Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
     "up_proj",
-    "q_proj",
+    "gate_proj",
     "down_proj",
     "v_proj",
-    "gate_proj",
-    "o_proj"
+    "o_proj",
+    "k_proj",
+    "q_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:df6689e2f578fbaf21d84eb6d1855558daa47d0ebae804222fface57e23ccf06
+oid sha256:28ecab03f46099302d89246504bcee438c176917b17835a1cd42da82ab53182a
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29f7afc7e3119428d25d28a4b5c1d04d4a2fe59b9f1401f26277e673a6fbf8f5
+oid sha256:d71ec22900c9235d8970e1163d1c71cc318465759605eb44e5b04d9364f8f0e4
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:679ecdaf40568d872b059363098e6daca106d64448dd721e63c6883eecad12d7
+oid sha256:dc12b3ebfd598da93336aea3b9e623a1adcbdea90c1ade145e09bc2a56a621b5
 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": 0.0038461538461538464,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.05,
+  "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": 0.0038461538461538464,
       "eval_loss": 3.8364155292510986,
-      "eval_runtime": 4.5099,
-      "eval_samples_per_second": 24.391,
-      "eval_steps_per_second": 12.196,
+      "eval_runtime": 4.3367,
+      "eval_samples_per_second": 25.365,
+      "eval_steps_per_second": 12.683,
       "step": 1
+    },
+    {
+      "epoch": 0.019230769230769232,
+      "grad_norm": 15.092826843261719,
+      "learning_rate": 5e-05,
+      "loss": 3.7393,
+      "step": 5
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "grad_norm": 6.490390300750732,
+      "learning_rate": 0.0001,
+      "loss": 3.1124,
+      "step": 10
+    },
+    {
+      "epoch": 0.038461538461538464,
+      "eval_loss": 2.4712672233581543,
+      "eval_runtime": 3.609,
+      "eval_samples_per_second": 30.479,
+      "eval_steps_per_second": 15.24,
+      "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": 8903816380416.0,
+  "total_flos": 115749612945408.0,
   "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 sha256:7f861f8979b71fcb8a27169e9ff1a31a5036fc77479e724eb7f33868acb173a5
+oid sha256:4c3115d9c24f06f07365bbb5b807466ad03164edb422981d31e8fcbc50438803
 size 6776