Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
     "q_proj",
+    "down_proj",
     "gate_proj",
     "o_proj",
     "k_proj",
-    "v_proj",
-    "down_proj"
+    "up_proj",
+    "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 sha256:1f68575dee3f94cedd53e9f87f4f1b2e25d222c7bb169611098a6eae80044dd4
+oid sha256:c136b41af48c22e0b60fb793a02309dce3cfe1936cce7fe1c48a02c3285c9d7b
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7a06a1492b09f6e7b7f85faeadf45c9c7b97bc589fa7dc2c2c9dd60d641495f
+oid sha256:629876ca08b3768ee7876f4fcf51cc2bf0843cb6a2819e0f51b45a43563adad3
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed413ffc1f3bedbef14e57f493d3e8611649fb25a4d11d4dded6eabfeeb78de
+oid sha256:df39d950c848edf06ddc44337bcda461f437550743c932459d37fa2b0c5b0d66
 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": 0.0004253056884635832,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005528973950026581,
+  "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": 0.0004253056884635832,
       "eval_loss": 7.85447359085083,
-      "eval_runtime": 42.5688,
-      "eval_samples_per_second": 23.256,
-      "eval_steps_per_second": 11.628,
+      "eval_runtime": 43.0645,
+      "eval_samples_per_second": 22.989,
+      "eval_steps_per_second": 11.494,
       "step": 1
+    },
+    {
+      "epoch": 0.002126528442317916,
+      "grad_norm": 6.904982089996338,
+      "learning_rate": 5e-05,
+      "loss": 8.2507,
+      "step": 5
+    },
+    {
+      "epoch": 0.004253056884635832,
+      "grad_norm": 8.058303833007812,
+      "learning_rate": 0.0001,
+      "loss": 7.2992,
+      "step": 10
+    },
+    {
+      "epoch": 0.004253056884635832,
+      "eval_loss": 6.549283981323242,
+      "eval_runtime": 42.3073,
+      "eval_samples_per_second": 23.4,
+      "eval_steps_per_second": 11.7,
+      "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": 40537282314240.0,
+  "total_flos": 599951778250752.0,
   "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 sha256:1913613e4881acbc49919ced88163786823e6eaea442c2ed99306eaedfeb7041
+oid sha256:9eca55169e2444aa263ac9f7fd2476856bb69a7c64ef8a449a52dfda62df1343
 size 6776