Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1213660373ae123c094b8116ac58b8a837794921d1dda0e9e3bcf54769a066c2
+oid sha256:037c5ffa3063ef38ebb486ccfcede2f41449c1689b1f475dacc9b5e056511fc2
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb999ca0c6bea46686aae9d745106bb9832160758e15a16b7c5891574507485
+oid sha256:63cbeb1133ce7ecd9e153e9a87026e8d65e7592acec86463b48424ea5330eed5
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
 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": 0.0008592910848549946,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01117078410311493,
+  "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": 0.0008592910848549946,
       "eval_loss": 10.392930030822754,
-      "eval_runtime": 9.3759,
-      "eval_samples_per_second": 52.262,
-      "eval_steps_per_second": 26.131,
+      "eval_runtime": 9.3711,
+      "eval_samples_per_second": 52.289,
+      "eval_steps_per_second": 26.144,
       "step": 1
+    },
+    {
+      "epoch": 0.004296455424274973,
+      "grad_norm": 0.12017610669136047,
+      "learning_rate": 5e-05,
+      "loss": 10.3991,
+      "step": 5
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "grad_norm": 0.1276823878288269,
+      "learning_rate": 0.0001,
+      "loss": 10.3839,
+      "step": 10
+    },
+    {
+      "epoch": 0.008592910848549946,
+      "eval_loss": 10.391303062438965,
+      "eval_runtime": 9.3631,
+      "eval_samples_per_second": 52.333,
+      "eval_steps_per_second": 26.166,
+      "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": 22629089280.0,
+  "total_flos": 294178160640.0,
   "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:c0dda948268ff1474a65ccb4a9a36df277f75f5b36f671a3fcb8e3fc09763724
+oid sha256:a242acb91fd25fafcb5858314f7101ca1dbee2b1095f60f86b5b61986a2fd28d
 size 6776