Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "o_proj",
     "down_proj",
+    "v_proj",
     "gate_proj",
-    "o_proj",
+    "k_proj",
     "up_proj",
-    "q_proj",
-    "v_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:f3919effb7c4d431f7b579d2b2bf8ec3e357a57f3b713587f45cdf0e466ce754
+oid sha256:16a4f9802e95e0053c8e5bd985ca22ef2f226357ec6854805622114dcebfbe3f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b22f1580eafa2e3345516de9a78578d04911f235539146d4acbef082bfbe1021
+oid sha256:893a578358edc20019bf0a012c5fee987b350aa1839e02176c6335bcda8c7bb1
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:6286a07b356beb4b76bbb49982b1e35c009b260102e0a6e40f5c518c1a9550e1
 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": 0.0014519056261343012,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.018874773139745917,
+  "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": 0.0014519056261343012,
       "eval_loss": 2.4837050437927246,
-      "eval_runtime": 34.7409,
-      "eval_samples_per_second": 8.348,
-      "eval_steps_per_second": 4.174,
+      "eval_runtime": 34.809,
+      "eval_samples_per_second": 8.331,
+      "eval_steps_per_second": 4.166,
       "step": 1
+    },
+    {
+      "epoch": 0.007259528130671506,
+      "grad_norm": 1.4090709686279297,
+      "learning_rate": 5e-05,
+      "loss": 2.4528,
+      "step": 5
+    },
+    {
+      "epoch": 0.014519056261343012,
+      "grad_norm": 1.6987773180007935,
+      "learning_rate": 0.0001,
+      "loss": 2.2668,
+      "step": 10
+    },
+    {
+      "epoch": 0.014519056261343012,
+      "eval_loss": 2.2202208042144775,
+      "eval_runtime": 35.1159,
+      "eval_samples_per_second": 8.258,
+      "eval_steps_per_second": 4.129,
+      "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": 369912849629184.0,
+  "total_flos": 4623910620364800.0,
   "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 sha256:626c74cb0e1f72335c4ad4de8be96ab765adda44bd37028e6b070c5b74fc9f36
+oid sha256:f3386a7be31b1d17774f60cddce496d906d003671dc02e6ff016c7eae5588445
 size 6776