Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
+    "down_proj",
+    "k_proj",
     "o_proj",
-    "v_proj",
     "up_proj",
-    "down_proj",
     "gate_proj",
-    "k_proj"
+    "v_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 sha256:4998de18f74674612e70c4326b904cfc500f9995221b39445fd76b3242168142
+oid sha256:c26dbdcce0564db1e75e6eb0b1c8bdda8cadf7c1cfd196a0e6e8af5c763ac618
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2db7c0c81bff27408892201a9973d40f19220cf72549aa56dff033a90010f8e
+oid sha256:8e10cae68928eeb8003c596f9c890ad56a41b36e82868e4476ac09368d6a9b92
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847da2026e6983c4161d87b22828e3d5b40be8301738cb9b9c8194c09c890984
+oid sha256:c7827bfc587d2b093f2fbabab8eafd8d5b11c8b91fe605dbe58f63e7b6b5350c
 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": 0.0001625619767536373,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.002113305697797285,
+  "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": 0.0001625619767536373,
       "eval_loss": 1.6511867046356201,
-      "eval_runtime": 73.99,
-      "eval_samples_per_second": 35.018,
-      "eval_steps_per_second": 17.516,
+      "eval_runtime": 74.5602,
+      "eval_samples_per_second": 34.75,
+      "eval_steps_per_second": 17.382,
       "step": 1
+    },
+    {
+      "epoch": 0.0008128098837681866,
+      "grad_norm": 0.17820429801940918,
+      "learning_rate": 5e-05,
+      "loss": 1.6622,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016256197675363732,
+      "grad_norm": 0.3048231899738312,
+      "learning_rate": 0.0001,
+      "loss": 1.5982,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016256197675363732,
+      "eval_loss": 1.649460792541504,
+      "eval_runtime": 74.5937,
+      "eval_samples_per_second": 34.735,
+      "eval_steps_per_second": 17.374,
+      "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": 31973997281280.0,
+  "total_flos": 402872365744128.0,
   "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 sha256:95615bbd7c456e8abd440b26fc3a7af5288b534ba8e4ae0dc8bc0e22f974cb42
+oid sha256:503f3c3effd92ef96517e2e88166f447a596af44af41473c1a5c03e16d8eff63
 size 6776