Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "q_proj",
     "gate_proj",
     "down_proj",
-    "k_proj",
     "up_proj",
-    "o_proj",
     "v_proj",
-    "q_proj"
+    "o_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 sha256:62ca779798609100d44846962ad1fcaa677352a0908c510c26fd5c92528a2d83
+oid sha256:46b65855b338ff1b456d800792c661529c71919bb7a50ee5bb8fc6beb4918363
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322f5b17889539f730ac70621a5d996c198f87b44d63115fc08be62e4de545ea
+oid sha256:f66c52f1783b27a1d42f2f4191fa818c66531b25d2fd06dad7542bef6ad31e2b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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": 2.5154502391815186,
-      "eval_runtime": 24.5946,
-      "eval_samples_per_second": 3.659,
-      "eval_steps_per_second": 1.83,
+      "eval_runtime": 6.0947,
+      "eval_samples_per_second": 14.767,
+      "eval_steps_per_second": 7.383,
       "step": 1
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 7.17006254196167,
+      "learning_rate": 5e-05,
+      "loss": 9.3033,
+      "step": 5
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "grad_norm": 6.0110344886779785,
+      "learning_rate": 0.0001,
+      "loss": 8.4186,
+      "step": 10
+    },
+    {
+      "epoch": 0.04678362573099415,
+      "eval_loss": 2.278883457183838,
+      "eval_runtime": 6.1015,
+      "eval_samples_per_second": 14.75,
+      "eval_steps_per_second": 7.375,
+      "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": 162873313591296.0,
+  "total_flos": 2117353076686848.0,
   "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:effc137662bba77ad19a78117ce0d188df23d4a83365adcabde7e19e841d68c9
+oid sha256:a1b2ec10c9eee34983efa01f0045a4b84eaeb353862a08afae2686412c8d87db
 size 6776