Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
+    "up_proj",
+    "k_proj",
     "down_proj",
     "v_proj",
     "o_proj",
-    "k_proj",
-    "up_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 sha256:0969afa9e1011cf1bab8b739ef82b7860500bbe938a8edb2fd04599004ae7b4c
+oid sha256:42cb1eb3ed5419c374edc8e4af60fb61b18e60bff030198976f7699d434f27b1
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a529f91dd3af936ee3accfb6bc70eeb1fa1834e896892d9f229a3aed3e273f8
+oid sha256:22e44c3f4c1267fcd8bba6ab71707e54926eb0eaa928fb57bc499d084873eeee
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486942267fe9e9626b2afeb9aa1e52deb2eb52f3c6033a0fffce7ee5b86e5efa
+oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
 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": 0.00024454362046830104,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0031790670660879136,
+  "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": 0.00024454362046830104,
       "eval_loss": 7.183546543121338,
-      "eval_runtime": 186.5181,
-      "eval_samples_per_second": 9.232,
-      "eval_steps_per_second": 4.616,
+      "eval_runtime": 187.0794,
+      "eval_samples_per_second": 9.205,
+      "eval_steps_per_second": 4.602,
       "step": 1
+    },
+    {
+      "epoch": 0.001222718102341505,
+      "grad_norm": 17.202749252319336,
+      "learning_rate": 5e-05,
+      "loss": 7.3138,
+      "step": 5
+    },
+    {
+      "epoch": 0.00244543620468301,
+      "grad_norm": 14.147286415100098,
+      "learning_rate": 0.0001,
+      "loss": 5.2795,
+      "step": 10
+    },
+    {
+      "epoch": 0.00244543620468301,
+      "eval_loss": 3.5840988159179688,
+      "eval_runtime": 190.3052,
+      "eval_samples_per_second": 9.049,
+      "eval_steps_per_second": 4.524,
+      "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": 191109141626880.0,
+  "total_flos": 2484418841149440.0,
   "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 sha256:58521982f83f89d0091532a09f3fbcbd0cca8e88f9313bd04234284bdbae6dc1
+oid sha256:a9fbd19b4e39e390b654ae62773c8bd7a6e44c8f2db9b2d06d3825cc244e2ad2
 size 6776