Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
+    "o_proj",
     "k_proj",
     "gate_proj",
     "q_proj",
-    "o_proj",
-    "down_proj",
-    "v_proj"
+    "v_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:ea250b957417ccfdff6ccae4d8575068ad5e362d0eb5d6a10dafc0587b2d87d0
+oid sha256:2e47748e2fdfffe8b3b02c0f984c2cc5be5d769fe01365f49602f727ae7119f8
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e87822a85276550902c22f72a0cbedb73f00278fea822074e57406b471d5f953
+oid sha256:a688ce0b47907670bc222ce32da643d67602df5e44f8818186b13c0af128f895
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:486942267fe9e9626b2afeb9aa1e52deb2eb52f3c6033a0fffce7ee5b86e5efa
+oid sha256:c5644a0717f1231448981eced6544705649d1cd238d725b15969f77f29be3b8e
 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": 0.0004575611988103409,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005948295584534431,
+  "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": 0.0004575611988103409,
       "eval_loss": 5.08507776260376,
-      "eval_runtime": 138.6164,
-      "eval_samples_per_second": 6.644,
-      "eval_steps_per_second": 3.326,
+      "eval_runtime": 169.1763,
+      "eval_samples_per_second": 5.444,
+      "eval_steps_per_second": 2.725,
       "step": 1
+    },
+    {
+      "epoch": 0.0022878059940517046,
+      "grad_norm": 30.90808868408203,
+      "learning_rate": 5e-05,
+      "loss": 4.6912,
+      "step": 5
+    },
+    {
+      "epoch": 0.004575611988103409,
+      "grad_norm": 10.183568000793457,
+      "learning_rate": 0.0001,
+      "loss": 0.9795,
+      "step": 10
+    },
+    {
+      "epoch": 0.004575611988103409,
+      "eval_loss": 0.2875328063964844,
+      "eval_runtime": 177.2332,
+      "eval_samples_per_second": 5.197,
+      "eval_steps_per_second": 2.601,
+      "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": 191109141626880.0,
+  "total_flos": 2484418841149440.0,
   "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:d6584eb33dc90bbe4503a908ed629cc3af4e0c474e63ceb00d41df3a39b4a6b0
+oid sha256:f4531970d508319c6f5c7516e1950a4c4cabb891ef71b4d0a59570815a47642f
 size 6776