424,
+      "eval_runtime": 1283.3075,
+      "eval_samples_per_second": 3.758,
+      "eval_steps_per_second": 1.88,
+      "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": 184956424814592.0,
+  "total_flos": 2404433522589696.0,
   "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 sha256:42d0afeac4e15c20885a4cd2cbed98803caac767785e644fd1d691de44fb7cc3
+oid sha256:5e8b3ea98f3f01b33b9f553e7c041f78b5cc8d6dc35d5117cf25916f4a3b91a1
 size 6776