Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "gate_proj",
     "k_proj",
     "q_proj",
     "o_proj",
-    "gate_proj",
-    "up_proj",
-    "v_proj"
+    "v_proj",
+    "down_proj",
+    "up_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 sha256:51254ae84cee0cc79eedc082981acdee64d0b4dcf3d42bbf4d60cbd2582a28ec
+oid sha256:f4d402b9cb7024a53d6777302f6924d7e8c7f6921e591c0a78b4357ae0a75fa4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23ca43d6f0b73dd43af521a252a7b2899ef9e4e13a0ff0837e558135d6f373d9
+oid sha256:0bcc5209d3528a3bf27446fb10f8d9cec9db364f2df732b74b78cac2f62bae42
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7484c1a22d352ce83f5f015e796e9ceb701757f35d7de923c63231cfddeda93
+oid sha256:aa7f64ab8cf96f1118762f8652227986903e4e175b8bcf5e33b2a546271ec0ca
 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": 2.0155702804162153e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00026202413645410797,
+  "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": 2.0155702804162153e-05,
       "eval_loss": 1.8410059213638306,
-      "eval_runtime": 1935.568,
-      "eval_samples_per_second": 10.793,
-      "eval_steps_per_second": 5.396,
+      "eval_runtime": 1911.8733,
+      "eval_samples_per_second": 10.926,
+      "eval_steps_per_second": 5.463,
       "step": 1
+    },
+    {
+      "epoch": 0.00010077851402081077,
+      "grad_norm": 1.9838496446609497,
+      "learning_rate": 5e-05,
+      "loss": 1.8474,
+      "step": 5
+    },
+    {
+      "epoch": 0.00020155702804162154,
+      "grad_norm": 1.3555948734283447,
+      "learning_rate": 0.0001,
+      "loss": 1.6573,
+      "step": 10
+    },
+    {
+      "epoch": 0.00020155702804162154,
+      "eval_loss": 1.4620121717453003,
+      "eval_runtime": 1917.889,
+      "eval_samples_per_second": 10.892,
+      "eval_steps_per_second": 5.446,
+      "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": 277434637221888.0,
+  "total_flos": 3606650283884544.0,
   "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 sha256:0bf8fc87b9dd6a9233bef64db94c0890d5a47b09836dff75f06861ab73bb2f50
+oid sha256:cc6bf3bf5e22ad8a59c9f34aceb832a9317ac714000dbe5c7aa3ed9a925fd387
 size 6776