Training in progress, step 4, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "v_proj",
-    "k_proj",
     "q_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
     "gate_proj",
-    "down_proj",
-    "up_proj"
+    "down_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 sha256:4552a8a22dd5569735e682a6a4951a6ae3e72157214b7d9d4bfc4bc84f5b00c8
+oid sha256:3f642c29a19f7001f56d25d8bf26f112769edde5998d20456a4f84a3ccb79c4f
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:dcca725865f8452db1cfb5a0618643e8845efef5b599c92e0cccc2f82476e609
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48707ce5b888f5fb4ed0bb81e0d8f92699172e8647e4e04f8cf50ce6a8cd793a
+oid sha256:bade30ee59540fd8c7e55f4754b4545929311eb046d50badc73ddb2a94bb2152
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:15cbfb53eda5550c271805f4bff07f52bac06bd6171dd491b0ac1e92e8437efb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07476635514018691,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.29906542056074764,
+  "eval_steps": 3,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,25 @@
     {
       "epoch": 0.07476635514018691,
       "eval_loss": NaN,
-      "eval_runtime": 3.561,
-      "eval_samples_per_second": 25.274,
-      "eval_steps_per_second": 3.37,
+      "eval_runtime": 3.5261,
+      "eval_samples_per_second": 25.524,
+      "eval_steps_per_second": 3.403,
       "step": 1
+    },
+    {
+      "epoch": 0.22429906542056074,
+      "eval_loss": NaN,
+      "eval_runtime": 2.0479,
+      "eval_samples_per_second": 43.947,
+      "eval_steps_per_second": 5.86,
+      "step": 3
     }
   ],
   "logging_steps": 10,
-  "max_steps": 1,
+  "max_steps": 14,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 4,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +37,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 518877213622272.0,
+  "total_flos": 2075508854489088.0,
   "train_batch_size": 8,
   "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:bbf14aa9949d462b868ec31ae385a7fb84f934e934aaed3f0647bc893083ae0c
+oid sha256:8e007adad79ee80e169a9cb8a199868a5773f153a5d83e19f9c42fdbdd8ce7d8
 size 6776