Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "v_proj",
-    "q_proj",
-    "gate_proj",
     "down_proj",
-    "up_proj",
-    "k_proj"
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_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 sha256:9918f1381a6c1a88174f43f47138f293cfc3a995d30fe8168d31884dd107a8fb
+oid sha256:99cafc3c9fb5fca8c01ed5df7b3fb99ecf6f89887b831ea3b830ea5b15b05d63
 size 114106856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562bbdd2774b9982f6e8c1b43e52d90af265fafaaed836cfb9ae5e6743c9a273
+oid sha256:290f1d689f9a2aeeaf83c0d12c42534ae1e3953d2beff34eb7c9cd64074a4e9e
 size 58562260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cee1d2f68de4a719aea4937b4c7c41801f3222b38c7d482b730834b7290e765
+oid sha256:942b61c8ab06a2c1f2a4404410ef618600837f075fef1b731f8a7b1ed464ff15
 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": 0.0004241331778178348,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005513731311631852,
+  "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": 0.0004241331778178348,
       "eval_loss": NaN,
-      "eval_runtime": 157.5743,
-      "eval_samples_per_second": 6.302,
-      "eval_steps_per_second": 3.154,
+      "eval_runtime": 135.2699,
+      "eval_samples_per_second": 7.341,
+      "eval_steps_per_second": 3.674,
       "step": 1
+    },
+    {
+      "epoch": 0.002120665889089174,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.004241331778178348,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.004241331778178348,
+      "eval_loss": NaN,
+      "eval_runtime": 134.469,
+      "eval_samples_per_second": 7.385,
+      "eval_steps_per_second": 3.696,
+      "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": 285209442385920.0,
+  "total_flos": 3707722751016960.0,
   "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 sha256:1047e72b808cc93b6de14b347405f2dd2bc664ade980727611ba59031a1cbcb4
+oid sha256:69a9c717e30609b3667b7ec9692359765244431b2e2f9c4802abadb29dd17f93
 size 6776