Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "o_proj",
     "up_proj",
-    "q_proj",
     "gate_proj",
+    "q_proj",
     "k_proj",
+    "down_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c1d2bc8c7b88e484724f4a72a20bffb23a0286072242cab94fe824188b648f3
+oid sha256:5488cc2e2b855a246cfb63a50d8e8f62e912de203053a9124406a57805938220
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdcaaa963dd9cc804ada4d487fd985830c38a0960827695ccbf8a3b3d4e881fe
+oid sha256:30f4ef5ed08eb2a58ab44fea060c07d35f388a4461044c12983e01f9306bd62d
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a1e11f532e67beeeeeaf9c2ddf2a6ed5e116ee96012aebc5d0634822ecd38f7
+oid sha256:ddb815a3dacb7e60bd913a1d3d924db89cf28af23f33eb9fe2eaa870fd378154
 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": 0.004678362573099415,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0608187134502924,
+  "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": 0.004678362573099415,
       "eval_loss": 2.005504608154297,
-      "eval_runtime": 4.736,
-      "eval_samples_per_second": 19.003,
-      "eval_steps_per_second": 9.502,
+      "eval_runtime": 4.0241,
+      "eval_samples_per_second": 22.365,
+      "eval_steps_per_second": 11.183,
       "step": 1
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 0.7950891256332397,
+      "learning_rate": 5e-05,
+      "loss": 2.0743,
+      "step": 5
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 1.2534737586975098,
+      "learning_rate": 0.0001,
+      "loss": 2.0283,
+      "step": 10
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "eval_loss": 1.9290282726287842,
+      "eval_runtime": 2.8458,
+      "eval_samples_per_second": 31.626,
+      "eval_steps_per_second": 15.813,
+      "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": 48109103087616.0,
+  "total_flos": 583322874937344.0,
   "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 sha256:0beb9e3dfdcf3db10cfcd04e84e9a4aff9010af81f25b73bd5ed0af4243977eb
+oid sha256:8f231729bb9e37f6f1727c4541ad17ee07fa4bf507ef85eb8d3006967374cb66
 size 6776