Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,13 +21,13 @@
   "revision": null,
   "target_modules": [
     "gate",
-    "o_proj",
-    "v_proj",
     "w1",
+    "o_proj",
     "w2",
     "q_proj",
     "k_proj",
-    "w3"
+    "w3",
+    "v_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 sha256:01c2d05db7857bc27737f91e23916ad15633cc0f851c73f92a95c22b7a85b483
+oid sha256:5a27038e659e17c3180b8526f72b83502ac9a5173b04ef039c683cd543f5ee59
 size 144805440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99785a8b9f7f88c982932d36b9cdef572207c155985d4deaa3c7ffe24565df80
+oid sha256:cba3f4225fc1aa208aea940ab560a0eab4ab18c85d30dddc76839b19cf5e9c79
 size 74291604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6383626d85e1286f49fa537daf3ec3286b3f9ea5b27e9bd441d08d262782ff
+oid sha256:1f87458b56b81341706d06a4ede04bec93a0e13eb8ba6069748b3bb4cddc346b
 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": 0.0026367831245880024,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.034278180619644036,
+  "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": 0.0026367831245880024,
       "eval_loss": 9.952766418457031,
-      "eval_runtime": 19.697,
-      "eval_samples_per_second": 8.123,
-      "eval_steps_per_second": 4.062,
+      "eval_runtime": 19.7234,
+      "eval_samples_per_second": 8.112,
+      "eval_steps_per_second": 4.056,
       "step": 1
+    },
+    {
+      "epoch": 0.013183915622940013,
+      "grad_norm": 7.932442665100098,
+      "learning_rate": 5e-05,
+      "loss": 9.1812,
+      "step": 5
+    },
+    {
+      "epoch": 0.026367831245880026,
+      "grad_norm": 8.679454803466797,
+      "learning_rate": 0.0001,
+      "loss": 8.8656,
+      "step": 10
+    },
+    {
+      "epoch": 0.026367831245880026,
+      "eval_loss": 7.980339050292969,
+      "eval_runtime": 19.8797,
+      "eval_samples_per_second": 8.048,
+      "eval_steps_per_second": 4.024,
+      "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": 323875007102976.0,
+  "total_flos": 4210375092338688.0,
   "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 sha256:22110bf4427271019015c85c889bdbb91d30f36d2732e91ab893a8faa31cd523
+oid sha256:8dadeb1424a6c986b22d1509b200d96fde1795bcb6263ea630a5908622a07e38
 size 6776