Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
+    "down_proj",
     "gate_proj",
-    "o_proj",
-    "k_proj",
     "q_proj",
-    "down_proj"
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_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 sha256:089f2cb07ea63efee708e7be2a09ebfb58a98ebc8b3cefc6ae6db25c45b29da3
+oid sha256:d191980d7e011eabcf83a0d05f8ee032e64e0c005a8a2f0622203291e579d5d1
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b053e325452b631e7225982d71b12727b1021b22e976becf4b966dbc1c8b959
+oid sha256:2885e123662980ef740ad9c8bd24d87373f837193839ecd74935567bb53ca68f
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
 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": 0.00023559901048415596,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0030627871362940277,
+  "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": 0.00023559901048415596,
       "eval_loss": 10.376893043518066,
-      "eval_runtime": 11.1811,
-      "eval_samples_per_second": 159.912,
-      "eval_steps_per_second": 79.956,
+      "eval_runtime": 10.972,
+      "eval_samples_per_second": 162.96,
+      "eval_steps_per_second": 81.48,
       "step": 1
+    },
+    {
+      "epoch": 0.0011779950524207798,
+      "grad_norm": 0.3874177634716034,
+      "learning_rate": 5e-05,
+      "loss": 41.5082,
+      "step": 5
+    },
+    {
+      "epoch": 0.0023559901048415596,
+      "grad_norm": 0.3574215769767761,
+      "learning_rate": 0.0001,
+      "loss": 41.4991,
+      "step": 10
+    },
+    {
+      "epoch": 0.0023559901048415596,
+      "eval_loss": 10.376096725463867,
+      "eval_runtime": 11.0366,
+      "eval_samples_per_second": 162.007,
+      "eval_steps_per_second": 81.003,
+      "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": 51329630208.0,
+  "total_flos": 667285192704.0,
   "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:ac3b2f75b3229b68b59061234b0dec1316e3e862935930212bdeaa959f391913
+oid sha256:ae0218b10a534502f1e8b8120a9a3fd62a63a6fff9c08da76cf0201f578e4037
 size 6776